Field Of Biometrics Research Articles

The vision of biostatistics and biometrics on the analysis of biometric data: the Framingham risk score as an example

The fields of Biostatistics and Biometrics play a crucial role in unraveling the mysteries of human health and empowering healthcare professionals to make informed decisions. By mining health data for meaningful patterns, they enable medical practitioners to identify emerging trends and develop targeted, effective policies and practices. Meanwhile, the analysis of biological data unleashes a wealth of insights, enabling accurate diagnoses and unleashing innovative therapies that transform lives. Together, these fields are a powerful force for good, fueling breakthroughs that enable us to better understand and heal the human body (Clayton and Hills 2019).

Replay Attention and Data Augmentation Network for 3-D Face and Object Reconstruction

3D face reconstruction from single-view images plays an important role in the field of biometrics, which is a long-standing challenging problem in the wild. Traditional 3DMM-based methods directly regressed parameters, which probably caused that the network learned the discriminative informative features insufficiently. In this paper, we propose a replay attention and data augmentation network (RADAN) for 3D dense alignment and face reconstruction. Unlike the traditional attention mechanism, our replay attention module aims to increase the sensitivity of the network to informative features by adaptively recalibrating the weight response in the attention, which typically reinforces the distinguishability of the learned feature representation. In this way, the network can further improve the accuracy of face reconstruction and dense alignment in unconstrained environments. Moreover, to improve the generalization performance of the model and the ability of the network to capture local details, we present a data augmentation strategy to preprocess the sample data, which generates the images that contain more local details and occluded face in cropping and pasting manner. Furthermore, we also apply the replay attention to 3D object reconstruction task to verify the commonality of this mechanism. Extensive experimental results on widely-evaluated datasets demonstrate that our approach achieves competitive performance compared to state-of-the-art methods. Code is available at https://github.com/zhouzhiyuan1/RADANet.

Pengenalan Pola Garis Telapak Tangan Menggunakan Metode Fuzzy K-Nearest Neighbor

Palm pattern recognition is an important topic in the field of pattern recognition and biometrics. This study aims to develop a palm line pattern recognition method using the Fuzzy K-Nearest Neighbor (Fuzzy KNN) method to improve the accuracy and effectiveness of the individual recognition system. The research was conducted by collecting images, performing segmentation, feature extraction, and implementing the Fuzzy KNN method. Based on the results of the experiments that have been carried out, it can be seen that the average accuracy obtained is 20%, which means that the system is less able to recognize palm line patterns. This is due to a lack of dataset which causes poor recognition performance on the model.

A novel approach for biometric recognition based on ECG feature vectors

In the field of biometrics, electrocardiogram (ECG) recognition has the advantages of being live, difficult to replicate, and easy to collect. However, most deep learning methods for biometric recognition use a fixed length of ECG beats and only identify ECGs from a fixed number of people. The fixed input length may lead to information loss and the model needs to be retrained when a new ECG is added to the database, which is inconvenient for real applications. In this paper, we propose a biometric recognition method based on an ECG feature vector that uses a pooling layer to accept variable-length beat signals. The method accepts new classes without requiring model retraining while achieving excellent recognition performance. We verified the robustness of the method in the ECG-ID database, the MITDB arrhythmia database, and a private USSTDB database consisting of the ECG records of 60 volunteers before and after exercise. In addition, this method has good recognition ability in cross-database tests. The proposed method reduces the gap in biometric identification of exercise ECGs and demonstrates robustness and good generalization.

