No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Cancelable Biometric Templates for Low-end Devices
Abstract
The use of biometrics for access control on hand-held devices such as smartphones and tablets is in common use now. The security of biometrics and privacy of users’ data has become more important in this scenario. The templates stored in the database or a network are prone to different attacks. Since, biometrics are unique to an individual, their loss imparts the loss of privacy and identity. Unlike passwords, biometrics once lost or stolen cannot be recovered. Cancelable biometrics is one way to address these issues. In cancelable biometrics, pseudo-identities are used in place of original biometric identities and multiple pseudo-identities can be generated for an individual. These pseudo-identities are supposed to be non-invertible and attackers can not extract original biometric from pseudo-identities. If one pseudo-identity is compromised in any way, another pseudo-identity can be issued. This way cancelable biometrics can provide privacy and security to biometrics.
This dissertation proposes three methods for generating cancelable biometric templates. Contributions have been made for transformations at feature level and also for extracting and compressing features. Two contributions have been made for feature level transformations using Binary Coding and Random Projection (RP). These techniques not only meet the requirements of performance, security, and privacy for many modalities but are also capable of dimension reduction without using any predefined dimension reduction algorithms. Rigorous experimentations have been performed for evaluating these methods on various datasets of modalities such as Face Near Infrared (NIR), Palm Print, Palm Vein, Dorsal Vein, Wrist Vein, and Knuckle Print. The evaluation of these methods has been done in three different scenarios for addressing different uses and attacks possible.
Convolutional AutoEncoders (CAEs) are a great tool for extracting features from images and compressing them to a lower dimension called latent space. Latent space is generated from the input images by extracting the relevant and the most useful features required for approximating the images. In the proposed work, a CAE is used for feature extraction.Extracted features are used for generating cancelable template using Random Salting and Random Convolution. The architecture has been trained for Palm Print, Palm Vein, and Wrist Vein images combined from different datasets namely, CASIA, PolyU, and CIEPUT. The proposed method has been rigorously experimented and evaluated for these modalities. The same evaluation protocol is used for evaluating this method too.
ResearchGate has not been able to resolve any citations for this publication.
Various template protection schemes are providing solutions to fulfil privacy preservation in biometric recognition systems, among them Cancellable Biometrics (CB). In this paper we propose two CB schemes, so called non-invertible many-to-one transforms, that alter the image's grey values in key-dependent manner. The obtained recognition performance and unlinkability results are compared to other signal domain cancellable transformation schemes proposed earlier in literature (block re-mapping and warping). Experiments are conducted on a multi-biometrics dataset including finger-vein, hand-vein and thermal face images. In particular, for thermal face biometrics this represents the first study concerning uni-modal template protection techniques and their respective evaluation.
Biometrics are being increasingly used across the world, but it also raises privacy and security concerns of the enrolled identities. The main reason is due to the fact that biometrics are not cancelable and if compromised may give access to the intruder. Cancelable biometric template is a solution to this problem which can be reissued if compromised. In this paper, we suggest a simple and powerful method called Random Permutation Locality Preserving Projection (RP-LPP) for Cancelable Biometric Recognition. Here, we exploit the mathematical relationship between the eigenvalues and eigenvectors of the original biometric image and its randomly permuted version is exploited for carrying out cancelable biometric recognition. The proposed technique work in a cryptic manner by accepting the cancelable biometric template and a key (called PIN) issued to a user. The effectiveness of the proposed techniques is demonstrated on three freely available face (ORL), iris (UBIRIS) and ear (IITD) datasets against state-of-the-art methods. The advantages of proposed technique are (i) the classification accuracy remains unaffected due to cancelable biometric templates generated using random permutation, (ii) security and quality of generated templates and (iii) robustness across different biometrics. In addition, no image registration is required for performing recognition.
A multimodal biometric system integrates information from more than one biometric modality to improve the performance of each individual biometric system and make the system robust to spoof attacks. In this paper, we propose a secure multimodal biometric system that uses convolution neural network (CNN) and Q-Gaussian multi support vector machine (QG-MSVM) based on a different level fusion. We developed two authentication systems with two different level fusion algorithms: a feature level fusion and a decision level fusion. The feature extraction for individual modalities is performed using CNN. In this step, we selected two layers from CNN that achieved the highest accuracy, in which each layer is regarded as separated feature descriptors. After that, we combined them using the proposed internal fusion to generate the biometric templates. In the next step, we applied one of the cancelable biometric techniques to protect these templates and increase the security of the proposed system. In the authentication stage, we applied QG-MSVM as a classifier for authentication to improve the performance. Our systems were tested on several publicly available databases for ECG and fingerprint. Experimental results show that the proposed multimodal systems are efficient, robust and reliable than existing multimodal authentication systems.
