Biometrics on mobile devices has attracted a lot of attention in recent years as it is considered a user-friendly authentication method. This interest has also been motivated by the success of Deep Learning (DL). Architectures based on Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) have established convenience for the task, improving the performance and robustness in comparison to traditional machine learning techniques. However, some aspects must still be revisited and improved. To the best of our knowledge, this is the first article that explores and proposes a novel gait biometric recognition systems based on Transformers, which currently obtain state-of-the-art performance in many applications. Several state-of-the-art architectures (Vanilla, Informer, Autoformer, Block-Recurrent Transformer, and THAT) are considered in the experimental framework. In addition, new Transformer configurations are proposed to further increase the performance. Experiments are carried out using the two popular public databases: whuGAIT and OU-ISIR. The results achieved prove the high ability of the proposed Transformer, outperforming state-of-the-art CNN and RNN architectures.

Numerous studies in the literature have already shown the potential of biometrics on mobile devices for authentication purposes. However, it has been shown that, the learning processes associated to biometric systems might expose sensitive personal information about the subjects. This study proposes GaitPrivacyON, a novel mobile gait biometrics verification approach that provides accurate authentication results while preserving the sensitive information of the subject. It comprises two modules: i) two convolutional Autoencoders with shared weights that transform attributes of the biometric raw data, such as the gender or the activity being performed, into a new privacy-preserving representation; and ii) a mobile gait verification system based on the combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) with a Siamese architecture. The main advantage of GaitPrivacyON is that the first module (convolutional Autoencoders) is trained in an unsupervised way, without specifying the sensitive attributes of the subject to protect. Two experimental studies have been examinated: i) MotionSense and MobiAct databases; and ii) OU-ISIR database. The experimental results achieved suggest the potential of GaitPrivacyON to significantly improve the privacy of the subject while keeping user authentication results higher than 96.6% Area Under the Curve (AUC). To the best of our knowledge, this is the first mobile gait verification approach that considers privacy-preserving methods trained in an unsupervised way.

Abstract Background User interaction with a mobile device predominantly consists of touch motions, otherwise known as swipe gestures, which are used as a behavioural biometric modality to verify the identity of a user. Literature reveals promising verification accuracy rates for swipe gesture authentication. Most of the existing studies have considered constrained environment in their experimental set-up. However, real-life usage of a mobile device consists of several unconstrained scenarios as well. Thus, our work aims to evaluate the stability of swipe gesture authentication across various usage scenarios of a mobile device. Methods The evaluations were performed using state-of-the-art touch-based classification algorithms—support vector machine (SVM), k-nearest neighbour (kNN) and naive Bayes—to evaluate the robustness of swipe gestures across device usage scenarios. To simulate real-life behaviour, multiple usage scenarios covering stationary and dynamic modes are considered for the analysis. Additionally, we focused on analysing the stability of verification accuracy for time-separated swipes by performing intra-session (acquired on the same day) and inter-session (swipes acquired a week later) comparisons. Finally, we assessed the consistency of individual features for horizontal and vertical swipes using a statistical method. Results Performance evaluation results indicate impact of body movement and environment (indoor and outdoor) on the user verification accuracy. The results reveal that for a static user scenario, the average equal error rate is 1%, and it rises significantly for the scenarios involving any body movement—caused either by user or the environment. The performance evaluation for time-separated swipes showed better verification accuracy rate for swipes acquired on the same day compared to swipes separated by a week. Finally, assessment on feature consistency reveal a set of consistent features such as maximum slope, standard deviation and mean velocity of second half of stroke for both horizontal and vertical swipes. Conclusions The performance evaluation of swipe-based authentication shows variation in verification accuracy across different device usage scenarios. The obtained results challenge the adoption of swipe-based authentication on mobile devices. We have suggested ways to further achieve stability through specific template selection strategies. Additionally, our evaluation has established that at least 6 swipes are needed in enrolment to achieve acceptable accuracy. Also, our results conclude that features such as maximum slope and standard deviation are the most consistent features across scenarios.

