No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
2D vs 3D Online Writer Identification: A Comparative Study
Abstract and Figures
Nowadays, different automatic systems for writer identification and verification are available. On-line writer identification through automatic analysis of handwriting acquired with a tablet has been widely studied. Furthermore, the recent development of Commercial Off-The-Shelf (COTS) wearables with integrated inertial measurement units (IMUs) recording limbs movement allows the study of handwriting movements executed on the air. The goal of this paper is to compare the performance of an online writer identification system while processing 2D data acquired by a tablet while writing on-paper and 3D data acquired by a smartwatch while writing on-air. To this end, a database of handwriting samples produced by the same writers while writing the same symbols in the two modalities has been built up. The results of the study show a performance gap smaller than 5% between the 2D and 3D top implementations of the system, confirming that 3D handwriting is a promising alternative for developing wearable user authentication system.
Figures - uploaded by Antonio Parziale
Author content
All figure content in this area was uploaded by Antonio Parziale
Content may be subject to copyright.
... Authors in [16] built a wristband gadget that could identify its wearers by comparing the movement of the user's wrist with the data that the wearer had entered via the keyboard. Users identification is performed on the basis of writing activities in a study conducted in [17]. 98 users were recruited for the experiment where a smartwatch accelerometer is used for the collection of data and a user identification accuracy of 89.77% accuracy is attained. ...
... Recording systems (motion tracker, tablet, smartwatch, etc.) and motor tasks (gait, reaching movements, handwriting, etc.) are selected according to the final application or the particular aspect of the movements to be investigated. Pen-tip movements during signing, drawing or writing acquired with graphic tablets and smartpads have been largely adopted (Diaz et al., 2019;Parziale et al., 2021;Cilia et al., 2022), but video recording of gait as well as food manipulation during feeding have also been suggested (Bhattacharjee et al., 2019;Kumar et al., 2021). ...
A crucial aspect in human-robot collaboration is the robot acceptance by human co-workers. Based on previous experiences of interaction with their fellow beings, humans are able to recognize natural movements of their companions and associate them with the concepts of trust and acceptance. Throughout this process, the judgment is influenced by several percepts, first of all the visual similarity to the companion, which triggers a process of self-identification. When the companion is a robot, the lack of these percepts challenges such a self-identification process, unavoidably lowering the level of acceptance. Hence, while, on the one hand, the robotics industry moves towards manufacturing robots that visually resemble humans, on the other hand, a question is still open on whether the acceptance of robots can be increased by virtue of the movements they exhibit, regardless of their exterior aspect. In order to contribute to answering this question, this paper presents two experimental setups for Turing tests, where an artificial agent performs human-recorded and artificial movements, and a human subject is to judge the human likeness of the movement in two different circumstances: by observing the movement replicated on a screen and by physically interacting with a robot executing the movements. The results reveal that humans are more likely to recognize human movements through interaction than observation, and that, under the interaction condition, artificial movements can be designed to resemble human ones for future robots to be more easily accepted by human co-workers.
... The analysis of movement, as the analysis of gait or handwriting, is the core of many tools used for biometric [6,7,17,18,24] and diagnostic [2][3][4]20] purposes. That is because complex movements are the result of a learning process that is individual and neurodegenerative disorders, like Parkinson's and Alzheimer's disease, affect motor skill learning, execution and retention. ...
Experimental studies led by Lashley and Raibert in the early phase of human movement science highlighted the phenomenon of motor equivalence, according to which complex movements are represented in the brain abstractly, in a way that is independent of the effector used for the execution of the movement. This abstract representation is known as motor program and it defines the temporal sequence of target points the effector has to move towards to accomplish the desired movement. We present and compare two algorithms for the extraction of motor programs from handwriting samples. One algorithm considers that lognormal velocity profiles are an invariant characteristic of reaching movements and it identifies the position of the target points by analysing the velocity profile of samples. The other algorithm seeks target points by identifying the trajectory points corresponding to maximum curvature variations because experimental studies have shown that the activity of the primary motor cortex encodes the direction of the movement. We have compared the performance of the two algorithms in terms of the number of virtual target points extracted by handwriting samples generated by 32 subjects with their dominant and non-dominant hands. The results have shown that the two algorithms show a similar performance over 55% of samples but the extraction of motor programs by analysing the curvature variations is more robust to noise and unmodeled motor variability.KeywordsMotor equivalenceMotor program extractionHandwriting representation
Human Activity Recognition (HAR), based on sensor devices and the Internet of Things (IoT), attracted many researchers since it has diversified applications in health sectors, smart environments, and entertainment. HAR has emerged as one of the important health monitoring applications and it necessitates the constant usage of smartphones, smartwatches, and wearable devices to capture patients' daily activities. To predict multiple human activities, deep learning (DL)-based methods have been successfully applied to time-series data that are generated by smartphones and wearable sensors. Although DL-based approaches were deployed in activity recognition, they still have encountered a few issues when working with time-series data. Those issues could be managed with the proposed methodology. This work proposed a couple of Hybrid Learning Algorithms (HLA) to build comprehensive classification methods for HAR using wearable sensor data. The aim of this work is to make use of the Convolution Memory Fusion Algorithm(CMFA) and Convolution Gated Fusion Algorithm(CGFA) that model learns both local features and long-term and gated-term dependencies in sequential data. Feature extraction has been enhanced with the deployment of various filter sizes. They are used to capture different local temporal dependencies, and thus the enhancement is implemented. This Amalgam Learning Model has been deployed on the WISDM dataset, and the proposed models have achieved 97.76%, 94.98% for smartwatch and smartphone of CMFA, 96.91%, 84.35% for smartwatch and smartphone of CGFA. Experimental results show that these models demonstrated greater accuracy than other existing deep neural network frameworks.