Face presentation attack detection: Research opportunities and perspectives

The rapid development of biometric methods and their implementation in practice has led to the widespread attacks called spoofing, which are purely biometric vulnerabilities, but are not used in conjunction with other IT security solutions. Although biometric recognition as a branch of computer science dates back to the 1960s, attacks on biometric systems have become more sophisticated since the 2010s due to great advances in pattern recognition. It should be noted that face recognition is the most attractive topic for deceiving recognition systems. Popular presentation attacks, such as print, replay and mask attacks, have demonstrated a high security risk for SOTA face recognition systems. Many Presentation Attack Detection (PAD) methods (also known as face anti-spoofing methods or countermeasures) have been proposed that can automatically detect and mitigate such targeted attacks. The article presents a systematic survey in face anti-spoofing with prognostic trends in this research area. A brief description of 16 outstanding previous surveys on the face PAD field is mentioned, from which it is possible to trace how this scientific topic has developed. SOTA in PAD provides an analysis of a wide range of the PAD methods, which are categorized into two unbalanced groups: digital (feature-based) and physical (sensor-based) methods. Generalization of deep learning methods as a recent trend aimed at improving recognition results requires special attention. This survey presents five types of generalization such as transfer learning, anomaly detection, few-shot and zero-shot learning, auxiliary supervision, and multi-spectral methods. A summary of over than 40 existing 2D/3D face spoofing databases is a guideline for those who want to select databases for experiments. One can also find a description of performance evaluation metrics and testing protocols. In addition, we discuss trends and perspectives in the emerging field of facial biometrics.

Design of Low-Complexity Convolutional Neural Network Accelerator for Finger Vein Identification System.

In the biometric field, vein identification is a vital process that is constrained by the invisibility of veins as well as other unique features. Moreover, users generally do not wish to have their personal information uploaded to the cloud, so edge computing has become popular for the sake of protecting user privacy. In this paper, we propose a low-complexity and lightweight convolutional neural network (CNN) and we design intellectual property (IP) for shortening the inference time in finger vein recognition. This neural network system can operate independently in client mode. After fetching the user's finger vein image via a near-infrared (NIR) camera mounted on an embedded system, vein features can be efficiently extracted by vein curving algorithms and user identification can be completed quickly. Better image quality and higher recognition accuracy can be obtained by combining several preprocessing techniques and the modified CNN. Experimental data were collected by the finger vein image capture equipment developed in our laboratory based on the specifications of similar products currently on the market. Extensive experiments demonstrated the practicality and robustness of the proposed finger vein identification system.

Gait Recognition Using Convolutional Neural Network

Biometrics are the body measurements and calculations related to individuals. Biometrics validation is used as a form of identification of individual. Gait recognition system is one of the most advanced technology that people have been working on for a while now that takes center stage in the field of biometrics. Compared to the other types of existing systems of biometric recognition such as fingerprint detection, iris-scanning systems etc., Gait Recognition system ensures no human intervention. This paper focuses on recognition based on a person’s gait. Every person has a distinct gait pattern that is unique to every other person. To train the model CASIA-B dataset has been used. The dataset includes 124 subjects where each sample has undergone Gait Energy Image extraction. Samples with clothing and baggage have been included which changes the silhouette of the person. Therefore, the model has been trained for a wider application where people wear different type of clothing and carry-ons. A Convolutional Neural Network consisting of 8 layers has been trained which performs well on both samples of dataset and an accuracy of 95.45% was obtained on dataset not involving layers of clothing and accuracy of 91.80% was obtained for the sample with clothing and baggage.

DRL-FVRestore: An Adaptive Selection and Restoration Method for Finger Vein Images Based on Deep Reinforcement

Finger vein recognition has become a research hotspot in the field of biometrics due to its advantages of non-contact acquisition, unique information, and difficulty in terms of forging or pirating. However, in the real-world application process, the extraction of image features for the biometric remains a significant challenge when the captured finger vein images suffer from blur, noise, or missing feature information. To address the above challenges, we propose a novel deep reinforcement learning-based finger vein image recovery method, DRL-FVRestore, which trained an agent that adaptively selects the appropriate restoration behavior according to the state of the finger vein image, enabling continuous restoration of the image. The behaviors of image restoration are divided into three tasks: deblurring restoration, defect restoration, and denoising and enhancement restoration. Specifically, a DeblurGAN-v2 based on the Inception-Resnet-v2 backbone is proposed to achieve deblurring restoration of finger vein images. A finger vein feature-guided restoration network is proposed to achieve defect image restoration. The DRL-FVRestore is proposed to deal with multi-image problems in complex situations. In this paper, extensive experimental results are conducted based on using four publicly accessible datasets. The experimental results show that for restoration with single image problems, the EER values of the deblurring network and damage restoration network are reduced by an average of 4.31% and 1.71%, respectively, compared to other methods. For images with multiple vision problems, the EER value of the proposed DRL-FVRestore is reduced by an average of 3.98%.

