No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
A Survey of Palmprint Recognition
Abstract
Palmprint recognition has been investigated over 10 years. During this period, many different problems related to palmprint recognition have been addressed. This paper provides an overview of current palmprint research, describing in particular capture devices, preprocessing, verification algorithms, palmprint-related fusion, algorithms especially designed for real-time palmprint identification in large databases and measures for protecting palmprint systems and users’ privacy. Finally, some suggestion is offered.
... [8][9][10][11] Lip prints are the fissures and lines found in the transition zone between the inner labial mucosa and the outer skin of the lips. [2,4,9,10,[12][13][14][15][16][17][18][19] They are verified to recover after undergoing alterations like minor trauma, inflammation, and diseases like herpes; hence, they play a beneficial role in human identification. [2,8,12] Although there are several classifications for lip prints, the most widely used classification was by Suzuki and Tsuchihashi and it is as follows [2,5,7,8,[12][13][14][15] : [ Figure 1]. 1. Type I: vertical grooves that run across the entire lip. 2. Type I': vertical grooves that do not cover the entire lip. ...
... [16] The science of dermatoglyphics involves the study of palmprints and fingerprints and was coined by Cummins and Midlo in 1926. [2,[17][18][19][20] Palmprints are more distinctive than fingerprints because they include more information. [2,17] Detailed analysis of palmprints has become vital to identifying the suspect and the related crime scene. ...
... [25] The presence of the Y chromosome, as well as high testosterone levels, causes a delay in maturation. [19] The establishment of dactyloscopy and cheiloscopy can be used as a reference in criminal case studies and civil litigations that may be useful, particularly in forensic science and justice. Only very few studies have been successfully established with lip print inheritance, whereas studies on the inheritance of palmprints are scanty. ...
INTRODUCTION Forensic sciences deal with key areas to be included in judicial makeup that has been approved by both the court and the scientific community, which distinguishes truth from forged. [1,2] Identification of individuals is a crucial task in forensic investigation. [3,4] Forensic odontology approaches include rugoscopy, cheiloscopy, bite marks, Background: Forensic sciences deal with key areas to be included in judicial makeup that has been approved by both the court and the scientific community, which distinguishes truth from counterfeit. Lip and palmprints are one of a kind and do not change during the lifetime of a person unless any pathologies. Objectives: To evaluate the heritability, and gender dimorphism of lip and palm prints among parents and their offspring. Methods: A total of 280 participants were included in the study. Lip and palm prints were collected from participants using a digital camera. The photographic data obtained is subjected to Adobe Photoshop and analysed for inheritance. Gender dimorphism is evaluated by the predominant lip pattern and palm ridge count in four designated areas. Results: A positive resemblance of 28.4% was found between parents and offspring in lips, and for the right palm, it was 60.2% and 55.12% for the left palm (principal lines) which are statistically insignificant. In all six quadrants, the most predominant lip pattern found in males is type 5, and in females, type 1 1. The mean palm ridge density was significantly higher among females than males in all designated areas. Conclusion: The digital method of analysing lip and palm print images with Adobe Photoshop 7 software is a convenient method that allows for better visualisation and easier lip and palm print recording and identification. Considerable inheritance patterns and gender dimorphism were observed that aid in personal identification.
... [8][9][10][11] Lip prints are the fissures and lines found in the transition zone between the inner labial mucosa and the outer skin of the lips. [2,4,9,10,[12][13][14][15][16][17][18][19] They are verified to recover after undergoing alterations like minor trauma, inflammation, and diseases like herpes; hence, they play a beneficial role in human identification. [2,8,12] Although there are several classifications for lip prints, the most widely used classification was by Suzuki and Tsuchihashi and it is as follows [2,5,7,8,[12][13][14][15] : [ Figure 1]. 1. Type I: vertical grooves that run across the entire lip. 2. Type I': vertical grooves that do not cover the entire lip. ...
... [16] The science of dermatoglyphics involves the study of palmprints and fingerprints and was coined by Cummins and Midlo in 1926. [2,[17][18][19][20] Palmprints are more distinctive than fingerprints because they include more information. [2,17] Detailed analysis of palmprints has become vital to identifying the suspect and the related crime scene. ...
... [25] The presence of the Y chromosome, as well as high testosterone levels, causes a delay in maturation. [19] The establishment of dactyloscopy and cheiloscopy can be used as a reference in criminal case studies and civil litigations that may be useful, particularly in forensic science and justice. Only very few studies have been successfully established with lip print inheritance, whereas studies on the inheritance of palmprints are scanty. ...
Background:
Forensic sciences deal with key areas to be included in judicial makeup that has been approved by both the court and the scientific community, which distinguishes truth from counterfeit. Lip and palmprints are one of a kind and do not change during the lifetime of a person unless any pathologies.
Objectives:
To evaluate the heritability, and gender dimorphism of lip and palm prints among parents and their offspring.
Methods:
A total of 280 participants were included in the study. Lip and palm prints were collected from participants using a digital camera. The photographic data obtained is subjected to Adobe Photoshop and analysed for inheritance. Gender dimorphism is evaluated by the predominant lip pattern and palm ridge count in four designated areas.
Results:
A positive resemblance of 28.4% was found between parents and offspring in lips, and for the right palm, it was 60.2% and 55.12% for the left palm (principal lines) which are statistically insignificant. In all six quadrants, the most predominant lip pattern found in males is type 5, and in females, type 11. The mean palm ridge density was significantly higher among females than males in all designated areas.
Conclusion:
The digital method of analysing lip and palm print images with Adobe Photoshop 7 software is a convenient method that allows for better visualisation and easier lip and palm print recording and identification. Considerable inheritance patterns and gender dimorphism were observed that aid in personal identification.
... The characteristics of biometric recognition are categorized into two main types: anatomical and behavioral [3]. The anatomical features include face [4], fingerprint [5], palm print [6], hand geometry [7], and ear shape [8], while gait [9] and signature [10] are some of the behavioral characteristics [11]. The evaluation of voice biometrics can be conducted through the examination of both anatomical and behavioral characteristics [3]. ...
... The PMF is approximated at x 0 by < l a t e x i t s h a 1 _ b a s e 6 4 = " d V E M j x W Y r g I F I H j x X 8 L z a d R j 0 R 4 = " > A A A C G H i c b V B N S 8 N A E N 3 U r x q / q h 6 9 B I v g q S Q i 1 W N B B I 8 V 7 A e 0 o W w 2 m 3 b t Z j f s T i o l 9 D 9 4 t b / G m 3 j 1 5 o 8 R 3 L Y 5 2 N Y H A 4 / 3 Z p i Z F y S c a X D d b 6 u w s b m 1 v V P c t f f 2 D w 6 P S s c n T S 1 T R W i D S C 5 V O 8 C a c i Z o A x h w 2 k 4 U x X H A a S s Y 3 s 3 8 1 o g q z a R 4 g n F C / R j 3 B Y s Y w W C k Z n c U S t C 9 U t m t u H M 4 6 8 T L S R n l q P d K P 9 1 Q k j S m A g j H W n c 8 N w E / w w o Y 4 X R i d 1 N N E 0 y G u E 8 7 h g o c U + 1 n 8 2 s n z o V R Q i e S y p Q A Z 6 7 + n c h w r P U 4 D k x n j G G g V 7 2 Z + J / X S S G 6 9 T M m k h S o I I t F U c o d k M 7 s d S d k i h L g Y 0 M w U c z c 6 p A B V p i A C W h p C 8 G C U L 7 0 R x a n H J i S L x P b N n l 5 q + m s k + Z V x a t W q o / X 5 d p 9 n l w R n a F z d I k 8 d I N q 6 A H V U Q M R 9 I x e 0 R u a W l P r 3 f q w P h e t B S u f O U V L s L 5 + A S T o o T M = < / l a t e x i t > . . . < l a t e x i t s h a 1 _ b a s e 6 ...
Spoofing-robust automatic speaker verification (SASV) systems are a crucial technology for the protection against spoofed speech. In this study, we focus on logical access attacks and introduce a novel approach to SASV tasks. A novel representation of genuine and spoofed speech is employed, based on the probability mass function (PMF) of waveform amplitudes in the time domain. This methodology generates novel time embeddings derived from the PMF of selected groups within the training set. This paper highlights the role of gender segregation and its positive impact on performance. We propose a countermeasure (CM) system that employs time-domain embeddings derived from the PMF of spoofed and genuine speech, as well as gender recognition based on male and female time-based embeddings. The method exhibits notable gender recognition capabilities, with mismatch rates of 0.94% and 1.79% for males and females, respectively. The male and female CM systems achieve an equal error rate (EER) of 8.67% and 10.12%, respectively. By integrating this approach with traditional speaker verification systems, we demonstrate improved generalization ability and tandem detection cost function evaluation using the ASVspoof2019 challenge database. Furthermore, we investigate the impact of fusing the time embedding approach with traditional CM and illustrate how this fusion enhances generalization in SASV architectures.
... Identity verification is a crucial problem in a security system. Common biometric properties such as iris [1] , fingerprint [2] , palm-print [3] and voice [4] have been used to provide additional security. The biometric properties can be divided into two categories: the physiological characteristics (e.g. ...
... To extend understanding of footstep recognition systems, the focused of this paper is to conduct a literature review using systematic literature review (SLR) method. SLR is a secondary study to collect data from relevant primary studies [3]. SLR could assist to find a solution by performing a review on the previous relevant research. ...