Wearable technology has advanced significantly and is now used in various entertainment and business contexts. Authentication methods could be trustworthy, transparent, and non-intrusive to guarantee that users can engage in online communications without consequences. An authentication system on a security framework starts with a process for identifying the user to ensure that the user is permitted. Establishing and verifying an individual’s appearance usually requires a lot of effort. Recent years have seen an increase in the usage of activity-based user identification systems to identify individuals. Despite this, there has not been much research into how complex hand movements can be used to determine the identity of an individual. This research used a one-dimensional residual network with squeeze-and-excitation (SE) configurations called the 1D-ResNet-SE model to investigate hand movements and user identification. According to the findings, the SE modules have enhanced the one-dimensional residual network’s identification ability. As a deep learning model, the proposed methodology is capable of effectively identifying features from the input smartwatch sensor and could be utilized as an end-to-end model to clarify the modeling process. The 1D-ResNet-SE identification model is superior to the other models. Hand movement assessment based on deep learning is an effective technique to identify smartwatch users.
This study explores an adaptive sparse representation approach for online writer identification. The main focus is on employing prior information that quantifies the degree of importance of a dictionary atom concerning a given writer. This information is proposed by a fusion of two derived components. The first component is a saliency measure obtained from the sum‐pooled sparse coefficients corresponding to the sub‐strokes of a set of enrolled writers. The second component is a similarity score, computed for each dictionary atom with regards to a given writer, that is related to the reconstruction error of the sub‐stroke based feature vectors. The proposed identification is accomplished with an ensemble of support vector machines (SVMs), wherein the input to the SVM trained for a writer is obtained by incorporating the adapted saliency values of that writer on the document descriptor obtained via average pooling of sparse codes. Experiments performed on the IAM and IBM‐UB1 online handwriting databases demonstrate the efficacy of the proposed scheme.
One of the biometric methods in authentication systems is the writer verification/identification using password handwriting. The main objective of this paper is to present a robust writer verification system by using cursive texts as well as block letter words. To evaluate the system, two datasets have been used. One of them is called Secure Password DB 150, which is composed of 150 users with 18 samples of single character words per user. Another dataset is public and called IAM online handwriting database, and it is composed of 220 users of cursive text samples. Each sample has been defined by a set of features, composed of 67 geometrical, statistical, and temporal features. In order to get more discriminative information, two feature reduction methods have been applied, Fisher Score and Info Gain Attribute Evaluation. Finally, the classification system has been implemented by hold-out cross validation and k-folds cross validation strategies for three different classifiers, K-NN, Naïve Bayes and Bayes Net classifiers. Besides, it has been applied for verification and identification approaches. The best results of 95.38% correct classification are achieved by using the k-nearest neighbor classifier for single character DB. A feature reduction by Info Gain Attribute Evaluation improves the results for Naïve Bayes Classifier to 98.34% for IAM online handwriting DB. It is concluded that the set of features and its reduction are a strong selection for the based-password handwritten writer identification in comparison with the state-of-the-art.
Biometric authentication is popular in authentication systems, and gesture as a carrier of behavior characteristics has the advantages of being difficult to imitate and containing abundant information. This research aims to use three-dimensional (3D) depth information of gesture movement to perform authentication with less user effort. We propose an approach based on depth cameras, which satisfies three requirements: Can authenticate from a single, customized gesture; achieves high accuracy without an excessive number of gestures for training; and continues learning the gesture during use of the system. To satisfy these requirements respectively: We use a sparse autoencoder to memorize the single gesture; we employ data augmentation technology to solve the problem of insufficient data; and we use incremental learning technology for allowing the system to memorize the gesture incrementally over time. An experiment has been performed on different gestures in different user situations that demonstrates the accuracy of one-class classification (OCC), and proves the effectiveness and reliability of the approach. Gesture authentication based on 3D depth cameras could be achieved with reduced user effort.
