Showing papers on "Biometrics published in 2022"

DS-CNN: A pre-trained Xception model based on depth-wise separable convolutional neural network for finger vein recognition

Abstract: Finger vein recognition received special attention among all other biometric traits due to its high security. Adequate recognition and classification accuracy ensure the security of personal authentication. Many convolutional neural networks (CNNs) have been proposed with a promising performance in biometric finger vein recognition. However, their architectures have several problems, such as high complexity, extraction of robust features, degraded performance, etc. Considering the issues of CNNs, the authors present a pre-trained CNN network named Xception model based on depth-wise separable CNNs with residual connection, which is considered to be a more effective, less complex neural network to extract robust features. Our work can be seen as a three-stage process. Initially, the concept of data pre-processing is applied to convert the raw input samples into the standard format. Afterward, data augmentation using different geometrical techniques is incorporated to overcome the lack of training samples required for training the deep learning model. Finally, the feature extraction and classification task is performed through the pre-trained Xception architecture to verify the person's identity. SDUMLA and THU-FVFDT2 datasets are utilized to test and evaluate the proposed multi-layered CNN model performance with existing arts. Our proposed method for the SDUMLA database achieved an accuracy of 99% with an F1-score of 98%. While on THU-FVFDT2, the proposed method obtained an accuracy of 90% with an F1-score of 88%. Experimental results conclude that the proposed work obtained excellent performance compared to existing methods.

Biometrics-protected optical communication enabled by deep learning–enhanced triboelectric/photonic synergistic interface

Abstract: Security is a prevailing concern in communication as conventional encryption methods are challenged by progressively powerful supercomputers. Here, we show that biometrics-protected optical communication can be constructed by synergizing triboelectric and nanophotonic technology. The synergy enables the loading of biometric information into the optical domain and the multiplexing of digital and biometric information at zero power consumption. The multiplexing process seals digital signals with a biometric envelope to avoid disrupting the original high-speed digital information and enhance the complexity of transmitted information. The system can perform demultiplexing, recover high-speed digital information, and implement deep learning to identify 15 users with around 95% accuracy, irrespective of biometric information data types (electrical, optical, or demultiplexed optical). Secure communication between users and the cloud is established after user identification for document exchange and smart home control. Through integrating triboelectric and photonics technology, our system provides a low-cost, easy-to-access, and ubiquitous solution for secure communication.

A Joint Bayesian Framework Based on Partial Least Squares Discriminant Analysis for Finger Vein Recognition

Abstract: Finger vein recognition has attracted considerable attention from the biometric identification technology community owing to its convenience and security. Unlike most previous works only pay attention to one part of finger vein recognition, we propose a joint Bayesian framework in this paper, which is based on partial least squares discriminant analysis (PLS-DA). It involves three major stages: 1) robust feature description, 2) discriminative feature mapping, and 3) separative verification. In stage 1), we extract line responses and orientation of finger veins using a bank of Gabor filter, and histograms are constructed in local patches as primitive features. Subsequently, in stage 2), a discriminant feature mapping based the PLS-DA (PLS-DA-FM) method is proposed to project these primitive features into low-dimensional forms in a supervised manner. Thus, highly compact and discriminative features are obtained in this stage. Finally, in stage 3), we directly build a Bayesian model based on the joint distribution of finger vein feature pairs to measure the similarity between the features. Extensive experiments on five finger vein datasets demonstrate the superior performance of the proposed method to most state-of-the-art finger vein recognition methods.

Face Spoofing, Age, Gender and Facial Expression Recognition Using Advance Neural Network Architecture-Based Biometric System

Abstract: Nowadays, the demand for soft-biometric-based devices is increasing rapidly because of the huge use of electronics items such as mobiles, laptops and electronic gadgets in daily life. Recently, the healthcare department also emerged with soft-biometric technology, i.e., face biometrics, because the entire data, i.e., (gender, age, face expression and spoofing) of patients, doctors and other staff in hospitals is managed and forwarded through digital systems to reduce paperwork. This concept makes the relation friendlier between the patient and doctors and makes access to medical reports and treatments easier, anywhere and at any moment of life. In this paper, we proposed a new soft-biometric-based methodology for a secure biometric system because medical information plays an essential role in our life. In the proposed model, 5-layer U-Net-based architecture is used for face detection and Alex-Net-based architecture is used for classification of facial information i.e., age, gender, facial expression and face spoofing, etc. The proposed model outperforms the other state of art methodologies. The proposed methodology is evaluated and verified on six benchmark datasets i.e., NUAA Photograph Imposter Database, CASIA, Adience, The Images of Groups Dataset (IOG), The Extended Cohn-Kanade Dataset CK+ and The Japanese Female Facial Expression (JAFFE) Dataset. The proposed model achieved an accuracy of 94.17% for spoofing, 83.26% for age, 95.31% for gender and 96.9% for facial expression. Overall, the modification made in the proposed model has given better results and it will go a long way in the future to support soft-biometric based applications.