Footstep recognition is a relatively new biometric which aims to discriminate people using walking characteristics. There are several feature and technology have been adopted in various research. This study will attempt to show a comparative technology and feature which is offered each previous related works. We performed a broad manually search to find SLRs published in the time period 1st January 2006 to 30th November 2018. Our broad search found 12 SLRs articles refer to 3 similar technology and 5 cluster feature. In over time, the number of published footstep recognition has increased, especially in conference publications. The differences in footsteps can be known from the power spectral density of sounds and vibrations generated by footsteps. Every footstep of the human has a certain density of frequency, either from density of sounds or vibrations generated. To improve accurately of the result, this paper suggests furthermore research to combining several measuring sensor and data processing method
... Palmprint is deemed to be a hard biometric trait since it contains many discriminative and permanent features, i.e. flexion creases, wrinkles, ridges, and minutiae [21]. Palmprint recognition based on images has received great research attention in the past two decades. ...
... Typically, a traditional palmprint recognition framework mainly contains the following procedures: image acquisition, preprocessing, feature extraction and matching [21]. In the past two decades, both conventional hand-crafted feature-based and deep learning-based methods have been proposed for palmprint recognition and achieved remarkable performance on the public databases. ...
The prevalence of smartphone and consumer camera has led to more evidence in the form of digital images, which are mostly taken in uncontrolled and uncooperative environments. In these images, criminals likely hide or cover their faces while their hands are observable in some cases, creating a challenging use case for forensic investigation. Many existing hand-based recognition methods perform well for hand images collected in controlled environments with user cooperation. However, their performance deteriorates significantly in uncontrolled and uncooperative environments. A recent work has exposed the potential of hand recognition in these environments. However, only the palmar regions were considered, and the recognition performance is still far from satisfactory. To improve the recognition accuracy, an algorithm integrating a multi-spatial transformer network (MSTN) and multiple loss functions is proposed to fully utilize information in full hand images. MSTN is firstly employed to localize the palms and fingers and estimate the alignment parameters. Then, the aligned images are further fed into pretrained convolutional neural networks, where features are extracted. Finally, a training scheme with multiple loss functions is used to train the network end-to-end. To demonstrate the effectiveness of the proposed algorithm, the trained model is evaluated on NTU-PI-v1 database and six benchmark databases from different domains. Experimental results show that the proposed algorithm performs significantly better than the existing methods in these uncontrolled and uncooperative environments and has good generalization capabilities to samples from different domains.
... On the other hand, the method based on hand shape keypoints can utilize these keypoints to perform orientation correction on the ROI and has faster localization speed, thus gradually becoming the mainstream research direction. The extraction process of the ROI based on hand shape keypoints, as shown in Fig 2, usually relies on valley points between the index and middle fingers and between the middle and ring fingers [13][14][15]. By establishing a coordinate system using these two valley points at a certain distance, the palm ROI can be located based on the corresponding distances within this coordinate system. ...
... In object detection networks, IOU is a metric used to measure the degree of overlap between the model detection box and the real target box, as shown in (13), where A and B represent the model detection box and the real target box, respectively. The IOU value range is between 0 and 1, indicating the degree of overlap between the predicted box and the actual target box. ...
Accurately extracting the Region of Interest (ROI) of a palm print was crucial for subsequent palm print recognition. However, under unconstrained environmental conditions, the user’s palm posture and angle, as well as the background and lighting of the environment, were not controlled, making the extraction of the ROI of palm print a major challenge. In existing research methods, traditional ROI extraction methods relied on image segmentation and were difficult to apply to multiple datasets simultaneously under the aforementioned interference. However, deep learning-based methods typically did not consider the computational cost of the model and were difficult to apply to embedded devices. This article proposed a palm print ROI extraction method based on lightweight networks. Firstly, the YOLOv5-lite network was used to detect and preliminarily locate the palm, in order to eliminate most of the interference from complex backgrounds. Then, an improved UNet was used for keypoints detection. This network model reduced the number of parameters compared to the original UNet model, improved network performance, and accelerated network convergence. The output of this model combined Gaussian heatmap regression and direct regression and proposed a joint loss function based on JS loss and L2 loss for supervision. During the experiment, a mixed database consisting of 5 databases was used to meet the needs of practical applications. The results showed that the proposed method achieved an accuracy of 98.3% on the database, with an average detection time of only 28ms on the GPU, which was superior to other mainstream lightweight networks, and the model size was only 831k. In the open-set test, with a success rate of 93.4%, an average detection time of 5.95ms on the GPU, it was far ahead of the latest palm print ROI extraction algorithm and could be applied in practice.
... The principal lines and wrinkles are prime features to discriminate one person from another [2]. The existing algorithms for palmprint can be classified into following classes: structural, subspace, statistical, transform, coding based approaches [3] and Deep learning based approaches [4][5][6][7][8][9]. Among all of the these mentioned categories, coding based approaches [10][11][12][13][14] demonstrate remarkable performance with ease in implementation and quick feature extraction with very low complexity. ...
... The optimal performance of the proposed approach is obtained when the parameters (α, β, c) are tuned to (9,17,2) for the PolyU 2D database while with IITD database, method achieves optimal performance when the parameters are tuned to (13,15,3). ...
The straight excitatory filters such as Gabor filters and Modified finite Radon transform can not include the vital and inherent curvature information residing in palmlines of the palmprint. Moreover, Gabor filter bank, employed in majority research work of the literature, is frequency dependent which require tuning to avoid false line representation for principle line/wrinkles. Therefore in this work to evade the false palmline assessment within the neighbourhood region and include inherent curvature attribute of the palmlines, a curvilinear anisotropic filter, (CAGF) is proposed and employed for palmprint representation. The proposed filter bank exploits both positive and negative concavities constituted within the palmlines. A novel representation called as the Anisotropic Differential Concavity (ADC) codes is obtained from difference plane obtained by subtracting curvilinear anisotropic filter responses of the palmprint sample at various orientations and for both positive and negative concavities, followed by the zero-crossings of these difference planes. Finally, it is observed that the experimental performance of the proposed representation, on standard PolyU 2D and IITD touch-less databases, outperforms several state-of-the-art approaches.
... Given that the quality of the ROI extraction greatly affects the recognition performance, it is obvious that efficient ROI extraction method is essential for palmprint identification. Thus, developing a successful ROI extraction technique is a crucial area of study for palmprint recognition researchers [17]. ...
The ridges, creases, wrinkles, and minutiae on the palmprint region of interest (ROI) are important features. These features are employed to confirm or identify an individual. One inevitable issue in the realization of palmprint recognition systems is the extraction procedure of this region under unrestricted environments. The variety in palm sizes, postures, lighting conditions, and backgrounds, however, certainly presents a significant issue. Finding and extracting the palm's area of interest (ROI) will be our main goal. This research introduces a robust automated algorithm based on square construction and each YCbCr color space features. After reading the image of the colored hand, this algorithm goes through two stages. Firstly, convert to the YCbCr color space. This stage guarantees precise locating of the hand region in addition to deleting irrelevant information from the image. Secondly, determining ROI is based on applying three steps: locating three key references, utilizing these key references to construct the main line, and finally, constructing the ROI square. The total color hand images (230) were used to test and evaluate the newly introduced algorithm; 30 were collected from the internet; and 200 were chosen from the Birjand University Mobile Palmprint Database (BMPD). The hand images include two orientations, left and right, varying sizes and backgrounds, uneven illumination, shadows, and some hand images have items on the finger(s). The experimental findings demonstrate that the introduced algorithm effectively attained 100% and 99.565% sensitivity and accuracy, respectively.
... The process of performing a series of adjustments and key point locations for various palmprint and palm vein images is referred to as ROI extraction [4]. The core idea is to extract the ROI is to employ the valley points between the fingers to establish a coordinate system and then obtain the ROI of palmprints [5]. Following this, the effective area of the centre is selected to extract features, and the final matching is completed for the recognition. ...
The palmprint comprises multiple unique patterns that are distinct in detecting human identity. There are numerous algorithms proposed by past researches for recognizing Two-dimensional Palmprint Region of Interest (2DPROI) images. In this research, an innovative Deep Learning Lacunarity Texture Analysis System (D2LTA) is developed for recognizing the accredited persons at higher recognition rate. To impart the D2LTA model, Two-dimensional palmprint hands’ ROI images are segmented using Mid-point ROI generation algorithm, produced a peculiar feature vector using lacunarity approach in a state-of-the-art manner, and then Deep Learning ConvNet classifier is proposed for D2LTA system to justify the accredit person. The key principle of the Mid-point ROI generation approach is to determine the perfect straight line on the center of the palm. Based on the straight line in the palm, determine the pixel values of the ROI’s rectangular box. To catch the perfect straight line, line mid-point method is used. To do this research, 2D-palm hands are procured from three different datasets such as BMPD, CASIA and IIT palm datasets and 2DPROI images are secured from PolyU, Hong Kong Polytechnic University, Hong Kong. The proposed model has been assessed with diverse dimensions to prove the acquirement 99.25% of higher precious authentication rate.
... Length, orientations, and edge points of palm principal lines are essential to the line-based approach [22]. Independent or combination of the line-based approaches along with the statistical operators increased the recognition accuracy [23], [24]. The study in this paper [25] used the principal lines information, and structure were extracted as feature values. ...
To make the methodical Palmprint Recognition System (PRS), this research proposed an unique Deep Learning classifier using the palm hand’s principal lines extraction approach and multifractal texture analysis approach. To reveal the efficient biometric security, a Deep Learning Multifractal Texture Analysis for Palmprint Recognition System (DLMTA-PRS) has been suggested. In DLMTA-PRS system, exact principal lines of Two–Dimensional Palmprint Region of Interest (2DPROI) image are extracted using morphological operations and an edge detection algorithm in a peculiar manner. Then, Feature values of 2DPROI image are fetched using multifractal texture analysis approach. To perform this approach, Box-counting and Gliding-Box algorithms are performed and the feature vector is created. The feature vector is classified using the proposed Convolution Neural Network (CNNNet) classifier approach to get the higher authentication security. The multi-spectral 2DPROI image database has been utilized for this research which is acquired from the PolyU, the Hong Kong Polytechnic University in Hong Kong. The suggested DLMTA-PRS system underwent scrutiny as well as proved the best of its by evaluating the DLMTA-PRS system using numerous criterias with the achievement of getting 99.25% accurate identification rate.