Handwritten signatures are biometric traits increasingly at the centre of debate by the scientific community. Over the last forty years, the interest in signature studies has grown steadily, having as its main reference in the application of automatic signature verification, as previously published reviews in 1989, 2000 and 2008 bear witness. Ever since, and over the last ten years, the application of handwritten signature technology has strongly evolved and much research has focused on the possibility of applying systems based on handwritten signature analysis and processing to a multitude of new fields. After several years of haphazard growth of this research area, it is time to assess its current developments for their applicability in order to draw a structured way forward. This perspective reports a systematic review of the last ten years of the literature on handwritten signatures with respect to the new scenario, focusing on the most promising domains of research and trying to elicit possible future research directions in this subject.
Despite decades of research on automated handwriting authentication, there is yet to emerge an automated handwriting authentication application that breaks into the mainstream. In this paper, we argue that the burgeoning wearables market holds the key to a practical handwriting authentication app. With potential applications in on-line education, standardized testing and mobile banking, we present Handwriting Watcher, a mechanism which leverages a wrist-worn sensor-enabled device to authenticate a user's free handwriting. Through experiments capturing a wide range of writing scenarios, we show Handwriting Watcher attains mean error rates as low as 6.56% across the population. Our work represents a promising step towards a market-ready, generalized handwriting authentication system.
The synthetic generation of static handwritten signatures based on motor equivalence theory has been recently proposed for biometric applications. Motor equivalence divides the human handwriting action into an effector dependent cognitive level and an effector independent motor level. The first level has been suggested by others as an engram, generated through a spatial grid, and the second has been emulated with kinematic filters. Our paper proposes a development of this methodology in which we generate dynamic information and provide a unified comprehensive synthesizer for both static and dynamic signature synthesis. The dynamics are calculated by lognormal sampling of the 8-connected continuous signature trajectory, which includes, as a novelty, the pen-ups. The forgery generation imitates a signature by extracting the most perceptually relevant points of the given genuine signature and interpolating them. The capacity to synthesize both static and dynamic signatures using a unique model is evaluated according to its ability to adapt to the static and dynamic signature inter- and intra-personal variability. Our highly promising results suggest the possibility of using the synthesizer in different areas beyond the generation of unlimited databases for biometric training.
The purpose of this research was to see if Kinect sensor can recognize numeric and alphabetic characters written with the hand in the air. Kinect sensor can capture motion without the sensor device being attached to the user’s body. The input screen has both modes of numerals and alphabet. The recognition rate was measured and the user wrote the numbers from zero to nine and the letters from A to Z twice. Alphabet recognition relied on Palm’s Graffiti. The input numerals and alphabet were recognized by dynamic programming matching based on interstroke information. In addition, this system can perform the numeral operation, such as +, −,
×
, and /. Most people are not used to writing in the air and are unfamiliar with Kinect sensor, and it takes some time to master them both. First, the user needs to become accustomed to using the sensor. Average recognition rates of 95.0% and 98.9%, respectively, were obtained for numerical and alphabetical characters.
We introduce a tool for quantitative evaluation of handwriting features largely adopted during forensic examination of questioned documents. The tool is based on a model of handwriting generation and execution according to which handwriting is composed of elementary movements, called strokes, whose order and timing of execution has been learned and stored in the brain. Thus, what characterizes handwriting individuality, and therefore should be inferred from the samples available, is the way the sequence of strokes are executed. The tool does not aim at reaching a conclusion on the writer's identity when comparing two documents, but provides the quantitative evaluation of a set of features that can be used by the expert to support his/her conclusion. Although the tool is meant to proceed automatically from the scanned image of the document to the quantita-tive evaluation of the features, it is equipped with an interface that allows the expert to follow the automatic procedure step-by-step and even to modify the output of any step and to modify it in case it is deemed as incorrect. The tool automatically produces a customizable report to illustrate the procedure, the features computation and to show the computed features values in both numerical and graphical form.
Recently, research in handwritten signature verification has been considered with renewed interest. In fact, in the age of e-society, handwritten signature still represents an extraordinary means for personal verification and the possibility of using automatic signature verification in a range of applications is becoming a reality. This paper focuses on some of the most remarkable aspects the field and highlights some recent research directions. A list of selected publications is also provided for interested researchers.
Personal identity verification is of great importance in today's world which is full of frauds and forgeries. A signature being a very good biometric has been since a long time for personal identity verification. Signature verification is the process used to recognize an individual's handwritten signature to prevent fraud. In this project, the dynamic features of the signature are considered so as to prevent forgeries. The pressure at the pen-tip together with the x and y coordinates of the signature are measured and features extracted from these are used to verify the signature. A signature verification system using Error Back Propagation Training Algorithm is designed using Neural Network Toolbox of MATLAB to verify the signatures. The attractive features of this system are its low cost, low intrusion, good performance and use of an acceptable and natural biometric (the signature). A two-step method is proposed, which involves identification of the signature in the first step followed by individual verification. Both the steps are carried out by Neural Networks trained using Error Back-Propagation Training Algorithm.