Spoofing attacks on biometric systems are one of the major impediments to their use for secure unattended applications. This paper explores features for face liveness detection based on tracking the gaze of the user. In the proposed approach, a visual stimulus is placed on the display screen, at apparently random locations, which the user is required to follow while their gaze is measured. This visual stimulus appears in such a way that it repeatedly directs the gaze of the user to specific positions on the screen. Features extracted from sets of collinear and colocated points are used to estimate the liveness of the user. Data are collected from genuine users tracking the stimulus with natural head/eye movements and impostors holding a photograph, looking through a 2D mask or replaying the video of a genuine user. The choice of stimulus and features are based on the assumption that natural head/eye coordination for directing gaze results in a greater accuracy and thus can be used to effectively differentiate between genuine and spoofing attempts. Tests are performed to assess the effectiveness of the system with these features in isolation as well as in combination with each other using score fusion techniques. The results from the experiments indicate the effectiveness of the proposed gaze-based features in detecting such presentation attacks.

This work explores the sensitivity of electroencephalographic-based biometric recognition to the type of tasks required by subjects to perform while their brain activity is being recorded. A novel wavelet-based feature is used to extract identity information from a database of 109 subjects who performed four different motor movement/imagery tasks while their data were recorded. Training and test of the system was performed using a number of experimental protocols to establish if training with one type of task and tested with another would significantly affect the recognition performance. Also, experiments were conducted to evaluate the performance when a mixture of data from different tasks was used for training. The results suggest that performance is not significantly affected when there is a mismatch between training and test tasks. Furthermore, as the amount of data used for training is increased using a combination of data from several tasks, the performance can be improved. These results indicate that a more flexible approach may be incorporated in data collection for EEG-based biometric systems which could facilitate their deployment and improved performance.

Education plays an important role in helping developing nations reduce poverty and improving quality of life. Ubiquitous and mobile technologies could greatly enhance education in such regions by providing augmented access to learning. This paper presents a three-year iterative study where a ubiquitous sensor based learning platform was designed, developed and tested to support science learning among primary school students in underprivileged Northern Thailand. The platform is built upon the school's existing mobile devices and was expanded to include sensor-based technology. Throughout the iterative design process, observations, interviews and group discussions were carried out with stakeholders. This lead to key reflections and design concepts such as the value of injecting anthropomorphic qualities into the learning device and providing personally and culturally relevant learning experiences through technology. Overall, the results outlined in this paper help contribute to knowledge regarding the design, development and implementation of ubiquitous sensor-based technology to support learning.

Research on using electroencephalographic signals for biometric recognition has made considerable progress and is attracting growing attention in recent years. However, the usability aspects of the proposed biometric systems in the literatures have not received significant attention. In this paper, we present a comprehensive survey to examine the development and current status of various aspects of electroencephalography (EEG)-based biometric recognition. We first compare the characteristics of different stimuli that have been used for evoking biometric information bearing EEG signals. This is followed by a survey of the reported features and classifiers employed for EEG biometric recognition. To highlight the usability challenges of using EEG for biometric recognition in real-life scenarios, we propose a novel usability assessment framework which combines a number of user-related factors to evaluate the reported systems. The evaluation scores indicate a pattern of increasing usability, particularly in recent years, of EEG-based biometric systems as efforts have been made to improve the performance of such systems in realistic application scenarios. We also propose how this framework may be extended to take into account Aging effects as more performance data becomes available.

In this paper we present a novel approach for biometric identification using electroencephalogram (EEG) signals based on features extracted with the Hilbert-Huang Transform (HHT). The instantaneous amplitude and the instantaneous frequency were computed after the HHT, and these were then used to generate the features for classification. The proposed system was evaluated using two publicly available databases in scenarios where only a single electrode is used to provide biometric information. One database (with 122 subjects) has the users viewing a series of pictures while the other one (with 109 subjects) has the users performing motor/imagery tasks. Average identification accuracies of 96% and 99% were reached for these two databases respectively using only a single electrode. These compare favourably with previously published results employing a variety of other features and classification approaches.