... These are broadly divided into physiological or the physical traits of a person, and behavioral traits, focusing on the specific way in which a person moves or interacts with their surroundings [12,32,45]. There is a plethora of work introducing physiological biometrics with approaches including among others face recognition [51,54,63], fingerprints [33,34,61], hand or palm prints [31,64], human iris features [5,13] or footprints [41,58]. Behavioral biometrics are receiving increasing attention as well, most notably the recognition of individuals based on their walking (i.e., gait) [20,44,47,57], typing patterns (i.e., keystroke dynamics) [9,30,39,52], or touch dynamics [15,53]. ...
In this paper we assess how well users know biometric authentication methods, how they perceive them, and if they have misconceptions about them. We present the results of an online survey that we conducted in two rounds (2019, N=57; and 2023, N=47) to understand the impact of the increasing availability of biometrics on their use and perception. The survey covered participants' general understanding of physiological and behavioral biometrics and their perceived usability and security. While most participants were able to name examples and stated that they use biometrics in their daily lives, they still had difficulties explaining the concepts behind them. We shed light on participants' misconceptions, their coping strategies with authentication failures and potential attacks, as well as their perception of the usability and security of biometrics in general. As such, our results can support the design of both further studies to gain deeper insights and future biometric interfaces to foster the informed use of biometrics.
... As a more and more popular biometric modality, the palmprint has richer feature information than the fingerprint, face, iris, etc., and the acquisition equipment is relatively cheap and convenient [1]. Moreover, palmprint recognition can be implemented at a distance in a non-contact manner [2,3,4], which is an obviously more hygeian modality than other modalities such as the fingerprint. ...
... Biometric features offer a powerful means of authentication, providing ample information for accurate person identification. These features encompass behavioral traits, such as handwritten signatures, voiceprints, and keystroke dynamics, as well as physiological characteristics like fingerprints, hand silhouettes, and blood vessel patterns [46]. While behavioral-traits-based systems are considered less intrusive, they exhibit higher variability over time; whereas, physiological-based systems tend to offer greater stability but often involve more intrusive measurement methods. ...
We propose a novel and versatile computational approach, based on hierarchical COSFIRE filters, that addresses the challenge of explainable retina and palmprint recognition for automatic person identification. Unlike traditional systems that treat these biometrics separately, our method offers a unified solution, leveraging COSFIRE filters’ trainable nature for enhanced selectivity and robustness, while exhibiting explainability and resilience to decision-based black-box adversarial attack and partial matching. COSFIRE filters are trainable, in that their selectivity can be determined with a one-shot learning step. In practice, we configure a COSFIRE filter that is selective for the mutual spatial arrangement of a set of automatically selected keypoints of each retina or palmprint reference image. A query image is then processed by all COSFIRE filters and it is classified with the reference image that was used to configure the COSFIRE filter that gives the strongest similarity score. Our approach, tested on the VARIA and RIDB retina datasets and the IITD palmprint dataset, achieved state-of-the-art results, including perfect classification for retina datasets and a 97.54% accuracy for the palmprint dataset. It proved robust in partial matching tests, achieving over 94% accuracy with 80% image visibility and over 97% with 90% visibility, demonstrating effectiveness with incomplete biometric data. Furthermore, while effectively resisting a decision-based black-box adversarial attack and impervious to imperceptible adversarial images, it is only susceptible to highly perceptible adversarial images with severe noise, which pose minimal concern as they can be easily detected through histogram analysis in preprocessing. In principle, the proposed learning-free hierarchical COSFIRE filters are applicable to any application that requires the identification of certain spatial arrangements of moderately complex features, such as bifurcations and crossovers. Moreover, the selectivity of COSFIRE filters is highly intuitive; and therefore, they provide an explainable solution.
... Unimodal biometric systems rely on a single characteristic like iris patterrns or palmprints, for identification. These traits are particularly significant due to their permanence, uniqueness, and high resistance to forgery, which ensures high recognition accuracy and valuable security [3,4]. However, unimodal systems face limitations. ...
Biometric recognition technology has witnessed widespread integration into daily life due to the growing emphasis on information security. In this domain, multimodal biometrics, which combines multiple biometric traits, has overcome limitations found in unimodal systems like susceptibility to spoof attacks or failure to adapt to changes over time. This paper proposes a new multimodal biometric recognition system that utilizes deep learning algorithms using iris and palmprint modalities. A pioneering approach is introduced, beginning with the implementation of the novel Modified Firefly Algorithm with L\'evy Flights (MFALF) to optimize the Contrast Limited Adaptive Histogram Equalization (CLAHE) algorithm, thereby effectively enhancing image contrast. Subsequently, feature selection is carried out through a unique hybrid of ReliefF and Moth Flame Optimization (MFOR) to extract informative features. For classification, we employ a parallel approach, first introducing a novel Preactivated Inverted ResNet (PIR) architecture, and secondly, harnessing metaheuristics with hybrid of innovative Johnson Flower Pollination Algorithm and Rainfall Optimization Algorithm for fine tuning of the learning rate and dropout parameters of Transfer Learning based DenseNet architecture (JFPA-ROA). Finally, a score-level fusion strategy is implemented to combine the outputs of the two classifiers, providing a robust and accurate multimodal biometric recognition system. The system's performance is assessed based on accuracy, Detection Error Tradeoff (DET) Curve, Equal Error Rate (EER), and Total Training time. The proposed multimodal recognition architecture, tested across CASIA Palmprint, MMU, BMPD, and IIT datasets, achieves 100% recognition accuracy, outperforming unimodal iris and palmprint identification approaches.
... Notable among these are facial recognition, fingerprint analysis, iris scanning, ear morphology, palmprint patterns, hand geometry, gait dynamics, and beyond. Palmprint recognition, in particular, has emerged as a leading modality owing to its cost-effectiveness, high accuracy, and broad acceptance among users [8,9], marking it as a cornerstone technology in the domain of biometric identification [10,11]. ...
The escalating reliance on biometric systems for identity verification underscores the imperative for robust data protection mechanisms. Biometric authentication, leveraging unique biological and behavioral characteristics, offers unparalleled precision in individual identification. However, the integrity and confidentiality of biometric data remain paramount concerns, given its susceptibility to compromise. This research delineates the development and implementation of an innovative framework for cancellable biometrics, focusing on facial and fingerprint recognition. This study introduces a novel cancellable biometrics framework that integrates graph theory encryption with three-dimensional chaotic logistic mapping. The methodology encompasses a multifaceted approach: initially employing graph theory for the secure and efficient encryption of biometric data, subsequently enhanced by the complexity and unpredictability of three-dimensional chaotic logistic mapping. This dual-layered strategy ensures the robustness of the encryption, thereby significantly elevating the security of biometric data against unauthorized access and potential compromise. Thus, the resulting cancellable biometrics, characterized by the ability to transform biometric data into an adjustable representation, addresses critical challenges in biometric security. It allows for the revocation and reissuance of biometric credentials, thereby safeguarding the original biometric characteristics of individuals. This feature not only enhances user privacy and data security but also introduces a dynamic aspect to biometric authentication, facilitating adaptability across diverse systems and applications. Preliminary evaluations of the proposed framework demonstrate a marked improvement in the security of face and fingerprint recognition systems. Through the application of graph theory encryption, coupled with three-dimensional chaotic logistic mapping, our framework mitigates the risks associated with traditional biometric systems. This includes enhanced protection against data breaches, template theft, and the cloning of biometric identifiers. Therefore, the integration of graph theory and chaotic logistic mapping in cancellable biometrics presents a significant advancement in the field of biometric security. The proposed framework not only fortifies the encryption of biometric data but also introduces flexibility and resilience in the management of biometric templates. Future research will aim to refine this framework, exploring its applicability and effectiveness across a broader spectrum of biometric modalities and examining its potential for real-world deployment. Additionally, further studies will investigate the optimization of encryption algorithms and the scalability of the system to accommodate the growing demands of biometric authentication.
... BACKGROUND A typical TLPR system consists of two components: image sensing and identity recognition. In detail, the recognition method includes palm region segmentation, keypoint detection, region of interest (ROI) localization, feature encoding, feature matching, and decision (Kong et al., 2009). According to the above components, the challenges in TLPR can be divided into two categories: image sensing-related and recognition method-related. ...
Palmprint recognition is a technology that uses the unique composite texture information of the palm surface for automatic identification. In this chapter, first, the main research contents of touchless palmprint recognition are introduced. Second, the establishment of the CUHKSZ large-scale touchless palmprint dataset will be described in detail. Third, parameter optimization experiments are conducted on the CUHKSZ dataset to observe the scientific problems caused by the increase in data scale. Fourth, the experiment comparing the EER of the most used touchless palmprint recognition algorithms on the large-scale dataset will be performed to provide baselines for future research. Finally, the recognition performances of the three most widely used biometric modals, including palmprint, face, and fingerprint, will be compared on the CUHKSZ dataset, which can demonstrate the advantages of touchless palmprint recognition. In the end of this chapter, future research directions will be put forward.
... For palmprint systems, essentially, they can be divided into two types in terms of image resolution. In general, the highresolution palmprint is mainly used in crime scenes for forensics, while the low-resolution palmprint is mainly used for commercial applications [46]. As the low-resolution imagebased methods are more related to our research, we include some representative methods in our review here. ...