Leakage of unprotected biometric authentication data has become a high-risk threat for many applications. Lots of researchers are investigating and designing novel authentication schemes to prevent such attacks. However, the biggest challenge is how to protect biometric data while keeping the practical performance of identity verification systems. For the sake of tackling this problem, this paper presents a novel finger vein recognition algorithm by using secure biometric template scheme based on deep learning and random projections, named FVR-DLRP. FVR-DLRP preserves the core biometric information even with the user’s password cracked, whereas the original biometric information is still safe. The results of experiment show that the algorithm FVR-DLRP can maintain the accuracy of biometric identification while enhancing the uncertainty of the transformation, which provides better protection for biometric authentication.
Wide spread use of biometric based authentication requires security of biometric data against identity thefts. Cancelable biometrics is a recent approach to address the concerns regarding privacy of biometric data, public confidence, and acceptance of biometric systems. This work proposes a template protection approach which generates revocable binary features from phase and magnitude patterns of log-Gabor filters. Multi-level transformations are applied at signal and feature level to distort the biometric data using user specific tokenized variables which are observed to provide better performance and security against information leakage under correlation attacks. A thorough analysis is performed to study the performance, non-invertibility, and changeability of the proposed approach under stolen token scenario on multiple biometric modalities. It is revealed that generated templates are non-invertible, easy to revoke, and also deliver good performance.
This work presents a palmprint recognition approach based on the local distribution of uniform patterns. Preprocessing segments palmprint region from foreground of image as well as aligns the palmprint along the line between tips of middle finger and mid of wrist. Palmprint texture has line and wrinkles like features which are a type of uniform patterns. Uniform LBP (ULBP) refers to the pattern of uniform appearance with limited discontinuities. ULBP histograms are used as features to handle occlusion upto 36%. Experiments are performed on 400 classes of the PolyU 2D, 600 classes of CASIA and 150 classes of IIITDMJ palmprint database. Correct identification rates of 99.6% for normal palmprints and 99% for randomly occluded palmprints are obtained on PolyU 2D database.
In this study, the application of adaptive Bloom filters to binary iris biometric feature vectors, that is, iris-codes, is proposed. Bloom filters, which have been established as a powerful tool in various fields of computer science, are applied in order to transform iris-codes to a rotation-invariant feature representation. Properties of the proposed Bloom filter-based transform concurrently enable (i) biometric template protection, (ii) compression of biometric data and (iii) acceleration of biometric identification, whereas at the same time no significant degradation of biometric performance is observed. According to these fields of application, detailed investigations are presented. Experiments are conducted on the CASIA-v3 iris database for different feature extraction algorithms. Confirming the soundness of the proposed approach, the application of adaptive Bloom filters achieves rotation-invariant cancellable templates maintaining biometric performance, a compression of templates down to 20-40% of original size and a reduction of bit-comparisons to less than 5% leading to a substantial speed-up of the biometric system in identification mode.
Cancelable biometrics is an important biometric template protection scheme and can effectively address privacy and security concerns in the case of stored biometric templates being compromised. This paper presents a Hadamard transform-based approach to the design of cancelable fingerprint templates. The proposed cancelable templates are alignment-free and hence do not suffer from inaccurate fingerprint registration. The proposed method aims to protect the binary string's frequency-domain samples because they include essential information about original fingerprint minutiae. The protection of the binary string's frequency-domain samples is achieved by the proposed partial Hadamard transform. The non-invertible transformation involved in our approach features a partial Hadamard matrix, which can be readily formed by a randomly generated index vector. A compromised template can be canceled and a new one be produced by generating a different index vector. The proposed approach is evaluated over the publicly available databases FVC2002 DB2 and DB3. The experimental results demonstrate that the performance of the new method is satisfactory compared to those of the existing alignment-free cancelable fingerprint templates.