A lightweight convolutional neural network built on inceptio-residual and reduction modules for deep facial recognition in realistic conditions

ABSTRACT Since the last two decades, face recognition has been a significant area in the fields of biometrics and machine learning that uses the different appearances and geometric-based facial features to recognize the living substances present in a frame or video. In this article, we have proposed an inceptio-residual convolutional neural network inspired by the ResNet architecture for deep facial feature extraction and recognition. Besides that, some of the well-known lite or moderately dense and highly accurate ImageNet benchmarked convolutional neural networks, such as VGG-19 BN, ResNet 18/34/50, SE-ResNet50, ResNeXt50, Inception V2/V3/V4, Xception50, and DualPathNet68, have been utilized for face recognition. In conjunction with that, the proposed one was tested along those above-standard networks with respect to various performance metrics. Based on the results, we concluded that the proposed Incepto-residual convolutional neural network has performed better than the ImageNet benchmarked Convolutional Neural Networks.

INVESTIGAÇÃO SOBRE PARÂMETROS TÁCTEIS DE MARCHA BASEADOS NO APRENDIZADO PROFUNDO DO ALGORITMO DE ESTIMATIVA DE CONSUMO ENERGÉTICO NO ESPORTE

ABSTRACT Introduction In medicine, Deep Learning is a type of machine learning that aims to train computers to perform human tasks by simulating the human brain. Gait recognition and gait motion simulation is one of the most interesting research areas in the field of biometrics and can benefit from this technological feature. Objective To use Deep Learning to format and validate according to the dynamic characteristics of gait. Methods Gait was used for identity recognition, and gait recognition based on kinematics and dynamic gait parameters was performed through pattern recognition, including the position and the intensity value of maximum pressure points, pressure center point, and pressure ratio. Results The investigation shows that the energy consumption of gait as modeled analyzed, and the model of gait energy consumption can be obtained, which is comprehensively affected by motion parameters and individual feature parameters. Conclusion Real-time energy measurement is obtained when most people walk. The research shows that the gait frequency and body parameters obtained from the tactile parameters of gait biomechanics can more accurately estimate the energy metabolism of exercise and obtain the metabolic formula of exercise. There is a good application prospect for assessing energy metabolism through the tactile parameters of gait. Level of evidence II; Therapeutic studies - investigating treatment outcomes.

Pseudo-Label Noise Prevention, Suppression and Softening for Unsupervised Person Re-Identification

Unsupervised person re-identification (ReID), including fully unsupervised ReID and unsupervised domain adaptive ReID, remains a challenge for the fields of biometrics and computer vision due to its difficulty in learning with unlabeled target domain data. Existing state-of-the-art methods, most of which generate pseudo-labels via unsupervised clustering for model optimization, are inevitably hampered by the under-explored problem of pseudo-label noise. Motivated by this, we propose a novel joint framework termed pseudo-label Noise Prevention, Suppression, and Softening (NPSS) for unsupervised person re-identification. Instead of refining generated label noise after clustering as many existing methods do, we start solving this issue from the source of pseudo-label noise by proposing a new Dynamic Camera-Adaptive Clustering (DCAC), which dynamically involves camera information to prevent noise caused by cross-camera variance, thus improving their quality during clustering. Moreover, we propose an Online Domain Union (ODU) mechanism for the classification model learning on the target domain via involving source domain data with their ground-truth labels, which effectively suppresses the indelible noisy pseudo-labels. Furthermore, we present the Self-Consistency Constraint (SCC) to soften the label noise in a single model with reduced computation and network parameter cost, which achieves intra-sample knowledge ensembling with our global-local SCC and cross-sample knowledge ensembling with our inter-instance SCC. Experiments demonstrate the effectiveness of our method as it surpasses state-of-the-art methods by a large margin on Market-1501, DukeMTMC-ReID, and MSMT17 benchmarks. The code is available at https://github.com/hjwang-824/NPSS.