A novel method based on the cross‐modality intersecting features of the palm‐vein and the palmprint is proposed for identity verification. Capitalising on the unique geometrical relationship between the two biometric modalities, the cross‐modality intersecting points provides a stable set of features for identity verification. To facilitate flexibility in template changes, a template transformation is proposed. While maintaining non‐invertibility, the template transformation allows transformation sizes beyond that offered by the conventional means. Extensive experiments using three public palm databases are conducted to verify the effectiveness the proposed system for identity recognition.
... Palmprint recognition constitutes a pivotal biometric technology deployed in the identification and verification of individuals, relying on the distinctive patterns inherent in their palmprints. This method, known for its reliability and security, finds extensive applications in diverse fields, including access control, security systems, and forensic investigations [1]. The palmprint recognition methodology originated with a focus on forensic analysis of latent prints, capitalizing on the intricate and extensive textural features compared to fingerprints. ...
This paper presents a comprehensive survey examining the prevailing feature extraction methodologies employed within biometric palmprint recognition models. It encompasses a critical analysis of extant datasets and a comparative study of algorithmic approaches. Specifically, this review delves into palmprint recognition systems, focusing on different feature extraction methodologies. As the dataset wields a profound impact within palmprint recognition, our study meticulously describes 20 extensively employed and recognized palmprint datasets. Furthermore, we classify these datasets into two distinct classes: contact-based datasets and contactless-based datasets. Additionally, we propose a novel taxonomy to categorize palmprint recognition feature extraction approaches into line-based approaches, texture descriptor-based approaches, subspace learning-based methods, local direction encoding-based approaches, and deep learning-based architecture approaches. Within each class, most foundational publications are reviewed, highlighting their core contributions, the datasets utilized, efficiency assessment metrics, and the best outcomes achieved. Finally, open challenges and emerging trends that deserve further attention are elucidated to push progress in future research.
... Existing palmprint representation algorithms can be broadly classified into structural, subspace, statistical, transform, and coding-based approaches [5]. Among these, coding approaches, a subcategory of transform-based algorithms [6][7][8][9], have shown remarkable performance, ease in implementation, and rapid feature extraction. ...
The inherent curvature in palm lines can pose challenges for palmprint recognition, particularly at lower resolutions where wrinkles become indistinguishable, leading to performance degradation. To address these issues, this study introduces a novel methodology employing curvi-linear anisotropic Gaussian filter-based Combined Differential Concavity and Infirmity (CDCI) codes. The use of curved filters has been proposed to represent curved palm lines more accurately, while anisotropic filtering is expected to enhance the extraction of blurred palm lines. The new representation, grounded in curvi-linear anisotropic Gaussian filtering, is posited to improve the recognition system's performance by effectively addressing these challenges. The proposed approach's effectiveness has been tested using the touchless IITD database and the contact-based PolyU 2D database. The experimental results suggest that the proposed methodology surpasses the performance of state-of-the-art coding-based procedures in palmprint recognition with the improvement of 3.82% and 36.36% in recognition rate and equal error rate.
... Using a two-dimensional discrete cosine transform (2D-DCT), the feature extraction process is carried out locally in this technique. A strong survey for most palm print recognition systems has been studied in addition to these works [18,20]. The obtained results are assessed using an intelligent palm print recognition method in terms of verification and recognition rate. ...
Biometric engineering is one of the most important and modern fields that affect human
life directly. It can be considered as a new technology relatively, that is used for identity
verification and/or the identification of persons depending on their physiological features,
which include the morphological, biological, and characteristics of their behaviors. Many
types of biometric recognitions are used depending on features of eyes, faces, hands (palm
and/or fingerprints), voice, and many others. All the works before were focused on persons’
detection only but nor on their ages. This feature (age) considered as one of the not solved
problems in the field of detection. In this paper, the palm recognition model consisted of
many steps. The first step related to palm detection. Other techniques used to remove noisy
portion from extracted image. After preparing images for training, a deep neural network
represented by convolutional neural network is selected. A new idea and method
(mechanism) is used. Palm print features' recognition algorithm depending on
Convolutional Neural Network (CNN) is presented for recognizing individuals (persons
recognition in different ages’ classes). Palm print technique is depended for different ages’
classes. The dataset is selected firstly for many known persons with different ages, for each
person many palm image items are trained and tested using deep learning techniques. As
mentioned, the CNN method is used for the training purpose, which means the recognition
must be done depending on the CNN deep learning algorithm. The FAR and GAR factors
are used to measure the performances of the recognition. The given results shown that the
selection of the palm instead of other features types makes the recognition easier. More
than 96% of the results were accurate. Also, the used algorithm which included the CNN
had competitive performance, the algorithm succeeded to separate between the features
according to the persons’ ages. The overall process is completed within 0.01×10-6 second,
which can be considered fast and suggested to be used in real time.
... Palm is less prone to damage and also low resolution images curtail sufficient information for recognition of palm prints. Several applications make use of palm prints such as forensic laboratory for crime scene investigations, medical diagnosis, palmistry, blood relation identification, selection of athletes and many more (Kong, 2009) ...
In this article different state of art palm print recognition techniques have been discussed. Furthermore, various aspects of palm print recognition methodologies pertaining to feature extraction and representation are elaborated. Various researchers have developed and used diverse databases for the purpose of experimentation and probing their methods. This article provides an analysis on each set of methodologies in terms of different parameters such as efficiency, accuracy and effectiveness. The comparative analysis provides several benchmarks to quantify the usefulness of each technique and determine the tradeoffs in terms of cost and effectiveness.
... Acquisition approaches premised on digital cameras, digital scanner and video cameras requires less effort for system design and can be found everywhere around. This approach can be used to collect palmprint images without contact, and they have the hygiene advantage [15]. In recent years, Android smartphones occupied 76% of the world's smartphones' market. ...
... Acquisition approaches premised on digital cameras, digital scanner and video cameras requires less effort for system design and can be found everywhere around. This approach can be used to collect palmprint images without contact, and they have the hygiene advantage [15]. In recent years, Android smartphones occupied 76% of the world's smartphones' market. ...
Palmprint recognition has emerged as a prominent biometric technology, widely applied in diverse scenarios. Traditional handcrafted methods for palmprint recognition often fall short in representation capability, as they heavily depend on researchers' prior knowledge. Deep learning (DL) has been introduced to address this limitation, leveraging its remarkable successes across various domains. While existing surveys focus narrowly on specific tasks within palmprint recognition-often grounded in traditional methodologies-there remains a significant gap in comprehensive research exploring DL-based approaches across all facets of palmprint recognition. This paper bridges that gap by thoroughly reviewing recent advancements in DL-powered palmprint recognition. The paper systematically examines progress across key tasks, including region-of-interest segmentation, feature extraction, and security/privacy-oriented challenges. Beyond highlighting these advancements, the paper identifies current challenges and uncovers promising opportunities for future research. By consolidating state-of-the-art progress, this review serves as a valuable resource for researchers, enabling them to stay abreast of cutting-edge technologies and drive innovation in palmprint recognition.
The use of biometric structures for authentication and identification has received increasing importance in diverse security and get admission to manipulate programs. Iris recognition, renowned for its excessive accuracy and strong point, has emerged as a strong biometric modality. In this studies paper, we present an modern approach to iris detection and popularity by combining traditional class techniques with the cutting-edge Generative Latent Attribute Model (KNN) algorithm from the domain of gadget learning.
This paper proposes a control strategy with three joint controllers to improve the speed response of a permanent magnet synchronous motor (PMSM) in an electric vehicle (EV) system. The first controller is an online adaptive optimal tracking controller (OTC) to enhance the tracking response of the speed of the PMSM. This controller is derived based on reinforcement learning (RL) method by approximating the solutions of the Hamilton-Jacobi-Isaacs (HJI) equations while still ensuring the stability of the closed-loop system of PMSM. Three components are approximated simultaneously online: one performance index (one critic), one control law (the first actor), and one worst disturbance law (the second actor). On the other hand, the DC-link voltage peak (DVP) the Bi-directional Quasi Z-Source Inverter (BZI) needs to be
regulated so that the PMSM can be operational in the high-speed zone. Therefore, the next two controllers are applied based on a frequencyresponse method to improve the responses of the inductor current and the DVP in the closed-loop control system of the BZI with unknown dynamics of the PMSM and BZI (PZI). The simulation results of the speed response with the PZI model show the effectiveness and robustness of the proposed control strategy.
Surprisingly, the high accuracies previously reported, exceeding 95%, dropped significantly when faced with the more demanding conditions of the forensic scenario, plummeting to as low as 65%. In essence, while facial recognition systems have shown impressive performance in ideal conditions, our study indicates a substantial decrease in accuracy when faced with the complexities and challenges typical of real-world forensic scenarios, highlighting the need for further advancements to bridge this gap. Recent advancements in machine learning and computer vision have shown facial recognition systems achieving accuracies that surpass human performance in controlled settings but fingerprint analysis is proved more accurate in all aspects. To investigate this, we created a large-scale synthetic facial dataset and designed a controlled facial lineup that mimics conditions encountered in real forensic situations. This approach allowed us to systematically assess facial recognition under various challenging real-world conditions. Using both our synthetic dataset and a well-known dataset of actual faces, we tested the accuracy of two widely used neural-based facial recognition systems. Comparative and Analytical method is applied for present Research. Artificial intelligence could help humans in accuracy and speeding up the process of investigation.
Person recognition systems have been applied for several years, as fingerprint recognition has been experimented with different image resolutions for 15 years. Fingerprint recognition and biometrics for security are becoming commonplace. Biometric systems are emerging and evolving topics seen as fertile ground for researchers to investigate more deeply and discover new approaches. Among the most prominent of these systems is the palm printing system, which identifies individuals based on the palm of their hands because of the advantages that the palm possesses that cannot be replicated among humans, as in its theory of other fingerprints. This paper proposes a biometric system to identify people by handprint, especially palm area, using deep learning technology via a pre-trained model on the PolyU-IITD dataset. The proposed system goes through several basic stages, namely data pruning, processing, training, and prediction, and the results were promising, as the system's accuracy reached 90% based on the confusion matrix measures.