Comprehensive survey of computational ECG analysis: Databases, methods and applications

Abstract: Electrocardiogram (ECG) recordings are indicative for the state of the human heart. Automatic analysis of these recordings can be performed using various computational methods from the areas of signal processing and machine learning. In addition to the 12-lead ECG devices and the Holter monitor, as currently the most widely used ECG screening methods in clinical practice, ECG recordings are recently often acquired with small novel wireless ECG body sensors. These novel types of body sensors allow for ECG monitoring and analysis to be used for a much broader array of applications than only diagnosing cardiovascular disorders. The new types of ECG measuring devices, as well as their broader and more frequent use, pose new challenges in the processing and analysis of ECG, and furthermore, raise the need for automatic, low-cost, real-time, and efficient ECG monitoring that can be used at home or under ambulatory settings alike. This paper provides a comprehensive survey on the variety of both ECG data and computational methods in various applications: morphological and rhythmic arrhythmia detection, signal quality assessment, biometric identification, respiration estimation, fetal ECG extraction, and physical and emotional monitoring. It includes an extensive overview of 45 diverse ECG public databases and their analysis with state-of-the-art computational ECG methods. We highlight the most notable achievements in each of these ECG application areas in the recent years, and, furthermore, identify future trends in computational ECG analysis, especially analysis of ECG from mobile devices. The general conclusion is that ECG for medical diagnosis is successfully analyzed with the existing methods, while different applications during daily ECG monitoring are still open fields. Given how deep learning has been able to successfully address a lot of the most significant computational ECG problems, like arrhythmia classification, in future, it is expected for deep learning methods to be comprehensively tested in areas where they have not been yet applied, such as respiration estimation and fetal ECG extraction.

Enhanced multimodal biometric recognition approach for smart cities based on an optimized fuzzy genetic algorithm

Abstract: Biometric security is a major emerging concern in the field of data security. In recent years, research initiatives in the field of biometrics have grown at an exponential rate. The multimodal biometric technique with enhanced accuracy and recognition rate for smart cities is still a challenging issue. This paper proposes an enhanced multimodal biometric technique for a smart city that is based on score-level fusion. Specifically, the proposed approach provides a solution to the existing challenges by providing a multimodal fusion technique with an optimized fuzzy genetic algorithm providing enhanced performance. Experiments with different biometric environments reveal significant improvements over existing strategies. The result analysis shows that the proposed approach provides better performance in terms of the false acceptance rate, false rejection rate, equal error rate, precision, recall, and accuracy. The proposed scheme provides a higher accuracy rate of 99.88% and a lower equal error rate of 0.18%. The vital part of this approach is the inclusion of a fuzzy strategy with soft computing techniques known as an optimized fuzzy genetic algorithm.

Gait Recognition Based on Deep Learning: A Survey

Abstract: In general, biometry-based control systems may not rely on individual expected behavior or cooperation to operate appropriately. Instead, such systems should be aware of malicious procedures for unauthorized access attempts. Some works available in the literature suggest addressing the problem through gait recognition approaches. Such methods aim at identifying human beings through intrinsic perceptible features, despite dressed clothes or accessories. Although the issue denotes a relatively long-time challenge, most of the techniques developed to handle the problem present several drawbacks related to feature extraction and low classification rates, among other issues. However, deep learning-based approaches recently emerged as a robust set of tools to deal with virtually any image and computer-vision-related problem, providing paramount results for gait recognition as well. Therefore, this work provides a surveyed compilation of recent works regarding biometric detection through gait recognition with a focus on deep learning approaches, emphasizing their benefits and exposing their weaknesses. Besides, it also presents categorized and characterized descriptions of the datasets, approaches, and architectures employed to tackle associated constraints.