A large portion of system breaches are caused by authentication failure, either during the login process or in the post-authentication session; these failures are themselves related to the limitations associated with existing authentication methods. Current authentication methods, whether proxy based or biometrics based, are not user-centric and/or endanger users’ (biometric) security and privacy. In this paper, we propose a biometrics based user-centric authentication approach. This method involves introducing a reference subject (RS), securely fusing the user’s biometrics with the RS, generating a BioCapsule (BC) from the fused biometrics, and employing BCs for authentication. Such an approach is user friendly, identity bearing yet privacy-preserving, resilient, and revocable once a BC is compromised. It also supports “one-click sign-on” across systems by fusing the user’s biometrics with a distinct RS on each system. Moreover, active and non-intrusive authentication can be automatically performed during post-authentication sessions. We formally prove that the secure fusion based approach is secure against various attacks. Extensive experiments and detailed comparison with existing approaches show that its performance (i.e., authentication accuracy) is comparable to existing typical biometric approaches and the new BC based approach also possesses many desirable features such as diversity and revocability.
Our daily interactions are based on recognizing people. As information technology advances, our interactions will be accomplished through newly designed interfaces, with a vital element being the automated process of recognition of a persons real identity: Biometrics. In recent years, biometrics has moved from using fingerprints, to many different methods of assessing human physical and behavioural traits. This useful guide introduces a new performance evaluation framework designed to provide complete coverage of performance evaluation of major biometric systems. Two key areas are presented: The first gives a unique snapshot of the performance evaluation of various biometrics within a common evaluation framework (databases and protocols). The second presents a state-of-the-art benchmarking evaluation framework for use in future performance evaluations comprised of open-source reference systems.
In this paper, we address the issue of producing cancelable biometric templates; a necessary feature in the deployment of any biometric authentication system. We propose a novel scheme that encrypts the training images used to synthesize the single minimum average correlation energy filter for biometric authentication. We show theoretically that convolving the training images with any random convolution kernel prior to building the biometric filter does not change the resulting correlation output peak-to-sidelobe ratios, thus preserving the authentication performance. However, different templates can be obtained from the same biometric by varying the convolution kernels thus enabling the cancelability of the templates. We evaluate the proposed method using the illumination subset of the CMU pose, illumination, and expressions (PIE) face dataset. Our proposed method is very interesting from a pattern recognition theory point of view, as we are able to 'encrypt' the data and perform recognition in the encrypted domain that performs as well as the unencrypted case, regardless of the encryption kernel used; we show analytically that the recognition performance remains invariant to the proposed encryption scheme, while retaining the desired shift-invariance property of correlation filters.
The usage of finger knuckle images for personal identification has shown promising results and generated lot of interest in biometrics. In this work, we investigate a new approach for efficient and effective personal identification using KnuckleCodes. The enhanced knuckle images are employed to generate KnuckleCodes using localized Radon transform that can efficiently characterize random curved lines and creases. The similarity between two KnuckleCodes is computed from the minimum matching distance that can account for the variations resulting from translation and positioning of fingers. The feasibility of the proposed approach is investigated on the finger knuckle database from 158 subjects. The experimental results, i.e., equal error rate of 1.08% and rank one recognition rate of 98.6%, suggest the utility of the proposed approach for online human identification.
Convolutional autoencoders are a great tool for extracting features from images and compressing them to a lower dimension called latent space. A latent space vector is generated from the input images by extracting the relevant and the most useful features required for approximating the images. In the proposed work, a convolutional autoencoder is used for feature extraction, random noise and random convolution are used for generating cancelable template from these features. This architecture has been trained for palm vein, wrist vein, and palm print images combined from different datasets namely, CASIA, CIEPUT, and PolyU. The proposed method has been experimented and evaluated for various modalities such as palm print, palm vein, and wrist vein. The evaluation of these methods has been done in three different scenarios for addressing different uses and attacks possible.
In order to use biometric based authentication in banking domain, it is vital to secure biometric databases from unauthorized access. As we all know a biometric trait is immutable, thus if it is stolen it is lost forever. Therefore, securing biometric databases is a paramount concern in today’s digital World. In this paper, we have presented a comprehensive study of biometric template protection schemes majorly focusing on cancelable biometric techniques. Moreover, we have proposed a cancelable finger dorsal template generation network trained on trait specific features without using any pre-trained network framework. The highly discriminative features learned from our network are further hashed using BioHashing technique to generate cancelable finger dorsal templates. The experimental results are evaluated on two benchmark publicly available finger knuckle databases: PolyU FKP and PolyU Contactless FKI. We have also performed in depth security analysis of the proposed framework in terms of invertibility, revocability and unlinkability.