This review explores the integration of sparse representation and compressed perception in optical image reconstruction. Beginning with an in-depth examination of sparse representation techniques, including dictionary learning and sparse coding, the study introduces a novel paradigm by incorporating compressed perception principles. The methodology aims to optimize efficiency, data storage, and reconstruction quality. The review delves into optimization strategies, adaptive techniques, multi-scale considerations, and real-time implementation, offering a comprehensive analysis of the current landscape. By synthesizing existing knowledge and proposing innovative approaches, this review contributes to advancing optical image reconstruction, promising future breakthroughs at the intersection of sparse representation and compressed perception.
Forensic human identification is of utmost importance in various contexts, including criminal investigations and disaster victim identification. This research paper explores the application of biometric identification techniques in forensic human identification, with a particular focus on fingerprint recognition, face recognition, hand geometry, voice recognition, vein recognition, DNA matching, retina recognition, iris recognition, ECG-based identification, and EEG-based identification. The paper provides an overview of the historical background and development of EEG-based identification, highlighting its significance in forensic investigations. Additionally, the study investigates the integration of machine learning approaches, including support vector machines (SVM), K-nearest neighbors (KNN), random forests, and deep learning. The paper also covers RNN and its architectures styles in particularly long short-term memory (LSTM), and gated recurrent unit (GRU) in forensic human identification. The paper discusses the advantages and limitations of these machine-learning techniques in enhancing the accuracy and efficiency of identification systems. Overall, this research paper sheds light on the importance of biometric identification and the potential of machine-learning approaches in forensic human identification, providing valuable insights for forensic experts, researchers, and practitioners in the field.
The research aims at determining whether the palmar creases are oriented similarly or varied among related individuals (e.g. family) and unrelated people, or remain discrete as fingerprints and palm prints are purported to. Convenience-based random sampling obtained five extended families (n=84 participants) within Imale Hamlet. Qualitative data collection methods involving use of palm-print scanners to take a photograph/scan of the entire palm for both of the hands or any available hand was done for each participant. For quantitative characterization, the circumference of the palm was marked with a 16-point scale with which the position of each of the three major palmar lines was estimated. The data was grouped as per family, and generations with respect to the family head. The start- and end-points of each palmar crease for both hands were averaged and used for descriptive and correlational analysis. Based on the intra- and inter-family correlation analysis, the results of this study support the hypothesis that palm creases orientation correlates among related and varies within unrelated individuals. Strong correlations were found among people of a family while weak correlations were seen in people of different families. However, the study only considered the start- and end-points of the palmar lines, which is not a perfect measure of the line orientation. Further studies should improve this model to account for the obliquity of the palmar creases to perfectly quantify the palmar orientations. Additionally, the study did not consider the effect of gender and inter-marriages on the palmar lines orientation. Further research need to elucidate such effect while aiming at elucidating the heredity pattern of the palmar crease trait.
The research aims at determining whether the palmar creases are oriented similarly or varied among related individuals (e.g. family) and unrelated people, or remain discrete as fingerprints and palm prints are purported to. Convenience-based random sampling obtained five extended families (n=84 participants) within Imale Hamlet. Qualitative data collection methods involving use of palm-print scanners to take a photograph/scan of the entire palm for both of the hands or any available hand was done for each participant. For quantitative characterization, the circumference of the palm was marked with a 16-point scale with which the position of each of the three major palmar lines was estimated. The data was grouped as per family, and the relationship to the head which facilitates generational variables and aids conceal the specific identities of the participants. The start- and end-points of each palmar crease for both hands were averaged and used for descriptive and correlational analysis. Based on the intra- and inter-family correlation analysis, the results of this study support the hypothesis that palm creases orientation correlates among related and varries within unrelated individuals. Strong correlations were found among people of a family while weak correlations were seen in people of different families. However, the study only considered the start- and end-points of the palmar lines, which is not a perfect measure of the line orientation. Further studies should improve this model to account for the obliquity of the palmar creases to perfectly quantify the palmar orientations. Additionally, the study did not consider the effect of gender and inter-marriages on the palmar lines orientation. Further research need to elucidate such effect while aiming at elucidating the heredity pattern of the palmar crease trait.
This book constitutes the refereed post-conference proceedings of the 8th EAI International Conference on Nature of Computation and Communication, ICTCC 2022, held in Vinh Long, Vietnam, in October 27-28 2022.
The 11 revised full papers presented were carefully selected from 32 submissions. The papers of ICTCC 2022 cover formal methods for self-adaptive systems and discuss natural approaches and techniques for natural computing systems and their applications.
Palmprint-based biometrics has received a lot of attention for personal identification. The paper proposes a novel learning discriminant feature technique for palmprint recognition, called the Learning Discriminant Line Direction Descriptor (LDLDD), that learns separately all three kind of directional pattern code. The dominant direction number (DDN) map is calculated first in this method. Then, this technique computes direction pattern maps with three multi-direction encoding methods based on the DDN map, where pixels with the same DDN values will use the same encoding strategy and belong to the same feature map. Finally, (2D)2LDA is used to train new feature subspaces that project these maps from a high-dimensional space to a discriminant space with lower dimensions. Experiments on Hong Kong Polytechnic University’s (PolyU and IITD) public databases show that the proposed method outperforms existing techniques in terms of accuracy.KeywordsPalmprint recognitionDominant direction numberMulti direction patternBiometrics
Binary pattern learning has been achieved promising recognition performance in palmprint identification. However, most of direction representation-based methods are hand-crafted. They present the direction characteristics only in one scale, and thus the comprehensive information from multiple scales and multiple directions are ignored. This is also true especially for the binary coding-based methods. As a solution to the problem, this paper proposes a multi-scale multi-direction binary (MSMDB) pattern learning method for palmprint identification. Specifically, we first form a feature container of multi-scales multi-directions for palmprint images. The container contains robust direction average vectors (DAVs). Then, a learning model is proposed to learn robust and discriminant direction information from the extracted convolution average features. The proposed model can project these DAVs into discriminant direction binary codes. The model not only maximizes the variance of the learned binary codes and inter-class distance, but also minimizes intra-class distance. Finally, we cluster all block histograms of multi-scale projections to form the discriminative direction binary palmprint descriptors for palmprint identification. We evaluate the performance of the proposed method on five public databases compared to other related methods. For example, MSMDB can achieve the best identification accuracy of 97.93 percent when the number of training data is 2 on the database IITD.
Authentication in personal identication using palm print method provides valuable evidence in one's identication. It has been investigated over years by different methods employed by both high resolution images which are further processed by different computerized techniques and software systems and low resolution images which have attracted many researchers attention. This paper proposes a brief introduction about palm prints its different methods employed and the current classication system which is less time consuming followed for research to be carried out for biometric authentication and scientic evidences which is useful for civil and commercial applications.
Palmvein technology is one of the most popular fields in pattern recognition. The most distinguishing advantage of vein features are high level of accuracy, difficult to forge and more table features. In this study, palmvein images of individuals were acquired; a Linear Discriminant Analysis and Firefly Algorithm (LDA-FA) model for feature extraction was formulated and implemented and the performance of the developed system was benchmarked with the LDA model. Five (5) palmvein images of each one hundred (100) individuals were captured using an infrared CCD sensitive camera. Linear discriminant Analysis was enhanced with Firefly Algorithm to extract sufficient features. Back Propagation Neural Network (BPNN) was used to determine the class the training and the testing image belong. 270 images were used in training the database and 230 images were used for testing the created database. The system was tested using False Positive Rate, False Negative Rate, Recognition Accuracy and Average Recognition Time. The system was tested for False Positive Rate, False Negative Rate and accuracy at threshold values of 0.25, 0.46, 0.60, 0.85. The LDA-FA achieved a false positive rate of 18.00%, 10.00%, 6.00%, 2.00%, false negative rate of 1.11%, 2.22%, 2.78%, 3.33% and accuracy of 95.22%, 96.09%, 96.52% and 96.96% at the threshold values respectively. The LDA achieved a false positive rate of 22.00%, 14.00%, 10.00%, 4.00%, false negative rate of 4.44%, 5.00%, 5.56%, 6.67% and accuracy of 91.74%, 93.04%, 93.48% and 93.91% at the threshold values respectively. The average training time generated by LDA-FA are 200.32s, 199.87s, 201.94 and 202.91 while that of LDA are 219.76s, 219.93s, 220.38s and 220.71 at the threshold values respectively. The result shows that the LDA-FA is less computationally expensive in terms of training time compared to the LDA model. The study concluded that the LDA-FA is more accurate with minimal false positive and false negative than LDA.
Various techniques in analyzing palmprint have been proposed but to the best of our knowledge, none has been studied on the selection and division of the region-of-interest (ROI). Previous methods were always applied only to a fixed size square region chosen as the central part of the palm, which were then divided into square blocks for extraction of local features. In this paper, we proposed a new method in locating and segmenting the ROI for palmprint analysis, where the selected region varies with the size of the palm. Instead of square blocks, the region is divided into sectors of elliptical half-rings, which are less affected by misalignment due to rotational error. More importantly, our arrangement of the feature vectors ensures that only features extracted from the same spatial region of two aligned palms will be compared with each other. Encouraging results obtained favor the use of this method in the future development of palmprint analysis techniques.