Direct use of the hand as an input device is an attractive method for providing natural human–computer interaction (HCI). Currently, the only technology that satisfies the advanced requirements of hand-based input for HCI is glove-based sensing. This technology, however, has several drawbacks including that it hinders the ease and naturalness with which the user can interact with the computer-controlled environment, and it requires long calibration and setup procedures. Computer vision (CV) has the potential to provide more natural, non-contact solutions. As a result, there have been considerable research efforts to use the hand as an input device for HCI. In particular, two types of research directions have emerged. One is based on gesture classification and aims to extract high-level abstract information corresponding to motion patterns or postures of the hand. The second is based on pose estimation systems and aims to capture the real 3D motion of the hand. This paper presents a literature review on the latter research direction, which is a very challenging problem in the context of HCI.
Storing and using specific instances improves the performance of several supervised learning algorithms. These include algorithms that learn decision trees, classification rules, and distributed networks. However, no investigation has analyzed algorithms that use only specific instances to solve incremental learning tasks. In this paper, we describe a framework and methodology, called instance-based learning, that generates classification predictions using only specific instances. Instance-based learning algorithms do not maintain a set of abstractions derived from specific instances. This approach extends the nearest neighbor algorithm, which has large storage requirements. We describe how storage requirements can be significantly reduced with, at most, minor sacrifices in learning rate and classification accuracy. While the storage-reducing algorithm performs well on several real-world databases, its performance degrades rapidly with the level of attribute noise in training instances. Therefore, we extended it with a significance test to distinguish noisy instances. This extended algorithm's performance degrades gracefully with increasing noise levels and compares favorably with a noise-tolerant decision tree algorithm.
Scikit-learn is a Python module integrating a wide range of state-of-the-art
machine learning algorithms for medium-scale supervised and unsupervised
problems. This package focuses on bringing machine learning to non-specialists
using a general-purpose high-level language. Emphasis is put on ease of use,
performance, documentation, and API consistency. It has minimal dependencies
and is distributed under the simplified BSD license, encouraging its use in
both academic and commercial settings. Source code, binaries, and documentation
can be downloaded from http://scikit-learn.sourceforge.net.
In the last decades, early disease identification through non-invasive and automatic methodologies has gathered increasing interest from the scientific community. Among others, Parkinson's disease (PD) has received special attention in that it is a severe and progressive neuro-degenerative disease. As a consequence, early diagnosis would provide more effective and prompt care strategies, that cloud successfully influence patients’ life expectancy. However, the most performing systems implement the so called black-box approach, which do not provide explicit rules to reach a decision. This lack of interpretability, has hampered the acceptance of those systems by clinicians and their deployment on the field. In this context, we perform a thorough comparison of different machine learning (ML) techniques, whose classification results are characterized by different levels of interpretability. Such techniques were applied for automatically identify PD patients through the analysis of handwriting and drawing samples. Results analysis shows that white-box approaches, such as Cartesian Genetic Programming and Decision Tree, allow to reach a twofold goal: support the diagnosis of PD and obtain explicit classification models, on which only a subset of features (related to specific tasks) were identified and exploited for classification. Obtained classification models provide important insights for the design of non-invasive, inexpensive and easy to administer diagnostic protocols. Comparison of different ML approaches (in terms of both accuracy and interpretability) has been performed on the features extracted from the handwriting and drawing samples included in the publicly available PaHaW and NewHandPD datasets. The experimental findings show that the Cartesian Genetic Programming outperforms the white-box methods in accuracy and the black-box ones in interpretability.
As a new human-computer interaction way, in-air handwriting allows users to perform gesture-based writing in the midair. However, most existing in-air handwriting systems mainly focus on recognizing either isolated characters/words or only a small number of texts, making those systems far from practical applications. Instead, here we present a 3D in-air handwritten Chinese text recognition (IAHCTR) system for the first time, and construct the first public large-scale IAHCT dataset. Moreover, a novel architecture, named the temporal convolutional recurrent network (TCRN), is proposed for online HCTR. Specifically, the TCRN first applies the 1-dimensional convolution to extract local contextual features from low-level trajectories, and then it utilizes the recurrent network to capture long-term dependencies of high-level outputs. Compared with the state-of-the-art architecture, the TCRN not only avoids the domain-specific knowledge for feature image extraction, but also attains higher training efficiency with a more compact model. Empirically, this TCRN also outperforms the single recurrent network with faster prediction and higher accuracy. Experiments on CASIA-OLHWDB2 & ICDAR-2013 demonstrate that the TCRN yields the best result in comparison to the state-of-the-art methods for online HCTR.