In recent years, developers have used the proliferation of biometric sensors in smart devices, along with recent advances in deep learning, to implement an array of biometrics-based authentication systems. Though these systems demonstrate remarkable performance and have seen wide acceptance, they present unique and pressing security and privacy concerns. One proposed method which addresses these concerns is the elegant, fusion-based BioCapsule method. The BioCapsule method is provably secure, privacy-preserving, cancellable and flexible in its secure feature fusion design. In this work, we extend BioCapsule to face-based recognition. Moreover, we incorporate state-of-art deep learning techniques into a BioCapsule-based facial authentication system to further enhance secure recognition accuracy. We compare the performance of an underlying recognition system to the performance of the BioCapsule-embedded system in order to demonstrate the minimal effects of the BioCapsule scheme on underlying system performance. We also demonstrate that the BioCapsule scheme outperforms or performs as well as many other proposed secure biometric techniques.
In order to achieve biometric security and enhance privacy-preserving, a novel palmprint template protection scheme based on random comparison and noise data is proposed. Firstly, Anisotropic Filter (AF) is employed to capture the orientation information of the palmprint. Then, the orientation feature of palmprint is measured by a chaotic matrix to generate secure and cancelable palmprint template. The pseudo-randomness and non-ergodicity of the chaotic matrix can guarantee the security of template. Finally, in order to enhance the privacy protection of the template, the noise data with independent and identically distributed is added, as the final cancelable palmprint template. Theoretical analysis shows that a proper amount of noise has little effect on the recognition accuracy while the privacy is enhanced. During the matching stage, the recognition accuracy can be improved by fusing matching scores at the score-layer or the decision-layer. The theoretical effect of adding noise on the performance is also analyzed. The matching scores of the experimental results are consistent with the theoretical values, which means that we can reasonably adjusted the proportion of noise data through calculations and protect palmprint privacy on the basis of ensuring the recognition accuracy. Furthermore, our methods can still achieve very high security in the worst case of secret key theft.
Cancelable biometric based template protection method proposed in this work addresses security and privacy concerns emerging from the phenomenal usage of biometric systems. Cancelable biometric transforms the original biometric identity of a user to a pseudo-biometric identity that is used for storage and matching purposes. The use of pseudo-identity mitigates privacy risks and allows revocability in case of compromise. This work proposes a novel template transformation technique named as ‘Random Distance Method’ which not only generates discriminative and privacy preserving revocable pseudobiometric identities but also reduces their size by 50%. Extensive experimentation is performed to analyze recognition and protection performance on unimodal and multimodal pseudo-identities generated with various biometric modalities like face, thermal face, palmprint, palmvein, and fingervein. It is observed that the matching performance obtained with the proposed cancelable templates in the worst-case is closer to the performance achieved in the original domain. Also, multimodal cancelable biometric templates generated with the proposed method are observed for improved performance. Further, the proposed approach is successfully analyzed for non-invertibilty, unlinkability, as well as its resistance for various types of attacks like attacks via record multiplicity, dictionary, false accepts, and brute force. IEEE
Cancelable biometric templates are transformed versions of original biometric templates used for authentication purposes. The transformation functions should fulfill the important template protection criteria of diversity, revocability, non-invertibility, and performance. Although there exists a number of transformation techniques, yet many of these techniques fail to meet security and privacy requirements in the stolen token scenario and tend to become invertible with degraded performance. The work proposes a novel cancelable biometric technique named as 'Random Slope' method for generating secure, revocable, and non-invertible templates. Two approaches (RS-V1 and RS-V2) developed using the proposed concept not only fulfill the important cancelability criteria, but also provide dimensionality reduction upto 75%. The performances of the proposed approaches are experimentally verified for various biometric modalities such as visible and thermal face, palmprint, palmvein, and fingervein. As compared to some state of the art template transformation schemes, the proposed RS-V1 and RS-V2 approaches establish their reliability and effectiveness by performing better than these existing techniques with significant reduction in dimensions.