Purpose Biometric authentication, which requires storage of biometric templates and/or encryption keys, raises a matter of serious concern, since the compromise of templates or keys necessarily compromises the information secured by those keys. To address such concerns, efforts based on dynamic key generation directly from the biometrics have recently emerged. However, previous methods often have quite unacceptable authentication performance and/or small key spaces and therefore are not viable in practice. The purpose of this paper is to propose a novel method which can reliably generate long keys while requires storage of neither biometric templates nor encryption keys. Design/methodology/approach This proposition is achieved by devising the use of fingerprint orientation fields for key generation. Additionally, the keys produced are not permanently linked to the orientation fields, hence, allowing them to be replaced in the event of key compromise. Findings The evaluation demonstrates that the proposed method for dynamic key generation can offer both good reliability and security in practice, and outperforms other related methods. Originality/value In this paper, the authors propose a novel method which can reliably generate long keys while requires storage of neither biometric templates nor encryption keys. This is achieved by devising the use of fingerprint orientation fields for key generation. Additionally, the keys produced are not permanently linked to the orientation fields, hence, allowing them to be replaced in the event of key compromise.

A new multimodal biometric database designed and acquired within the framework of the European BioSecure Network of Excellence is presented. It is comprised of more than 600 individuals acquired simultaneously in three scenarios: 1) over the Internet, 2) in an office environment with desktop PC, and 3) in indoor/outdoor environments with mobile portable hardware. The three scenarios include a common part of audio/video data. Also, signature and fingerprint data have been acquired both with desktop PC and mobile portable hardware. Additionally, hand and iris data were acquired in the second scenario using desktop PC. Acquisition has been conducted by 11 European institutions. Additional features of the BioSecure Multimodal Database (BMDB) are: two acquisition sessions, several sensors in certain modalities, balanced gender and age distributions, multimodal realistic scenarios with simple and quick tasks per modality, cross-European diversity, availability of demographic data, and compatibility with other multimodal databases. The novel acquisition conditions of the BMDB allow us to perform new challenging research and evaluation of either monomodal or multimodal biometric systems, as in the recent BioSecure Multimodal Evaluation campaign. A description of this campaign including baseline results of individual modalities from the new database is also given. The database is expected to be available for research purposes through the BioSecure Association during 2008.

Among numerous pattern recognition methods the neural network approach has been the subject of much research due to its ability to learn from a given collection of representative examples. This paper is concerned with the design of a Weightless Neural Network, which decomposes a given pattern into several sets of n points, termed n-tuples. Considerable research has shown that by optimising the input connection mapping of such n-tuple networks classification performance can be improved significantly. This paper investigates the hybridisation of Genetic Algorithm (GA) and Particle Swarm Optimisation (PSO) techniques in search of better connection maps to the N-tuples. Experiments were conducted to evaluate the proposed method by applying the trained classifier to recognise hand-printed digits from a widely used database compiled by U.S. National Institute of Standards and Technology (NIST).

In this paper, we develop a fingerprint matching method which operates by first introducing an integrated measure, which combines two different matching criteria based on heterogeneous features. We then devise a genetically guided algorithm to optimise the integrated measure for simultaneous fingerprint alignment and verification. The proposed method is evaluated through experiments conducted on two public domain collections of fingerprint images and compared with related work, with very encouraging results.

This paper presents a face verification framework for fusing matching scores that measure similarities of local facial features. The framework is aimed to handle an open set verification scenario when users who try to enroll can be unknown to the system at the training phase. The kernel discriminant analysis is adopted within the framework to explore the discriminatory information of local matching scores in a high-dimensional non-linear space. A large sample size problem is raised for system training and an effective strategy is provided for tackling this problem. We demonstrate the framework by fusing the scores calculated using local binary pattern features. The experimental results show that our method improves the verification performance significantly when compared to a number of competitive techniques.