With the ubiquity of handwriting in everyday tasks, it is surprising that existing avenues for handwriting authentication remain largely out of reach for the average individual or organization. Current solutions often rely on expensive or specialized equipment, and most existing research focuses on signatures rather than freeform handwriting. This limits the applicability of such technology to a narrow range of scenarios. In this paper we argue that wearable devices might make handwriting authentication scalable and affordable. We design and evaluate two wearables-driven freeform handwriting authentication systems, one centered on a deep neural network and the other using human-engineered features. Our authentication systems are thoroughly tested across three writing experiments (involving 53 participants) that were carefully mapped to typical writing scenarios. We show the best performing configuration to attain an Equal Error Rate of 5.51%, suggesting the potential of this modality for use in a multi-modal authentication system. To evaluate how our authentication systems perform against attacks by determined attackers, we developed and evaluated two impostor attacks that correspond to highly likely attack vectors. We then show that certain authentication system configurations are resistant to the attack. This paper represents an important step towards consumer ready wearables-driven freeform handwriting authentication.
Building upon findings in computational model of handwriting learning and execution, we introduce the concept of stability to explain the difference between the actual movements performed during multiple execution of the subject’s signature, and conjecture that the most stable parts of the signature should play a paramount role in evaluating the similarity between a questioned signature and the reference ones during signature verification. We then introduce the Stability Modulated Dynamic Time Warping algorithm for incorporating the stability regions, i.e. the most similar parts between two signatures, into the distance measure between a pair of signatures computed by the Dynamic Time Warping for signature verification. Experiments were conducted on two datasets largely adopted for performance evaluation. Experimental results show that the proposed algorithm improves the performance of the baseline system and compares favourably with other top performing signature verification systems.
Biometric recognition, or simply biometrics, is a rapidly evolving field with applications ranging from accessing one's computer, to gaining entry into a country. Biometric systems rely on the use of physical or behavioral traits, such as fingerprints, face, voice and hand geometry, to establish the identity of an individual. The deployment of large-scale biometric systems in both commercial (e.g., grocery stores, amusement parks, airports) and government (e.g., US-VISIT) applications, increases the public's awareness of this technology. This rapid growth also highlights the challenges associated with designing and deploying biometric systems. Indeed, the problem of biometric recognition is a grand challenge in its own right. The past five years have seen a significant growth in biometric research resulting in the development of innovative sensors, robust and efficient algorithms for feature extraction and matching, enhanced test methodologies and novel applications. These advances have resulted in robust, accurate, secure and cost effective biometric systems.
The Handbook of Biometrics -- an edited volume by prominent invited researchers in biometrics -- describes the fundamentals as well as the latest advancements in the burgeoning field of biometrics. It is designed for professionals, practitioners and researchers in biometrics, pattern recognition and computer security. The Handbook of Biometrics can be used as a primary textbook for an undergraduate biometrics class. This book is also suitable as a secondary textbook or reference for advanced-level students in computer science.
Writer identification is an important topic for pattern recognition and artificial intelligence. Traditional methods rely heavily on sophisticated hand-crafted features to represent the characteristics of different writers. In this paper, we propose an end-to-end framework for online text-independent writer identification by using a recurrent neural network (RNN). Specifically, the handwriting data of a particular writer are represented by a set of random hybrid strokes (RHSs). Each RHS is a randomly sampled short sequence representing pen tip movements ( xy -coordinates) and pen-down or pen-up states. RHS is independent of the content and language involved in handwriting; therefore, writer identification at the RHS level is more general and convenient than the character level or the word level, which also requires character/word segmentation. The RNN model with bidirectional long short-term memory is used to encode each RHS into a fixed-length vector for final classification. All the RHSs of a writer are classified independently, and then, the posterior probabilities are averaged to make the final decision. The proposed framework is end-to-end and does not require any domain knowledge for handwriting data analysis. Experiments on both English (133 writers) and Chinese (186 writers) databases verify the advantages of our method compared with other state-of-the-art approaches.
In recent years, biometrics authentication becomes popular. No key is required in biometrics authentication while password must be remembered in password authentication. Moreover, living parts for biometrics authentication cannot be stolen with usual method. Therefore, reading devices for biometrics authentication on IT devices also gradually become popular. Especially, fingerprint readers are the most popular devices on IT devices since they are small and they can be attached with a few costs. However, there is a critical problem in biometrics authentication when information for biometrics authentication is once stolen. Especially, it is known that fingerprints can be copied with remaining prints on the surface of smart phones. Information for biometrics authentication cannot be changed. That is, the information never be used again to protect against the fraud use. From the above, the best way for authentication is changeable biometrics authentication. Information which is related with personal physical characteristics is required but it must be changeable. One of the examples is a sign with handwriting. In this method, personal characteristics of tracks, speed and pressure are used for personal identification and they are information in biometrics. Those characteristics cannot be change when the same sign is written by the same person, but the sign can be changed when the information for authentication is stolen. Usually, pen tablets or touch panels are used for signs in biometrics authentication. However, stylus pens for tablets bother managers in public use. Fingers for signs on touch panels are also exposed to the menace of smudge attacks. Therefore, in this paper, we use Leap Motion device for signs in biometrics authentication. In our authentication system, signs in the air can be used for personal identification. Personal characteristics of tracks, speed and inclination of fingers are captured and used for the identification.