The wide deployment of biometric recognition systems in the last two decades has raised privacy concerns regarding the storage and use of biometric data. As a consequence, the ISO/IEC 24745 international standard on biometric information protection has established two main requirements for protecting biometric templates: irreversibility and unlinkability. Numerous efforts have been directed to the development and analysis of irreversible templates. However, there is still no systematic quantitative manner to analyse the unlinkability of such templates. In this paper we address this shortcoming by proposing a new general framework for the evaluation of biometric templates’ unlinkability. To illustrate the potential of the approach, it is applied to assess the unlinkability of four state-of-the-art techniques for biometric template protection: biometric salting, Bloom filters, Homomorphic Encryption and block re-mapping. For the last technique, the proposed framework is compared with other existing metrics to show its advantages. IEEE
In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively.
In this paper, we propose a secure multibiometric system that uses deep neural networks and error-correction coding. We present a feature-level fusion framework to generate a secure multibiometric template from each user's multiple biomet-rics. Two fusion architectures, fully connected architecture and bilinear architecture, are implemented to develop a robust multibiometric shared representation. The shared representation is used to generate a cancelable biometric template that involves the selection of a different set of reliable and discriminative features for each user. This cancelable template is a binary vector and is passed through an appropriate error-correcting decoder to find a closest codeword and this codeword is hashed to generate the final secure template. The efficacy of the proposed approach is shown using a mul-timodal database where we achieve state-of-the-art matching performance, along with cancelability and security.
As a result of the growing demand for security of stored biometric data, cancelable biometric has attracted considerable attention. Cancelable biometric has advantages over other template protection methods because of diversity, revocability and non-invertibility. In this paper, a cancelable biometric using iris is proposed in which biometric features is combined with a tokenized (pseudo-) random number (TRN). The performance of the proposed cancelable biometric is compared with the base BioHashing method at best, stolen-key and stolen-biometric scenarios. The performance evaluation of the proposed algorithm is carried out over the CASIA V1.0 and CASIA V3-Interval iris databases. From the experimental results, it is observed that the proposed cancelable iris biometric outperforms base BioHashing method in terms of EER and FRR.
Face detection and alignment in unconstrained environment are challenging due to various poses, illuminations and occlusions. Recent studies show that deep learning approaches can achieve impressive performance on these two tasks. In this paper, we propose a deep cascaded multi-task framework which exploits the inherent correlation between them to boost up their performance. In particular, our framework adopts a cascaded structure with three stages of carefully designed deep convolutional networks that predict face and landmark location in a coarse-to-fine manner. In addition, in the learning process, we propose a new online hard sample mining strategy that can improve the performance automatically without manual sample selection. Our method achieves superior accuracy over the state-of-the-art techniques on the challenging FDDB and WIDER FACE benchmark for face detection, and AFLW benchmark for face alignment, while keeps real time performance.
Biometric characteristics are largely immutable, i.e. unprotected storage of biometric data provokes serious privacy threats, e.g. identity theft, limited re-newability, or cross-matching. In accordance with the ISO/IEC 24745 standard, technologies of cancelable biometrics offer solutions to biometric information protection by obscuring biometric signal in a non-invertible manner, while biometric comparisons are still feasible in the transformed domain. In the presented work alignment-free cancelable iris biometrics based on adaptive Bloom filters are proposed. Bloom filter-based representations of binary biometric templates (iris-codes) enable an efficient alignment-invariant biometric comparison while a successive mapping of parts of a binary biometric template to a Bloom filter represents an irreversible transform. In experiments, which are carried out on the CASIA - v 3 iris database, it is demonstrated that the proposed system maintains biometric performance for diverse iris recognition algorithms, protecting biometric templates at high security levels.
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.
Nonlinear principal component analysis is a novel technique for multivariate data analysis, similar to the well-known method of principal component analysis. NLPCA, like PCA, is used to identify and remove correlations among problem variables as an aid to dimensionality reduction, visualization, and exploratory data analysis. While PCA identifies only linear correlations between variables, NLPCA uncovers both linear and nonlinear correlations, without restriction on the character of the nonlinearities present in the data. NLPCA operates by training a feedforward neural network to perform the identity mapping, where the network inputs are reproduced at the output layer. The network contains an internal “bottleneck” layer (containing fewer nodes than input or output layers), which forces the network to develop a compact representation of the input data, and two additional hidden layers. The NLPCA method is demonstrated using time-dependent, simulated batch reaction data. Results show that NLPCA successfully reduces dimensionality and produces a feature space map resembling the actual distribution of the underlying system parameters.