A palm, a large inner surface of a hand, contains pattern of ridges and valleys much like a fingerprint. The palmprint is expected to be more distinctive than the fingerprint, since the area of the palm is much larger than that of the finger and the palm has additional distinctive features such as principle lines, ridges, minutiae points, singular points and texture. This paper presents a palmprint recognition algorithm using phase-based image matching. The use of the phase components in 2D (two-dimensional) discrete Fourier transforms of palmprint images makes possible to achieve highly robust palmprint recognition. Experimental evaluation using palmprint images clearly demonstrates an efficient matching performance of the proposed algorithm
Local binary pattern (LBP) is a powerful texture descriptor that is gray-scale and rotation invariant according to T. Ojala et al. (2002). Because texture is one of the most clearly observable features in low-resolution palmprint images, we think local binary pattern based features are very discriminative for palmprint identification. In this paper, we propose a palmprint identification approach using boosted local binary pattern based classifiers. The palmprint area is scanned with a scalable sub-window from which local binary pattern histograms are extracted to represent the local features of a palmprint image. The multi-class problem is transformed into a two-class one of intra- and extra-class by classifying every pair of palmprint images as intra-class or extra-class ones in the work of B. Moghaddam et al. (1996). We use the AdaBoost algorithm in the work of Y. Freund and R.E. Schapire (1997) to select those sub-windows that are more discriminative for classification. Weak classifiers are constructed based on the Chi square distance between two corresponding local binary pattern histograms. Experiments on the UST-HK palmprint database show competitive performance
Principal component analysis (PCA) has been very successful in image recognition. Recent researches on PCA-based methods are mainly concentrated on two issues, feature extraction and classification. In this paper we propose bi-directional PCA (BDPCA) with assembled matrix distance (AMD) metric to simultaneously deal with these two issues. For feature extraction, we propose a BDPCA approach which can reduce the dimension of the original image matrix in both column and row directions. For classification, we present an AMD metric to calculate the distance between two feature matrices. The results of our experiments show that, BDPCA with AMD metric is very effective in image recognition.
This paper describes a computational approach to edge detection. The success of the approach depends on the definition of a comprehensive set of goals for the computation of edge points. These goals must be precise enough to delimit the desired behavior of the detector while making minimal assumptions about the form of the solution. We define detection and localization criteria for a class of edges, and present mathematical forms for these criteria as functionals on the operator impulse response. A third criterion is then added to ensure that the detector has only one response to a single edge. We use the criteria in numerical optimization to derive detectors for several common image features, including step edges. On specializing the analysis to step edges, we find that there is a natural uncertainty principle between detection and localization performance, which are the two main goals. With this principle we derive a single operator shape which is optimal at any scale. The optimal detector has a simple approximate implementation in which edges are marked at maxima in gradient magnitude of a Gaussian-smoothed image. We extend this simple detector using operators of several widths to cope with different signal-to-noise ratios in the image. We present a general method, called feature synthesis, for the fine-to-coarse integration of information from operators at different scales. Finally we show that step edge detector performance improves considerably as the operator point spread function is extended along the edge.
Automated personal authentication using biometric features is getting more and more popular for solving the security problems. A new branch of biometric technology, palmprint authentication, has attracted increasing amount of attention because palmprints are abundant of line features and thus low reso- lution images can be used. In this paper, we propose a new approach for palm- print feature extraction, template representation and matching. Using of time se- ries technologies such as SAX representation and MINDIST calculation is the key to make this new approach simple, flexible and reliable. Experiment shows that this approach can achieve an accuracy of 98.7% when performing one to one verification on a 600 palmprints database. This new approach, which is very computationally efficient, also facilitates the biometric feature fusion as well as palmprint identification using incomplete templates.
This paper presents a novel Daubechies-based kernel Princi- pal Component Analysis (PCA) method by integrating the Daubechies wavelet representation of palm images and the kernel PCA method for palmprint recognition. The palmprint is first transformed into the wavelet domain to decompose palm images and the lowest resolution subband coefficients are chosen for palm representation. The kernel PCA method is then applied to extract non-linear features from the subband coefficients. Finally, weighted Euclidean linear distance based NN clas- sifier and support vector machine (SVM) are comparatively performed for similarity measurement. Experimental results on PolyU Palmprint Databases demonstrate that the proposed approach achieves highly com- petitive performance with respect to the published palmprint recognition approaches.
This paper aims to study the accuracy and robustness of personal identification or verification systems where palmprint is the only modality available or utilized. Three different representations of palmprint are fused at the score-level by the sum rule, and at the decision-level by weighed or majority votes. Results showed that fusion at the score-level is easier to formulate and justify, and performs better than fusing at the decision-level. On a database of 340 subjects (10 samples/class), 10-fold and 2-fold cross-validation is accurate to 99.8% and 99.2% respectively. When operating as a verification system, it can achieve a false acceptance rate of 0.68% while maintaining a false rejection rate of 5%.
"Correlation is a robust and general technique for pattern recognition and is used in many applications, such as automatic target recognition, biometric recognition and optical character recognition. The design, analysis, and use of correlation pattern recognition algorithms require background information, including linear systems theory, random variables and processes, matrix/vector methods, detection and estimation theory, digital signal processing, and optical processing.". "This book provides a needed review of this diverse background material and develops the signal processing theory, the pattern recognition metrics, and the practical application know-how from basic premises. It shows both digital and optical implementations. It also contains state-of-the-art technology presented by the team that developed it and includes case studies of significant current interest, such as face and target recognition." "It is suitable for advanced undergraduate or graduate students taking courses in pattern recognition theory, whilst reaching technical levels of interest to the professional practitioner."--BOOK JACKET.
The wavelet theory has become hot in the last few years for its important relative characters, such as subband coding, multiresolution analysis and filter banks. In this paper, we propose a novel method of feature extraction for palmprint identification based on wavelet transform, which is very efficient to handle the textural characteristics of palmprint images at low resolution. The matching results show that the proposed feature extraction method is efficient in terms of matching accuracy and computational speed.
ABSTRACT Amethod,for palmprint ,verification has been ,proposed. The verification system ,is consists of two ,steps: One is enrolment step; the second one is verification step. In the enrollment step the palm is scanned and its regionof interest (ROI) is extracted. After then ROI and it is owner’s name ,stored in the ,database. Several palm ,images ,are stored database ,like using ,same methods. In verification ,steps palm ,image ,is scanned ,for verification. The image’s ROI is extracted. The feature vector has been ,obtained ,by applying ,cosine ,transform ,to a ,data extracted from ,ROI. The ROI is compared ,with the template images, which are in the database by using cosine transform and Euler method. During the comparison time, if one of the template,image ,comparison ,results is smaller ,than threshold level, it can be said that the template image’s owner is also a the new palm’s owner.
Objective methods for assessing perceptual image quality traditionally attempted to quantify the visibility of errors (differences) between a distorted image and a reference image using a variety of known properties of the human visual system. Under the assumption that human visual perception is highly adapted for extracting structural information from a scene, we introduce an alternative complementary framework for quality assessment based on the degradation of structural information. As a specific example of this concept, we develop a Structural Similarity Index and demonstrate its promise through a set of intuitive examples, as well as comparison to both subjective ratings and state-of-the-art objective methods on a database of images compressed with JPEG and JPEG2000.
We present a palmprint approach to identifying individuals. Some significant features covering both geometrical and structural characteristics can be extracted from the palmprint to distinguish a person from others. The experiments show that this approach can be effectively used as a new biometric technology for automated personal identification.
This paper investigates the performance improvement for palmprint authentication using multiple classifiers. The proposed methods on personal authentication using palmprints can be divided into three categories; appearance- , line -, and texture-based. A combination of these approaches can be used to achieve higher performance. We propose to simultaneously extract palmprint features from PCA, Line detectors and Gabor-filters and combine their corresponding matching scores. This paper also investigates the comparative performance of simple combination rules and the hybrid fusion strategy to achieve performance improvement. Our experimental results on the database of 100 users demonstrate the usefulness of such approach over those based on individual classifiers.
Palmprint is a new biometric method to recognize a person. The most
important feature of palmprint is the lines. In this paper, a set of
line detector is devised for palmprint. There are two parameters in
these detectors, one controls the smoothness and connection of the
lines, the other controls the width of lines which can be detected. The
lines in different directions are detected by corresponding direction
detectors and then fused into one edge image. In training stage, the
lines of the training samples are represented and stored with chain
code. In the verification stage, the lines are matched using Hausdorff
distance. Experimental results show the efficiency of this method.
Traditional cryptosystems are based on passwords, which can be cracked (simple ones) or forgotten (complex ones). This paper
proposes a novel cryptosystem based on palmprints. This system directly uses the palmprint as a key to encrypt/decrypt information.
The information of a palmprint is so complex that it is very difficult, if not impossible, to crack the system while it need
not remember anything to use the system. In the encrypting phase, a 1024 bits binary string is extracted from the palmprints
using differential operations. Then the string is translated to a 128 bits encrypting key using a Hash function, and at the
same time, an error-correct-code (ECC) is generated. Some general encryption algorithms use the 128 bits encrypting key to
encrypt the secret information. In decrypting phase, the 1024 bits binary string extracted from the input palmprint is first
corrected using the ECC. Then the corrected string is translated to a decrypting key using the same Hash function. Finally,
the corresponding general decryption algorithms use decrypting key to decrypt the information. The experimental results show
that the accuracy and security of this system can meet the requirement of most applications.
In palmprint recognition field, orientation based approaches are thought to achieve the best results in terms of recognition rates. In this paper, we propose a novel orientation based scheme, in which three strategies, the modified finite Radon transform, enlarged training set and pixel to area matching, have been designed to further improve its performance. The experimental results of verification conducted on Hong Kong Polytechnic University Palmprint Database show that our approach has higher recognition rates and faster processing speed.