Meta-Heuristic Optimization and Keystroke Dynamics for Authentication of Smartphone Users

Abstract: Personal Identification Numbers (PIN) and unlock patterns are two of the most often used smartphone authentication mechanisms. Because PINs have just four or six characters, they are subject to shoulder-surfing attacks and are not as secure as other authentication techniques. Biometric authentication methods, such as fingerprint, face, or iris, are now being studied in a variety of ways. The security of such biometric authentication is based on PIN-based authentication as a backup when the maximum defined number of authentication failures is surpassed during the authentication process. Keystroke-dynamics-based authentication has been studied to circumvent this limitation, in which users were categorized by evaluating their typing patterns as they input their PIN. A broad variety of approaches have been proposed to improve the capacity of PIN entry systems to discriminate between normal and abnormal users based on a user’s typing pattern. To improve the accuracy of user discrimination using keystroke dynamics, we propose a novel approach for improving the parameters of a Bidirectional Recurrent Neural Network (BRNN) used in classifying users’ keystrokes. The proposed approach is based on a significant modification to the Dipper Throated Optimization (DTO) algorithm by employing three search leaders to improve the exploration process of the optimization algorithm. To assess the effectiveness of the proposed approach, two datasets containing keystroke dynamics were included in the conducted experiments. In addition, we propose a feature selection algorithm for selecting the proper features that enable better user classification. The proposed algorithms are compared to other optimization methods in the literature, and the results showed the superiority of the proposed algorithms. Moreover, a statistical analysis is performed to measure the stability and significance of the proposed methods, and the results confirmed the expected findings. The best classification accuracy achieved by the proposed optimized BRNN is 99.02% and 99.32% for the two datasets.

On Learning Disentangled Representations for Gait Recognition

Abstract: Gait, the walking pattern of individuals, is one of the important biometrics modalities. Most of the existing gait recognition methods take silhouettes or articulated body models as gait features. These methods suffer from degraded recognition performance when handling confounding variables, such as clothing, carrying and viewing angle. To remedy this issue, we propose a novel AutoEncoder framework, GaitNet, to explicitly disentangle appearance, canonical and pose features from RGB imagery. The LSTM integrates pose features over time as a dynamic gait feature while canonical features are averaged as a static gait feature. Both of them are utilized as classification features. In addition, we collect a Frontal-View Gait (FVG) dataset to focus on gait recognition from frontal-view walking, which is a challenging problem since it contains minimal gait cues compared to other views. FVG also includes other important variations, e.g., walking speed, carrying, and clothing. With extensive experiments on CASIA-B, USF, and FVG datasets, our method demonstrates superior performance to the SOTA quantitatively, the ability of feature disentanglement qualitatively, and promising computational efficiency. We further compare our GaitNet with state-of-the-art face recognition to demonstrate the advantages of gait biometrics identification under certain scenarios, e.g., long-distance/lower resolutions, cross viewing angles. Source code is available at http://cvlab.cse.msu.edu/project-gaitnet.html.

Adam or Eve? Automatic users’ gender classification via gestures analysis on touch devices

Abstract: Abstract Gender classification of mobile devices’ users has drawn a great deal of attention for its applications in healthcare, smart spaces, biometric-based access control systems and customization of user interface (UI). Previous works have shown that authentication systems can be more effective when considering soft biometric traits such as the gender, while others highlighted the significance of this trait for enhancing UIs. This paper presents a novel machine learning-based approach to gender classification leveraging the only touch gestures information derived from smartphones’ APIs. To identify the most useful gesture and combination thereof for gender classification, we have considered two strategies: single-view learning, analyzing, one at a time, datasets relating to a single type of gesture, and multi-view learning, analyzing together datasets describing different types of gestures. This is one of the first works to apply such a strategy for gender recognition via gestures analysis on mobile devices. The methods have been evaluated on a large dataset of gestures collected through a mobile application, which includes not only scrolls, swipes, and taps but also pinch-to-zooms and drag-and-drops which are mostly overlooked in the literature. Conversely to the previous literature, we have also provided experiments of the solution in different scenarios, thus proposing a more comprehensive evaluation. The experimental results show that scroll down is the most useful gesture and random forest is the most convenient classifier for gender classification. Based on the (combination of) gestures taken into account, we have obtained F1-score up to 0.89 in validation and 0.85 in testing phase. Furthermore, the multi-view approach is recommended when dealing with unknown devices and combinations of gestures can be effectively adopted, building on the requirements of the system our solution is built-into. Solutions proposed turn out to be both an opportunity for gender-aware technologies and a potential risk deriving from unwanted gender classification.