The objective of this research is to develop a method to verify who the writer is from his/her figure drawn in three-dimensional space and to reduce the false rejection error rate and the false acceptance error rate. The previous research on writer verification mainly used pen tablets. However, this research used a Kinect Sensor since we expected that the Kinect Sensor could give the useful information of individual features which a pen tablet could not. The verification method calculates the distance between the input figure and the reference figure obtained from pre-processing of the sample data. The distance is compared with the threshold to determine success or failure and the equal error rate is calculated from the false rejection error rate and false acceptance error rate. Twenty-three examinees drew cubes, cylinders and circular pyramids, which were collected as sample data and test data using the Kinect Sensor. With experimental results, we show that writer verification based on three-dimensional information is very effective.
The growing popularity of wearable devices is leading to new ways to interact with the environment, with other smart devices, and with other people. Wearables equipped with an array of sensors are able to capture the owner's physiological and behavioural traits, thus are well suited for biometric authentication to control other devices or access digital services. However, wearable biometrics have substantial differences from traditional biometrics for computer systems, such as fingerprints, eye features, or voice. In this article, we discuss these differences and analyse how researchers are approaching the wearable biometrics field. We review and provide a categorization of wearable sensors useful for capturing biometric signals. We analyse the computational cost of the different signal processing techniques, an important practical factor in constrained devices such as wearables. Finally, we review and classify the most recent proposals in the field of wearable biometrics in terms of the structure of the biometric system proposed, their experimental setup, and their results. We also present a critique of experimental issues such as evaluation and feasibility aspects, and offer some final thoughts on research directions that need attention in future work.
The authentication mechanism being equipped in most of the smartphones, by detecting a 4-digit password or a simple pattern, are easy to be hacked and impersonated. In this paper, a 3-D hand gesture signature (HGS) based biometric authentication system is designed and implemented by taking advantage of the on-phone accelerometer to capture the 3-D acceleration information when user makes a gesture to gain access to the phone. The captured data will be processed through a sequence of signal processing such as data smooth, gesture spotting, sequence alignment, and interpolation, and then a match rule will be used to compare the processed data and the genuine user's registered pattern to determine whether granting the access to the phone to the user. And an automatic template updating strategy based on cluster analysis is proposed to improve the stability of the system. The 3-D HGS authentication system has been implemented on real smartphones, and the results tested for a total of 76520 times by 19 users show very low false acceptance (0.27%) and false rejection rates (4.65%). Furthermore, comparison tests have been carried out among the 3-D HGS and two similar authentication systems by exporting the real gesture samples from the phones to a desktop PC, the simulation results reveal the 3-D HGS system has the best authentication accuracy.
Owing to the rapid growth of touchscreen mobile terminals and pen-based
interfaces, handwriting-based writer identification systems are attracting
increasing attention for personal authentication, digital forensics, and other
applications. However, most studies on writer identification have not been
satisfying because of the insufficiency of data and difficulty of designing
good features under various conditions of handwritings. Hence, we introduce an
end-to-end system, namely DeepWriterID, employed a deep convolutional neural
network (CNN) to address these problems. A key feature of DeepWriterID is a new
method we are proposing, called DropSegment. It designs to achieve data
augmentation and improve the generalized applicability of CNN. For sufficient
feature representation, we further introduce path signature feature maps to
improve performance. Experiments were conducted on the NLPR handwriting
database. Even though we only use pen-position information in the pen-down
state of the given handwriting samples, we achieved new state-of-the-art
identification rates of 95.72% for Chinese text and 98.51% for English text.
The support-vector network is a new learning machine for two-group classification problems. The machine conceptually implements the following idea: input vectors are non-linearly mapped to a very high-dimension feature space. In this feature space a linear decision surface is constructed. Special properties of the decision surface ensures high generalization ability of the learning machine. The idea behind the support-vector network was previously implemented for the restricted case where the training data can be separated without errors. We here extend this result to non-separable training data. High generalization ability of support-vector networks utilizing polynomial input transformations is demonstrated. We also compare the performance of the support-vector network to various classical learning algorithms that all took part in a benchmark study of Optical Character Recognition.
We discuss the dynamics of signatures in the light of recent findings in motor learning, according to which a
signature is a highly automated motor task and, as such, it is stored in the brain as both a trajectory plan and a motor plan. We then conjecture that such a stored representation does not necessarily include the entire signature, but can be limited to only parts of it, those that have been learned better and therefore are executed more automatically than others. Because these regions are executed more automatically than others, they are less prone to significant variations depending on the actual writing conditions, and therefore should represent better than other regions the distinctive features of signatures. To support
our conjecture, we report and discuss the results of experiments
conducted by using an algorithm for finding those regions in the signature ink and eventually using them for automatic signature verification.