Among numerous pattern recognition methods the neural network approach has been the subject of much research due to its ability to learn from a given collection of representative examples. This paper concerns with the optimization of a weightless neural network, which decomposes a given pattern into several sets of n points, termed n-tuples. A population-based stochastic optimization technique, known as Particle Swarm Optimization (PSO), has been used to select an optimal set of connectivity patterns to improve the recognition performance of such .n-tuple. classifiers. The original PSO was refined by combining it with a bio-inspired technique called the Self-Organized Criticality (SOC) to add diversity in the population for finding better solutions. The hybrid algorithms were adapted for the n-tuple system and the performance was measured in selecting better connectivity patterns. The aim was to improve the discriminating power of the classifier in recognizing handwritten characters by exploiting the criticality dispersion in the swarm population. This paper presents the implementation of the hybrid model in greater detail with the effect of criticality dispersion in finding better solutions.

Biometric authentication is increasingly gaining popularity in a wide range of applications. However, the storage of the biometric templates and/or encryption keys that are necessary for such applications is a matter of serious concern, as the compromise of templates or keys necessarily compromises the information secured by those keys. In this paper, we propose a novel method, which requires storage of neither biometric templates nor encryption keys, by directly generating the keys from statistical features of biometric data. An outline of the process is as follows: given biometric samples, a set of statistical features is first extracted from each sample. On each feature subset or single feature, we model the intra and interuser variation by clustering the data into natural clusters using a fuzzy genetic clustering algorithm. Based on the modelling results, we subsequently quantify the consistency of each feature subset or single feature for each user. By selecting the most consistent feature subsets and/or single features for each user individually, we generate the key reliably without compromising its relative security. The proposed method is evaluated on handwritten signature data and compared with related methods, and the results are very promising.

Minutiae point pattern matching is the most common approach for fingerprint verification. Although many minutiae point pattern matching algorithms have been proposed, reliable automatic fingerprint verification remains as a challenging problem, both with respect to recovering the optimal alignment and the construction of an adequate matching function. In this paper, we develop a memetic fingerprint matching algorithm (MFMA) which aims to identify the optimal or near optimal global matching between two minutiae sets. Within the MFMA, we first introduce an efficient matching operation to produce an initial population of local alignment configurations by examining local features of minutiae. Then, we devise a hybrid evolutionary procedure by combining the use of the global search functionality of a genetic algorithm with a local improvement operator to search for the optimal or near optimal global alignment. Finally, we define a reliable matching function for fitness computation. The proposed algorithm was evaluated by means of a series of experiments conducted on the FVC2002 database and compared with previous work. Experimental results confirm that the MFMA is an effective and practical matching algorithm for fingerprint verification. The algorithm is faster and more accurate than a traditional genetic-algorithm-based method. It is also more accurate than a number of other methods implemented for comparison, though our method generally requires more computational time in performing fingerprint matching.

Automatic image registration is an important process in remote sensing applications. In this paper, an efficient automatic system is resented for the estimation of the similarity transform parameters from partially overlapping images. Several aspects of the proposed system including corner extraction, corner matching and iterative transform parameter estimation are discussed in details. Experimental results using remote sensing images are presented.

A novel strategy for the representation and manipulationof distributed documents, potentially complex andheterogeneous, is presented in this paper. The documentunder the proposed model is represented in a hierarchicalstructure. Associated metadata' describes the flexiblehierarchy with the scope of dynamically restructuring thetree at runtime. All useful functionals can also be includedwithin the hierarchy to minimize reliance on externalprograms in manipulating sensitive data. Thisgives the proposed model two key properties: generality(capable of representing any document format includingfuture innovations) and autonomy (non-reliance on externalprograms). The model also allows incorporation ofadditional features for security and access control. Biometricperson authentication measures are introduced. Abrief example illustrates the key ideas.

Speech recognition and speaker recognition by machine are crucial ingredients for many important applications such as natural and flexible human-machine interfaces. Most developments in speech-based automatic recognition have relied on acoustic speech as the sole input signal, disregarding its visual counterpart. However, recognition based on acoustic speech alone can be afflicted with deficiencies that preclude its use in many real-world applications, particularly under adverse conditions. The combination of auditory and visual modalities promises higher recognition accuracy and robustness than can be obtained with a single modality. Multimodal recognition is therefore acknowledged as a vital component of the next generation of spoken language systems. The paper reviews the components of bimodal recognizers, discusses the accuracy of bimodal recognition, and highlights some outstanding research issues as well as possible application domains.