Bias in Automated Speaker Recognition

Abstract: Automated speaker recognition uses data processing to identify speakers by their voice. Today, automated speaker recognition is deployed on billions of smart devices and in services such as call centres. Despite their wide-scale deployment and known sources of bias in related domains like face recognition and natural language processing, bias in automated speaker recognition has not been studied systematically. We present an in-depth empirical and analytical study of bias in the machine learning development workflow of speaker verification, a voice biometric and core task in automated speaker recognition. Drawing on an established framework for understanding sources of harm in machine learning, we show that bias exists at every development stage in the well-known VoxCeleb Speaker Recognition Challenge, including data generation, model building, and implementation. Most affected are female speakers and non-US nationalities, who experience significant performance degradation. Leveraging the insights from our findings, we make practical recommendations for mitigating bias in automated speaker recognition, and outline future research directions.

Machine and Deep Learning Applications to Mouse Dynamics for Continuous User Authentication

Abstract: Static authentication methods, like passwords, grow increasingly weak with advancements in technology and attack strategies. Continuous authentication has been proposed as a solution, in which users who have gained access to an account are still monitored in order to continuously verify that the user is not an imposter who had access to the user credentials. Mouse dynamics is the behavior of a user’s mouse movements and is a biometric that has shown great promise for continuous authentication schemes. This article builds upon our previous published work by evaluating our dataset of 40 users using three machine learning and three deep learning algorithms. Two evaluation scenarios are considered: binary classifiers are used for user authentication, with the top performer being a 1-dimensional convolutional neural network (1D-CNN) with a peak average test accuracy of 85.73% across the top-10 users. Multi-class classification is also examined using an artificial neural network (ANN) which reaches an astounding peak accuracy of 92.48%, the highest accuracy we have seen for any classifier on this dataset.

3D Face Reconstruction in Deep Learning Era: A Survey

Abstract: 3D face reconstruction is the most captivating topic in biometrics with the advent of deep learning and readily available graphical processing units. This paper explores the various aspects of 3D face reconstruction techniques. Five techniques have been discussed, namely, deep learning, epipolar geometry, one-shot learning, 3D morphable model, and shape from shading methods. This paper provides an in-depth analysis of 3D face reconstruction using deep learning techniques. The performance analysis of different face reconstruction techniques has been discussed in terms of software, hardware, pros and cons. The challenges and future scope of 3d face reconstruction techniques have also been discussed.

Application of Biometric System to Enhance the Security in Virtual World

Abstract: Virtual worlds was becoming increasingly popular in a variety of fields, including education, business, space exploration, and video games. Establishing the security of virtual worlds was becoming more critical as they become more widely used. Virtual users were identified using a behavioral biometric system. Improve the system's ability to identify objects by fusing scores from multiple sources. Identification was based on a review of user interactions in virtual environments and a comparison with previous recordings in the database. For behavioral biometric systems like the one described, it appears that score-level biometric fusion was a promising tool for improving system performance. As virtual worlds become more immersive, more people will want to participate in them, and more people will want to be able to interact with each other. Each region of the Meta-verse was given a glimpse of the current state of affairs and the trends to come. As hardware performance and institutional and public interest continue to improve, the Meta-verse's development is hampered by limitations like computational method limits and a lack of realized collaboration between virtual world stakeholders and developers alike. A major goal of the proposed research was to verify the accuracy of the biometric system to enhance the security in virtual world. In this study, the precision of the proposed work was compared to that of previous work.

Enhanced multimodal biometric recognition approach for smart cities based on an optimized fuzzy genetic algorithm

Abstract: Biometric security is a major emerging concern in the field of data security. In recent years, research initiatives in the field of biometrics have grown at an exponential rate. The multimodal biometric technique with enhanced accuracy and recognition rate for smart cities is still a challenging issue. This paper proposes an enhanced multimodal biometric technique for a smart city that is based on score-level fusion. Specifically, the proposed approach provides a solution to the existing challenges by providing a multimodal fusion technique with an optimized fuzzy genetic algorithm providing enhanced performance. Experiments with different biometric environments reveal significant improvements over existing strategies. The result analysis shows that the proposed approach provides better performance in terms of the false acceptance rate, false rejection rate, equal error rate, precision, recall, and accuracy. The proposed scheme provides a higher accuracy rate of 99.88% and a lower equal error rate of 0.18%. The vital part of this approach is the inclusion of a fuzzy strategy with soft computing techniques known as an optimized fuzzy genetic algorithm.