Comparison of Forensic Value of Biometric Analysis in Face & Ear Recognition in the Punjabi Population, Pakistan

Background: The use of face biometrics is very prevalent in forensic investigations for the identification of the perpetrators of crime due to the excessive use of CCTV footage that is usually available at the scene of a crime in urban settings. Ear biometric analysis of ear prints is also in vogue as a result of research advancements in the fields of biometrics. Keeping in view this scenario, it is the need of the hour to analyze the forensic value of this type of forensic evidence and compare these two tools of forensic biometrics. Purpose: To analyze and compare the forensic value of biometric analysis of face and ear print recognitions in the Punjabi population, in Punjab, Pakistan. Study design: This study is conducted by collecting the data from 100 samples of different people belonging to different backgrounds from different cities in Punjab, Pakistan after their informed consent and ethical approval. Their facial photographs and ear prints were collected for proceeding biometric analysis to form a database for comparison and recognition. Method and materials: After collecting data, the comparison is done to see whether we can recognize a person by only using ear print analysis or face biometrics after running a search in our own created database. Moreover, we also calculated the forensic values of this biometric analysis separately on its own and combined these two i.e., face and ear biometrics. . Furthermore, standard deviation, F-statistics, and Chitest p-value were also applied to see the power of discrimination of these two biometric methods of identification Results: In 100 samples, face recognition was proved to be 80 % recognition of identity as compared with only ear prints which showed 56 % accuracy in identifying the individuals who participated in this research. Furthermore, the combined result of both face recognition and ear biometrics showed 90 % recognition of the identity of the individuals. Statistical analysis proved that biometric analysis of the face for recognition of the identity of individuals was more valued as compared with ear print recognition. Also, it was found that if we combine these two methods of biometrics, the forensic value of recognition of individuals has increased and showed good results. Conclusion: The forensic value of biometric evidence of face and ear recognition is a very important tool for the forensic identification of individuals in crime scene investigations. Biometric facial recognition is better as compared to only ear print biometric analysis. Furthermore, using face and ear biometrics enhances the forensic value of biometric analysis. Keywords: Biometric analysis, Forensic value, face recognition, ear print recognition,

There is an elephant in the room: towards a critique on the use of fairness in biometrics

The proliferation of biometric systems in our societies is shaping public debates around its political, social and ethical implications. Yet, whilst concerns towards the racialised use of this technology have been on the rise, the field of biometrics remains unperturbed by these debates. Despite the lack of critical analysis, algorithmic fairness has recently been adopted by biometrics. Different studies have been published to understand and mitigate demographic bias in biometric systems, without analysing the political consequences. In this paper, we offer a critical reading of recent debates about biometric fairness and show its detachment from political debates. Building on previous fairness demonstrations, we prove that biometrics will be always biased. Yet, we claim algorithmic fairness cannot distribute justice in scenarios which are broken or whose intended purpose is to discriminate. By focusing on demographic biases rather than examine how these systems reproduce historical and political injustices, fairness has overshadowed the elephant in the room of biometrics.