A new palmprint classification method is proposed in this paper by using the dual-tree complex wavelet transform. The dual-tree complex wavelet transform has such important properties as the approximate shift-invariance and high directional selectivity. These properties are very important in invariant palmprint classification. Support vector machines are used as a classifier and the Gaussian radial basis function kernel is selected in the experiments. Experimental results show that the dual-tree complex wavelet features outperform the scalar wavelet features, and three previously developed methods. We conclude that the dual-tree complex wavelet features should be used for invariant palmprint classification instead of the scalar wavelet features
Biometrics-based verification is an effective approach to personal authentication using biological features extracted from the individual. In this paper, we propose specific verification technology by making use of hand-based features. Two hand-based features, the hand geometry and the palmprint, are simultaneously grabbed by the CCD camera-based devices. Basically, geometrical features of the hands are used to roughly verify the identity. The samples possessing the confused hand shapes should be to re-check by the palmprint features. First, the crucial points and the ROI of palmprint are determined in the preprocessing stage. The hand shape features of length 11 are computed from these detected points. Next, the multi-resolutional palmprint features are extracted from the ROI and the three middle fingers. In that way the reference vectors are obtained for computing the similarity values in various resolutions. In addition, the various verified results in multiple resolutions are integrated to achieve a better performance by using the positive Boolean function (PBF) and the bootstrapping method. Experimental results were conducted to show the effectiveness of our proposed approaches.
This paper describes the design and development of a multimodal biometric personal recognition system based on features extracted from a set of 14 geometrical parameters of the hand, the palmprint, four digitprints, and four fingerprints. The features are extracted from a single high-resolution gray-scale image of the palmar surface of the hand using the linear discriminant analysis (LDA) appearance-based feature-extraction approach. The information contained in the extracted features is combined at the matching-score level. The resolutions of the palmprint, digitprint and fingerprint sub-images, the similarity/dissimilarity measures, the matching-score normalization technique, and the fusion rule at the matching-score level, which optimize the system performance, were determined experimentally. The biometric system, when using a system configuration with optimum parameters, showed an average equal error rate (EER) of 0.0005%, which makes it sufficiently accurate for use in high-security biometric systems.
Currently there is much interest in the use of biometrics for authentication and identification applications. This has been heightened most recently because of the threat of terrorism. Biometrics authentication and identification systems offer several advantages over systems based on knowledge or possession such as unsupervised (legacy) password/PIN-based systems and supervised (legacy) passport-based systems. To optimize security it is important that biometrics authentication systems are designed to withstand different sources of attack. We identify some such threats to biometrics systems and detail issues related to the tradeoff between security and convenience. We further show how to estimate a biometrics’ intrinsic security, sometimes called a biometrics’ individuality, with fingerprints as an example.
Recently, multi-modal biometric fusion techniques have attracted increasing atove the recognition performance in some difficult biometric problems. The small sample biometric recognition problem is such a research difficulty in real-world applications. So far, most research work on fusion techniques has been done at the highest fusion level, i.e. the decision level. In this paper, we propose a novel fusion approach at the lowest level, i.e. the image pixel level. We first combine two kinds of biometrics: the face feature, which is a representative of contactless biometric, and the palmprint feature, which is a typical contacting biometric. We perform the Gabor transform on face and palmprint images and combine them at the pixel level. The correlation analysis shows that there is very small correlation between their normalized Gabor-transformed images. This paper also presents a novel classifier, KDCV-RBF, to classify the fused biometric images. It extracts the image discriminative features using a Kernel discriminative common vectors (KDCV) approach and classifies the features by using the radial base function (RBF) network. As the test data, we take two largest public face databases (AR and FERET) and a large palmprint database. The experimental results demonstrate that the proposed biometric fusion recognition approach is a rather effective solution for the small sample recognition problem.
Automatic biometric systems based on human characteristics for personal identification have attracted great attention. Their performance highly depends on the distinctive information in the biometrics. Identical twins having the closest genetics-based relationship are expected to have maximum similarity in their biometrics. Classifying identical twins is a challenging problem for some automatic biometric systems. Palmprint has been studied for personal identification for over seven years. Most of the previous research concentrates on algorithm development. In this paper, we systemically examine palmprints from the same DNA for automatic personal identification and to uncover the genetically related palmprint features. The experimental results show that the three principal lines and some portions of weak lines are genetically related features but our palms still contain rich genetically unrelated features for classifying identical twins.
Unimodal analysis of palmprint and palm vein has been investigated for person recognition. One of the problems with unimodality is that the unimodal biometric is less accurate and vulnerable to spoofing, as the data can be imitated or forged. In this paper, we present a multimodal personal identification system using palmprint and palm vein images with their fusion applied at the image level. The palmprint and palm vein images are fused by a new edge-preserving and contrast-enhancing wavelet fusion method in which the modified multiscale edges of the palmprint and palm vein images are combined. We developed a fusion rule that enhances the discriminatory information in the images. Here, a novel palm representation, called “Laplacianpalm” feature, is extracted from the fused images by the locality preserving projections (LPP). Unlike the Eigenpalm approach, the “Laplacianpalm” finds an embedding that preserves local information and yields a palm space that best detects the essential manifold structure. We compare the proposed “Laplacianpalm” approach with the Fisherpalm and Eigenpalm methods on a large data set. Experimental results show that the proposed “Laplacianpalm” approach provides a better representation and achieves lower error rates in palm recognition. Furthermore, the proposed multimodal method outperforms any of its individual modality.
Recently, biometric palmprint has received wide attention from researchers. It is well-known for several advantages such as stable line features, low-resolution imaging, low-cost capturing device, and user-friendly. In this paper, an automated scanner-based palmprint recognition system is proposed. The system automatically captures and aligns the palmprint images for further processing. Several linear subspace projection techniques have been tested and compared. In specific, we focus on principal component analysis (PCA), fisher discriminant analysis (FDA) and independent component analysis (ICA). In order to analyze the palmprint images in multi-resolution-multi-frequency representation, wavelet transformation is also adopted. The images are decomposed into different frequency subbands and the best performing subband is selected for further processing. Experimental result shows that application of FDA on wavelet subband is able to yield both FAR and FRR as low as 1.356 and 1.492% using our palmprint database.
In this paper, we propose a novel robust line orientation code for palmprint verification, whose performance is improved by using three strategies. Firstly, a modified finite Radon transform (MFRAT) is proposed, which can extract the orientation feature of palmprint more accurately and solve the problem of sub-sampling better. Secondly, we construct an enlarged training set to solve the problem of large rotations caused by imperfect preprocessing. Finally, a matching algorithm based on pixel-to-area comparison has been designed, which has better fault tolerant ability. The experimental results of verification on Hong Kong Polytechnic University Palmprint Database show that the proposed approach has higher recognition rate and faster processing speed.
Although several palmprint representations have been proposed for personal authentication, there is little agreement on which palmprint representation can provide best representation for reliable authentication. In this paper, we characterize user's identity through the simultaneous use of three major palmprint representations and achieve better performance than either one individually. This paper also investigates comparative performance between Gabor, line and appearance based palmprint representations and using their score and decision level fusion. The combination of various representations may not always lead to higher performance as the features from the same image may be correlated. Therefore we also propose product of sum rule which achieves better performance than any other fixed combination rules. Our experimental results on the database of 100 users achieve 34.56% improvement in performance (equal error rate) as compared to the case when features from single palmprint representation are employed. The proposed usage of multiple palmprint representations, especially on the peg-free and non-contact imaging setup, achieves promising results and demonstrates its usefulness.
In this paper, we propose a feature-level fusion approach for improving the efficiency of palmprint identification. Multiple elliptical Gabor filters with different orientations are employed to extract the phase information on a palmprint image, which is then merged according to a fusion rule to produce a single feature called the Fusion Code. The similarity of two Fusion Codes is measured by their normalized hamming distance. A dynamic threshold is used for the final decisions. A database containing 9599 palmprint images from 488 different palms is used to validate the performance of the proposed method. Comparing our previous non-fusion approach and the proposed method, improvement in verification and identification are ensured.
User verification systems that use a single biometric indicator often have to contend with noisy sensor data, restricted degrees of freedom, non-universality of the biometric trait and unacceptable error rates. Attempting to improve the performance of individual matchers in such situations may not prove to be effective because of these inherent problems. Multibiometric systems seek to alleviate some of these drawbacks by providing multiple evidences of the same identity. These systems help achieve an increase in performance that may not be possible using a single biometric indicator. Further, multibiometric systems provide anti-spoofing measures by making it difficult for an intruder to spoof multiple biometric traits simultaneously. However, an effective fusion scheme is necessary to combine the information presented by multiple domain experts. This paper addresses the problem of information fusion in biometric verification systems by combining information at the matching score level. Experimental results on combining three biometric modalities (face, fingerprint and hand geometry) are presented.
In this paper, a novel method for palmprint recognition, called Fisherpalms, is proposed. In this method, each pixel of a palmprint image is considered as a coordinate in a high-dimensional image space. A linear projection based on Fisher’s linear discriminant is used to project palmprints from this high-dimensional original palmprint space to a significantly lower dimensional feature space (Fisherpalm space), in which the palmprints from the different palms can be discriminated much more efficiently. The relationship between the recognition accuracy and the resolution of the palmprint image is also investigated. The experimental results show that, in the proposed method, the palmprint images with resolution 32 × 32 are optimal for medium security biometric systems while those with resolution 64 × 64 are optimal for high security biometric systems. High accuracies (>99%) have been obtained by the proposed method and the speed of this method (responding time⩽0.4 s) is rapid enough for real-time palmprint recognition.
This paper proposes a novel and successful method for recognizing palmprint based on radial basis probabilistic neural network (RBPNN) proposed by us. The RBPNN is trained by the orthogonal least square (OLS) algorithm and its structure is optimized by the recursive OLS algorithm (ROLSA). The Hong Kong Polytechnic University (PolyU) palmprint database, which is pre-processed by a fast fixed-point algorithm for independent component analysis (FastICA), is exploited to test our approach. The experimental results show that the RBPNN achieves higher recognition rate and better classification efficiency than other usual classifiers.