Capsule Network-Based Deep Transfer Learning Model for Face Recognition

Abstract: Face recognition (FR) is a technique for recognizing individuals through the use of face photographs. The FR technology is widely applicable in a variety of fields, including security, biometrics, authentication, law enforcement, smart cards, and surveillance. Recent advances in deep learning (DL) models, particularly convolutional neural networks (CNNs), have demonstrated promising results in the field of FR. CNN models that have been pretrained can be utilized to extract characteristics for effective FR. In this regard, this research introduces the GWOECN-FR approach, a unique grey wolf optimization with an enhanced capsule network-based deep transfer learning model for real-time face recognition. The proposed GWOECN-FR approach is primarily concerned with reliably and rapidly recognizing faces in input photos. Additionally, the GWOECN-FR approach is preprocessed in two steps, namely, data augmentation and noise reduction by bilateral filtering (BF). Additionally, for feature vector extraction, an expanded capsule network (ECN) model can be used. Additionally, grey wolf optimization (GWO) combined with a stacked autoencoder (SAE) model is used to identify and classify faces in images. The GWO algorithm is used to optimize the SAE model’s weight and bias settings. The GWOECN-FR technique’s performance is validated using a benchmark dataset, and the results are analyzed in a variety of aspects. The GWOECN-FR approach achieved a TST of 0.03 s on the FEI dataset, whereas the AlexNet-SVM, ResNet-SVM, and AlexNet models achieved TSTs of 0.125 s, 0.0051 s, and 0.0062 s, respectively. The experimental results established that the GWOECN-FR technology outperformed more contemporary approaches.

BioSec: A Biometric Authentication Framework for Secure and Private Communication Among Edge Devices in IoT and Industry 4.0

Abstract: To address the privacy and security related challenges in Internet of Things (IoT) environment, we proposed a biometric method called BioSec to provide authentication in IoT integrated with edge consumer electronics with fingerprint authentication. Further, we ensured the security of biometric data both in the transmission channel and database with the standard encryption method. In this way, BioSec ensures secure and private communication among edge devices in IoT and Industry 4.0. Finally, we have compared three encryption methods used to protect biometric templates in terms of processing times and identified that AES-128-bit key encryption method outperforms others.

Finger-vein presentation attack detection using depthwise separable convolution neural network

Abstract: Biometrics is a powerful tool for identifying and authenticating persons based on their unique characteristics. Finger vein (FV) seems to be an emerging biometric of all types of hand-based biometrics, which have garnered considerable interest because of the extensive information and ease of implementation. As the FV system has grown in popularity, there have been numerous attempts to compromise it. Recent research reveals that the finger-vein recognition (FVR) system is vulnerable to presentation attacks, in which the sensory device accepts a fake printed FV image and grants access as if it were a genuine attempt. Few deep learning (DL) studies were developed in the past to detect spoof attacks in FV images. Existing works rely on performance improvement by neglecting the problems of the limited dataset, high computational complexity, and unavailability of lightweight and efficient feature descriptors. Therefore, we have proposed a novel depthwise separable convolution neural network (DSC) with residual connection and a linear support vector machine (LSVM) for the automatic detection of FV presentation attacks. At first, we apply the data augmentation method to raw images to increase the size of datasets. Afterward, this DSC technique is applied to extract robust features from FV images. Finally, a LSVM classifier is used to classify the images into bonafide and fake images. The proposed DSC-LSVM method is evaluated on two publicly available datasets such as Idiap and SCUT-FVD. The experimental results show that the DSC-SVM model attained a low error rate of 0.00% for presentation attack detection (PAD) on both datasets compared to state-of-the-art approaches. Several experimental results show that the DSC-LSVM model required less computation time and fewer parameters to detect spoof finger vein images. It concludes that the DSC-LSVM system is outperformed for PAD on finger vein images compared to existing methods.

Sensitive loss: Improving accuracy and fairness of face representations with discrimination-aware deep learning

Abstract: We propose a discrimination-aware learning method to improve both the accuracy and fairness of biased face recognition algorithms. The most popular face recognition benchmarks assume a distribution of subjects without paying much attention to their demographic attributes. In this work, we perform a comprehensive discrimination-aware experimentation of deep learning-based face recognition. We also propose a notational framework for algorithmic discrimination with application to face biometrics. The experiments include three popular face recognition models and three public databases composed of 64,000 identities from different demographic groups characterized by sex and ethnicity. We experimentally show that learning processes based on the most used face databases have led to popular pre-trained deep face models that present evidence of strong algorithmic discrimination. Finally, we propose a discrimination-aware learning method, Sensitive Loss, based on the popular triplet loss function and a sensitive triplet generator. Our approach works as an add-on to pre-trained networks and is used to improve their performance in terms of average accuracy and fairness. The method shows results comparable to state-of-the-art de-biasing networks and represents a step forward to prevent discriminatory automatic systems.