Nonparametric regression is a set of techniques for estimating a regression curve without making strong assumptions about the shape of the true regression function. These techniques are therefore useful for building and checking parametric models, as well as for data description. Kernel and nearest-neighbor regression estimators are local versions of univariate location estimators, and so they can readily be introduced to beginning students and consulting clients who are familiar with such summaries as the sample mean and median.
Methods of recording and processing handwriting movements by means of a computer-controlled digitizer are discussed. It is concluded that the presence of measurement ‘noise’ in the sampled movements makes it necessary to choose high sampling frequencies in combination with low-pass digital filters, especially if time derivatives have to be estimated. However, increasing the sampling frequency beyond some critical value does not improve the signal-to-quantization-noise ratio unless the raw samples are preprocessed by summing groups of samples. In order to correct for occasional nonsimultaneous sampling of the x- and y-coordinates a second type of preprocessing is required (linear interpolation). Subsequently, it is shown that low-pass filtering and differentiation can be carried out in the frequency domain, using FFT, if suitable extrapolation time functions and filter characteristics are chosen. Finally, various automatic procedures for the division of movement patterns into meaningful segments and a procedure for estimating the accuracy of the digitizer are proposed.
This paper presents PAC-learning analyses for instance-based learning algorithms for both symbolic and numeric-prediction tasks. The algorithms analyzed employ a variant of the k-nearest neighbor pattern classifier. The main results of these analyses are that the IB1 instance-based learning algorithm can learn, using a polynomial number of instances, a wide range of symbolic concepts and numeric functions. In. addition, we show that a bound on the degree of difficulty of predicting symbolic values may be obtained by considering the size of the boundary of the target concept, and a bound on the degree of difficulty in predicting numeric values may be obtained by considering the maximum absolute value of the slope between instances in the instance space. Moreover, the number of training instances required by IB1 is polynomial in these parameters. The implications of these results for the practical application of instance-based learning algorithms are discussed.
We report a series of user studies that evaluate the feasibility and usability of light-weight user authentication with a single tri-axis accelerometer. We base our investigation on uWave, a state-of- the-art recognition system for user-created free-space manipula- tion, or gestures. Our user studies address two types of user au- thentication: non-critical authentication (or identification) for a user to retrieve privacy-insensitive data; and critical authentica- tion for protecting privacy-sensitive data. For non-critical authen- tication, our evaluation shows that uWave achieves high recogni- tion accuracy (98%) and its usability is comparable with text ID- based authentication. Our results also highlight the importance of constraints for users to select their gestures. For critical authenti- cation, the evaluation shows uWave achieves state-of-the-art resi- lience to attacks with 3% false positives and 3% false negatives, or 3% equal error rate. We also show that the equal error rate increases to 10% if the attackers see the users performing their gestures. This shows the limitation of gesture-based authentication and highlights the need for visual concealment.
As a result of advances in mobile technology, new services which benefit from the ubiquity of these devices are appearing. Some of these services require the identification of the subject since they may access private user information. In this paper, we propose to identify each user by drawing his/her handwritten signature in the air (in-air signature). In order to assess the feasibility of an in-air signature as a biometric feature, we have analysed the performance of several well-known pattern recognition techniques—Hidden Markov Models, Bayes classifiers and dynamic time warping—to cope with this problem. Each technique has been tested in the identification of the signatures of 96 individuals. Furthermore, the robustness of each method against spoofing attacks has also been analysed using six impostors who attempted to emulate every signature. The best results in both experiments have been reached by using a technique based on dynamic time warping which carries out the recognition by calculating distances to an average template extracted from several training instances. Finally, a permanence analysis has been carried out in order to assess the stability of in-air signature over time.
Thesupport-vector network is a new learning machine for two-group classification problems. The machine conceptually implements the following idea: input vectors are non-linearly mapped to a very high-dimension feature space. In this feature space a linear decision surface is constructed. Special properties of the decision surface ensures high generalization ability of the learning machine. The idea behind the support-vector network was previously implemented for the restricted case where the training data can be separated without errors. We here extend this result to non-separable training data.
High generalization ability of support-vector networks utilizing polynomial input transformations is demonstrated. We also compare the performance of the support-vector network to various classical learning algorithms that all took part in a benchmark study of Optical Character Recognition.