This paper presents a new approach for personal authentication using hand images. The proposed method attempts to improve the performance of palmprint-based verification system by integrating hand geometry features. Unlike prior bimodal biometric systems, the users do not have to undergo the inconvenience of using two different sensors in our system since the palmprint and hand geometry images are acquired simultaneously using a single camera. The palmprint and handshape images are used to extract salient features and are then examined for their individual and combined verification performances. The image acquisition setup used here is inherently simple and it does not employ any special illumination nor does it use any alignment pegs to cause any inconvenience to the users. Our experiments on an image database of 100 users achieve promising results and suggest that the fusion of matching scores can achieve better performance than the fusion at representation.
In this paper, we propose a novel palmprint verification approach based on principal lines. In feature extraction stage, the modified finite Radon transform is proposed, which can extract principal lines effectively and efficiently even in the case that the palmprint images contain many long and strong wrinkles. In matching stage, a matching algorithm based on pixel-to-area comparison is devised to calculate the similarity between two palmprints, which has shown good robustness for slight rotations and translations of palmprints. The experimental results for the verification on Hong Kong Polytechnic University Palmprint Database show that the discriminability of principal lines is also strong.
Most previous research in the area of personal authentication using the palmprint as a biometric trait has concentrated on enhancing accuracy yet resistance to attacks is also a centrally important feature of any biometric security system. In this paper, we address three relevant security issues: template re-issuances, also called cancellable biometrics,1 replay attacks, and database attacks. We propose to use a random orientation filter bank (ROFB) as a feature extractor to generate noise-like feature codes, called Competitive Codes for templates re-issuances. Secret messages are hidden in templates to prevent replay and database attacks. This technique can be regarded as template watermarking. A series of analyses is provided to evaluate the security levels of the measures.
Human authentication is the security task whose job is to limit access to physical locations or computer network only to those with authorisation. This is done by equipped authorised users with passwords, tokens or using their biometrics. Unfortunately, the first two suffer a lack of security as they are easy being forgotten and stolen; even biometrics also suffers from some inherent limitation and specific security threats. A more practical approach is to combine two or more factor authenticator to reap benefits in security or convenient or both. This paper proposed a novel two factor authenticator based on iterated inner products between tokenised pseudo-random number and the user specific fingerprint feature, which generated from the integrated wavelet and Fourier–Mellin transform, and hence produce a set of user specific compact code that coined as BioHashing. BioHashing highly tolerant of data capture offsets, with same user fingerprint data resulting in highly correlated bitstrings. Moreover, there is no deterministic way to get the user specific code without having both token with random data and user fingerprint feature. This would protect us for instance against biometric fabrication by changing the user specific credential, is as simple as changing the token containing the random data. The BioHashing has significant functional advantages over solely biometrics i.e. zero equal error rate point and clean separation of the genuine and imposter populations, thereby allowing elimination of false accept rates without suffering from increased occurrence of false reject rates.
This paper investigates the feasibility of person identification based on feature points extracted from palmprint images. Our approach first extracts a set of feature points along the prominent palm lines (and the associated line orientation) from a given palmprint image. Next we decide if two palmprints belong to the same hand by computing a matching score between the corresponding sets of feature points of the two palmprints. The two sets of feature points/orientations are matched using our previously developed point matching technique which takes into account the non-linear deformations as well as the outlier points present in the two sets. The estimates of the matching score distributions for the genuine and imposter sets of palm pairs showed that palmprints have a good discrimination power. The overlap between the genuine and imposter distributions was found to be about 5%. Our preliminary results indicate that adding palmprint information may improve the identity verification provided by fingerprints in cases where fingerprint images cannot be properly acquired (e.g., due to dry skin).
As a result of the growing demand for accurate and reliable personal authentication, biometric recognition, a substitute for or complement to existing authentication technologies, has attracted considerable attention. It has recently been reported that, along with its variants, BioHashing, a new technique that combines biometric features and a tokenized (pseudo-) random number (TRN), has achieved perfect accuracy, having zero equal error rates (EER) for faces, fingerprints and palmprints. There are, however, anomalies in this approach. These are identified in this paper, in which we systematically analyze the details of the approach and conclude that the claim of having achieved a zero EER is based upon an impractical hidden assumption. We simulate the claimants’ experiments and find that it is not possible to achieve their reported performance without the hidden assumption and that, indeed, the results are worse than when using the biometric alone.
A multimodal biometric scheme using watermarking technique to provide more secure and reliable personal recognition is proposed
in this paper. Two distinct biometric traits have been under consideration: palmprint and knuckleprint. The palmprint image
is chosen to be the host image. Knuckleprint biometric feature is selected to use as watermark hidden in the host image. Such
that knuckleprint watermark not only protects palmprint biometric data, but also can be used as a covert recognition. Meanwhile,
the bimodal biometrics recognition provides the improvement in the accuracy performance of the system. The experiment results
demonstrate the effectiveness of the proposed method.
Biometric systems are widely applied since they offer inherent ad- vantages over traditional knowledge-based and token-based personal authenti- cation approaches. This has led to the development of palmprint systems and their use in several real applications. Biometric systems are not, however, in- vulnerable. The potential attacks including replay and brute-force attacks have to be analyzed before they are massively deployed in real applications. With this in mind, this paper will consider brute-force break-ins directed against palmprint verification systems.
A new approach for the personal identification using hand images is presented. This paper attempts to improve the performance of palmprint-based verification system by integrating hand geometry features. Unlike other bimodal biometric systems, the users does not have to undergo the inconvenience of passing through two sensors since the palmprint and hand geometry features can be are acquired from the same image, using a digital camera, at the same time. Each of these gray level images are aligned and then used to extract palmprint and hand geometry features. These features are then examined for their individual and combined performance. The image acquisition setup used in this work was inherently simple and it does not employ any special illumination nor does it use any pegs to cause any inconvenience to the users. Our experimental results on the image dataset from 100 users confirm the utility of hand geometry features with those from palmprints and achieve promising results with a simple image acquisition setup.
This paper presents a novel approach of palmprint authentication by matching the orientation code. In this approach, each
point on a palmprint is assigned a orientation. And all point orientations of a palmprint constitute a palmprint orientation
code (POC). Four directional templates with different directions are devised to extract the POC. The similarity of two POC
is measured using their Hamming distance. This approach is tested on the public PolyU Palmprint Database and the experimental
results demonstrate its effectiveness.
Traditional personal authentication methods have many instinctive defects. Biometrics is an effective technology to overcome
these defects. The unimodal biometric systems, which use a single trait for authentication, can result in some problems like
noisy sensor data, non-universality and/or lack of distinctiveness of the biometric trait, unacceptable error rates, and spoof
attacks. These problems can be addressed by using multi-biometric features in the system. This paper investigates the fusion
of palmprint and iris for personal authentication. The features of the palmprint and the iris are first extracted and matched
respectively. Then these matching distances are normalized. Finally, the normalized distances are fused to authenticate the
identity. The experimental results show that combining palmprint and iris can dramatically improve the accuracy of the system.
In recent years, palmprint identification has been developed for security purpose. In this paper, a novel scheme of palmprint
identification is proposed. We apply 2-dimensional 2_band (Discrete Wavelet Transform) and 3_band wavelet decomposition to
get the low subband images, and then use them as identification feature vectors. We choose support vector machines as classifier.
The experimental results demonstrate that it is a simple and accurate identification strategy and the correct recognition
rate is high up to 100%.
This paper presents a novel method of feature-level fusion (FLF) based on kernel principle component analyze (KPCA). The proposed
method is applied to fusion of hand biometrics include palmprint, hand shape and knuckleprint, and we name the new feature
as “handmetric”. For different kind of samples, polynomial kernel is employed to generate the kernel matrixes that indicate
the relationship among them. While fusing these kernel matrixes by fusion operators and extracting principle components, the
handmetric feature space is established and nonlinear feature-level fusion projection could be implemented. The experimental
results testify that the method is efficient for feature fusion, and could keep more identity information for verification.
This paper presents a novel approach of palmprint identification with Hidden Markov Models (HMMs). Palmprint is first aligned
and normalized by using the boundary of the fingers. Then the continuous HMMs are used to identify palmprints. The palmprint
features are extracted by using Sobel operators and projecting technique. It shows that HMMs with six states and two Gaussian
mixtures can obtain the highest identification rate, 97.80%, in one-to-320 matching test. Experimental results demonstrate
the feasibility of HMMs on the palmprint identification task.
A feature-level fusion approach is proposed for improving the efficiency of palmprint identification. Multiple Gabor filters
are employed to extract the phase information on a palmprint image, which is then merged according to a fusion rule to produce
a single feature called the Fusion Code. The similarity of two Fusion Codes is measured by their normalized hamming distance.
A database containing 7,752 palmprint images from 386 different palms is used to validate the performance of the proposed
method. Empirically comparing our previous non-fusion approach and the proposed method, improvement in verification is ensured
This paper presents a novel fusion strategy for personal identification using face and palmprint biometrics. In the context
of biometrics, three levels of information fusion schemes have been suggested: feature extraction level, matching score level
and decision level. This work considers the first level fusion scheme. The purpose of our paper is to investigate whether
the integration of face and palmprint biometrics can achieve higher performance that may not be possible using a single biometric
indicator alone. Both Principal Component Analysis (PCA) and Independent Component Analysis (ICA) are considered in this feature
vector fusion context. We compare the results of the combined biometrics with the results of the individual face and palmprint.
It is found that the performance is significantly improved in both cases, especially in the case of feature fusion using ICA
obtaining encouraging results with a 99.17% recognition accuracy rate using a test set sized of 40 people.