This paper presents a novel approach for hand matching that achieves significantly improved performance even in the presence of large hand pose variations. The proposed method utilizes a 3-D digitizer to simultaneously acquire intensity and range images of the user's hand presented to the system in an arbitrary pose. The approach involves determination of the orientation of the hand in 3-D space followed by pose normalization of the acquired 3-D and 2-D hand images. Multimodal (2-D as well as 3-D) palmprint and hand geometry features, which are simultaneously extracted from the user's pose normalized textured 3-D hand, are used for matching. Individual matching scores are then combined using a new dynamic fusion strategy. Our experimental results on the database of 114 subjects with significant pose variations yielded encouraging results. Consistent (across various hand features considered) performance improvement achieved with the pose correction demonstrates the usefulness of the proposed approach for hand based biometric systems with unconstrained and contact-free imaging. The experimental results also suggest that the dynamic fusion approach employed in this work helps to achieve performance improvement of 60% (in terms of EER) over the case when matching scores are combined using the weighted sum rule.
Recent years have seen the rapid spread of biometric technologies for automatic people recognition. However, security and privacy issues still represent the main obstacles for the deployment of biometric-based authentication systems. In this paper, we propose an approach, which we refer to as BioConvolving, that is able to guarantee security and renewability to biometric templates. Specifically, we introduce a set of noninvertible transformations, which can be applied to any biometrics whose template can be represented by a set of sequences, in order to generate multiple transformed versions of the template. Once the transformation is performed, retrieving the original data from the transformed template is computationally as hard as random guessing. As a proof of concept, the proposed approach is applied to an on-line signature recognition system, where a hidden Markov model-based matching strategy is employed. The performance of a protected on-line signature recognition system employing the proposed BioConvolving approach is evaluated, both in terms of authentication rates and renewability capacity, using the MCYT signature database. The reported extensive set of experiments shows that protected and renewable biometric templates can be properly generated and used for recognition, at the expense of a slight degradation in authentication performance.
This paper evaluates the performance both of some texture measures which have been successfully used in various applications and of some new promising approaches proposed recently. For classification a method based on Kullback discrimination of sample and prototype distributions is used. The classification results for single features with one-dimensional feature value distributions and for pairs of complementary features with two-dimensional distributions are presented
Multimodal biometric systems consolidate the evidence presented by multiple biometric sources and typically provide better recognition performance compared to systems based on a single biometric modality. Although information fusion in a multimodal system can be performed at various levels, integration at the matching score level is the most common approach due to the ease in accessing and combining the scores generated by different matchers. Since the matching scores output by the various modalities are heterogeneous, score normalization is needed to transform these scores into a common domain, prior to combining them. In this paper, we have studied the performance of different normalization techniques and fusion rules in the context of a multimodal biometric system based on the face, fingerprint and hand-geometry traits of a user. Experiments conducted on a database of 100 users indicate that the application of min–max, z-score, and tanh normalization schemes followed by a simple sum of scores fusion method results in better recognition performance compared to other methods. However, experiments also reveal that the min–max and z-score normalization techniques are sensitive to outliers in the data, highlighting the need for a robust and efficient normalization procedure like the tanh normalization. It was also observed that multimodal systems utilizing user-specific weights perform better compared to systems that assign the same set of weights to the multiple biometric traits of all users.
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.
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.
Given the recent explosion of interest in human authentication, verification based on tokenized pseudo-random numbers and the user specific biometric feature (BioHashing) has received much attention. These methods have significant functional advantages over sole biometrics i.e. zero equal error rate. The main drawback of the base BioHashing method proposed in the literature relies in exhibiting low performance when an “impostor” B steals the pseudo-random numbers of A and he tries to authenticate as A. In this paper, we introduce some ideas to improve the base BioHashing approach in order to maintain a very low equal error rate when nobody steals the Hash key, and to reach good performance also when an “impostor” steals the Hash key.
This paper presents a new approach to achieve the performance improvement for the traditional palmprint authentication approaches. The cohort information is used in the matching stage but only when the matching scores are inadequate to generate reliable decisions. The cohort information can also be utilized to achieve the significant performance improvement for the combination of modalities and this is demonstrated from the experimental results in this paper. The rigorous palmprint authentication results presented in this paper are the best in the literature and confirm the utility of significant information that can be extracted from the imposter scores. The statistical estimation of confidence level for the palmprint matching requires an excellent match between the theoretical distribution and the real score distribution. The performance analysis presented in this paper, from over 29.96 million imposter matching scores, suggests that Beta-Binomial function can more accurately model the distribution of real palmprint matching scores.