This paper deals with non-parametric two-sample tests on dispersions. Two samples, X- and Y-samples of m and n independent observations from populations with continuous cumulative distribution functions F(u) and G(u) respectively, are considered. It is required for the basic test that the difference in locations (medians) of the two populations be known and, when this is so, the two samples may be adjusted to have equal locations. Taking these location parameters to be zero without loss of generality, we test the hypothesis that against alternatives of the form . The two samples are ordered in a single joint array and ranks are assigned from each end of the joint array towards the middle. The statistic used is W, the sum of ranks for the X-sample. The distribution of W is studied and tables of significant values of W are provided for and both upper- and lower-tail significance levels .005, .01, .025 and .05. The first four moments of W are developed and a normal approximation to the null distribution of W is devised. Large-sample properties of the W-test are considered. A proof of limiting normality is based on a theorem of Chernoff and Savage. Consistency of the W-test is indicated and its relative efficiency in comparison with the variance-ratio F-test is obtained as when F(u) is the normal distribution function. Other non-parametric tests of dispersions are reviewed. The W-test is less efficient asymptotically than some of these other tests but is easier to apply, particularly with the tables provided. A modified test is suggested for the case where the difference in population locations is not known. This involves replacing the two original samples by two corresponding samples of deviations from sample medians. The procedure of the W-test is applied to the two samples of deviations. The properties of the modified test have not been investigated except for a sampling study of rather limited scope. That study indicates that the moments of W for the modified test are not greatly different from those under the basic procedure.
A model is presented that deals with problems of motor control, motor learning, and sensorimotor integration. The equations of motion for a limb are parameterized and used in conjunction with a quantized, multi-dimensional memory organized by state variables. Descriptions of desired trajectories are translated into motor commands which will replicate the specified motions. The initial specification of a movement is free of information regarding the mechanics of the effector system. Learning occurs without the use of error correction when practice data are collected and analyzed.
Elderly and young control subjects performed back-and-forth handwriting movements in various orientations, therefore varying the coordination demands. Elderly subjects showed higher normalized jerk and straightness scores than the young subjects. However, jerk scores were independent of the coordination demands in either group. In contrast, the straightness scores were highly dependent on stroke orientation for the elderly, but they remained constant across orientations for the young controls. Moreover, group differences in stroke size and stroke duration were not significant, and orientation effects were unrelated. It is suggested that the orientation-dependent straightness scores in the elderly may result from unequal timing or improper scaling of muscle forces. These data suggest that aging deteriorates the spatial coordination of finger and wrist movements, but not accelerative force control.
Handwriting is a classic example of how the details of movement can be scale and plane invariant: letter forms reflecting personal style are unchanged, whether one is writing on a piece of paper, on a blackboard or in the sand using the foot. Recent research points to a role for the parietal cortex in such motor equivalence.
Motivated by several rulings in United States courts concerning expert testimony in general, and handwriting testimony in particular, we undertook a study to objectively validate the hypothesis that handwriting is individual. Handwriting samples of 1,500 individuals, representative of the U.S. population with respect to gender, age, ethnic groups, etc., were obtained. Analyzing differences in handwriting was done by using computer algorithms for extracting features from scanned images of handwriting. Attributes characteristic of the handwriting were obtained, e.g., line separation, slant, character shapes, etc. These attributes, which are a subset of attributes used by forensic document examiners (FDEs), were used to quantitatively establish individuality by using machine learning approaches. Using global attributes of handwriting and very few characters in the writing, the ability to determine the writer with a high degree of confidence was established. The work is a step towards providing scientific support for admitting handwriting evidence in court. The mathematical approach and the resulting software also have the promise of aiding the FDE.
Decision trees are attractive classifiers due to their high
execution speed. But trees derived with traditional methods often cannot
be grown to arbitrary complexity for possible loss of generalization
accuracy on unseen data. The limitation on complexity usually means
suboptimal accuracy on training data. Following the principles of
stochastic modeling, we propose a method to construct tree-based
classifiers whose capacity can be arbitrarily expanded for increases in
accuracy for both training and unseen data. The essence of the method is
to build multiple trees in randomly selected subspaces of the feature
space. Trees in, different subspaces generalize their classification in
complementary ways, and their combined classification can be
monotonically improved. The validity of the method is demonstrated
through experiments on the recognition of handwritten digits
Gesture recognition pertains to recognizing meaningful expressions of motion by a human, involving the hands, arms, face, head, and/or body. It is of utmost importance in designing an intelligent and efficient human-computer interface. The applications of gesture recognition are manifold, ranging from sign language through medical rehabilitation to virtual reality. In this paper, we provide a survey on gesture recognition with particular emphasis on hand gestures and facial expressions. Applications involving hidden Markov models, particle filtering and condensation, finite-state machines, optical flow, skin color, and connectionist models are discussed in detail. Existing challenges and future research possibilities are also highlighted
The analysis of handwritten documents from the viewpoint of determining their writership has great bearing on the criminal justice system. In many cases, only a limited amount of handwriting is available and sometimes it consists of only numerals. Using a large number of handwritten numeral images extracted from about 3000 samples written by 1000 writers, a study of the individuality of numerals for identification/verification purposes was conducted. The individuality of numerals was studied using cluster analysis. Numerals discriminability was measured for writer verification. The study shows that some numerals present a higher discriminatory power and that their performances for the verification/identification tasks are very different.
- H L Teulings
Teulings, H.L.: MovAlyzeR. Version 6.1. Neuroscript LTD (2021). https://www.
neuroscript.net