A novel strategy for the representation and manipulation of multimedia documents is introduced. The model allows such documents to be treated as autonomous entities capable of representing and modifying their own internal structures. The model is sufficiently flexible as to allow any given arbitrary document format and any programming language to be incorporated within its implementation.

This paper evaluates lip features for person recognition, and compares the performance with that of the acoustic signal. Recognition accuracy is found to be equivalent in the two domains, agreeing with the findings of Chibelushi (1997). The optimum dynamic window length for both acoustic and visual modalities is found to be about 100 ms. Recognition performance of the upper lip is considerably better than the lower lip, achieving 15% and 35% identification error rates respectively, using a single digit test and training token.

The integration of multiple classifiers promises higher classification accuracy and robustness than can be obtained with a single classifier. This paper proposes a new adaptive technique for classifier integration based on a linear combination model. The proposed technique is shown to exhibit robustness to a mismatch between test and training conditions. It often outperforms the most accurate of the fused information sources. A comparison between adaptive linear combination and non-adaptive Bayesian fusion shows that, under mismatched test and training conditions, the former is superior to the latter in terms of identification accuracy and insensitivity to information source distortion.

We present a new distance measure that can be used for comparing digital images. The proposed grey block distance (GBD) is compared with the Hutchinson metric to show its usefulness as a measure of the visual similarity of images.

This paper introduces new texture descriptors that perform well for rotated and unrotated texture images without the need to be trained with rotated samples. The algorithm uses a circular sampling of the image to produce rotation invariant features. By combining features derived from multiple concentric circles a higher performance in texture classification is achieved.

Presents work carried out on fractal (or attractor) image compression. The approach relies on the assumption that image redundancy can be efficiently exploited through self-transformability. The algorithms described utilize a novel region-based partition of the image that greatly increases the compression ratios achieved over traditional block-based partitionings. Due to the large search spaces involved, heuristic algorithms are used to construct these region-based transformations. Results for three different heuristic algorithms are given. The results show that the region-based system achieves almost double the compression ratio of the simple block-based system at a similar decompressed image quality. For the Lena image, compression ratios of 41:1 can be achieved at a PSNR of 26.56 dB.

Presents a face segmentation architecture using fuzzy inference. The head of a talker and two key structural features of his face (eyes and mouth) are located based on temporal and spatial information extracted from a head-and-shoulder image sequence. The architecture is modular and the segmentation uses a coarse-to-fine fuzzy reasoning strategy implemented across a three-level multi-resolution image pyramid. Results illustrating the performance of the system are given.>

The authors extend the alternative Hough transform method for the detection of multiple circles proposed by the authors (1990) to the detection of multiple concentric circles contained in an image. The parameters of a circle are determined by the groups of three edge points on the circle. The extension of the proposed rules to search for the three edge points ensures that every member of a group will be on the same circle, either on the inner circle or on the outer one, instead of some of them lying on the inner circle and some of them lying on the outer one. The application of the proposed method to a noisy gray-scale image containing washers shows that the clusters representing circle centers in the parameter space are much more compact than those obtained by the original Hough method for circle detection without involving postprocessing operations.>

A novel approach for circle detection based on the Hough transform is presented. It avoids the use of trigonometric functions in the transform equations. Instead of using traditional circle parameterization, which involves gradient direction information, this method uses three edge points to accumulate evidence for circle centers. The method can be extended to the detection of multiple circles where the gradient direction information is only used as a guide to select candidate edge points. A set of rules is proposed for the selection of triple edge points to define circle parameters which can guarantee that the points selected will not be on different circles. The responses for different circles produced in the parameter space using the proposed method are shown to be more compact around the true centers of the circles, thus, removing the need for postprocessing in the parameter space. The application of this method not only reduces the processing time, but also avoids the detection inaccuracy caused by the edge gradient direction errors.>