Modified Firefly Optimization with Deep Learning based Multimodal Biometric Verification Model

Biometric security has become a main concern in the data security field. Over the years, initiatives in the biometrics field had an increasing growth rate. The multimodal biometric method with greater recognition and precision rate for smart cities remains to be a challenge. By comparison, made with the single biometric recognition, we considered the multimodal biometric recognition related to finger vein and fingerprint since it has high security, accurate recognition, and convenient sample collection. This article presents a Modified Firefly Optimization with Deep Learning based Multimodal Biometric Verification (MFFODL-MBV) model. The presented MFFODL-MBV technique performs biometric verification using multiple biometrics such as fingerprint, DNA, and microarray. In the presented MFFODL-MBV technique, EfficientNet model is employed for feature extraction. For biometric recognition, MFFO algorithm with long short-term memory (LSTM) model is applied with MFFO algorithm as hyperparameter optimizer. To ensure the improved outcomes of the MFFODL-MBV approach, a widespread experimental analysis was performed. The wide-ranging experimental analysis reported improvements in the MFFODL-MBV technique over other models.

Periocular biometrics and its relevance to partially masked faces: A survey

Periocular is one of the promising biometric traits for human recognition. It encompasses a surrounding area of eyes that includes eyebrows, eyelids, eyelashes, eye-folds, eyebrows, eye shape, and skin texture. Its relevance is more emphasize during the COVID-19 pandemic due to the masked faces. So, this article presents a detailed review of periocular biometrics to understand its current state. The paper first discusses the various face and periocular techniques, specially designed to recognize humans wearing a face mask. Then, different aspects of periocular biometrics are reviewed: (a) the anatomical cues present in the periocular region useful for recognition, (b) the various feature extraction and matching techniques developed, (c) recognition across different spectra, (d) fusion with other biometric modalities (face or iris), (e) recognition on mobile devices, (f) its usefulness in other applications, (g) periocular datasets, and (h) competitions organized for evaluating the efficacy of this biometric modality. Finally, various challenges and future directions in the field of periocular biometrics are presented.

Contactless Fingerprint Recognition Using Deep Learning—A Systematic Review

Contactless fingerprint identification systems have been introduced to address the deficiencies of contact-based fingerprint systems. A number of studies have been reported regarding contactless fingerprint processing, including classical image processing, the machine-learning pipeline, and a number of deep-learning-based algorithms. The deep-learning-based methods were reported to have higher accuracies than their counterparts. This study was thus motivated to present a systematic review of these successes and the reported limitations. Three methods were researched for this review: (i) the finger photo capture method and corresponding image sensors, (ii) the classical preprocessing method to prepare a finger image for a recognition task, and (iii) the deep-learning approach for contactless fingerprint recognition. Eight scientific articles were identified that matched all inclusion and exclusion criteria. Based on inferences from this review, we have discussed how deep learning methods could benefit the field of biometrics and the potential gaps that deep-learning approaches need to address for real-world biometric applications.

Ear semantic segmentation in natural images with Tversky loss function supported DeepLabv3+ convolutional neural network

Semantic segmentation is a fundamental problem for computer vision. On the other hand, for studies in the field of biometrics, semantic segmentation is gaining more importance. Many successful biometric recognition systems require a high- performance semantic segmentation algorithm. In this study, we present an effective ear segmentation technique in natural images. A convolutional neural network is trained for pixel-based ear segmentation. DeepLab v3+ network structure, with ResNet-18 as the backbone and Tversky lost function layer as the last layer, has been trained with natural and uncontrolled images. We perform the proposed network training using only the 750 images in the Annotated Web Ears (AWE) training set. The corresponding tests are performed on the AWE Test Set, University of Ljubljana Test Set, and the Collection A of In-The-Wild dataset. For the Annotated Web Ears (AWE) dataset, intersection over union (IoU) is measured as 86.3% for the AWE database. To the best of our knowledge, this is the highest performance achieved among the algorithms tested on the AWE test set.

Advances in Vision-Based Gait Recognition: From Handcrafted to Deep Learning.

Identifying people’s identity by using behavioral biometrics has attracted many researchers’ attention in the biometrics industry. Gait is a behavioral trait, whereby an individual is identified based on their walking style. Over the years, gait recognition has been performed by using handcrafted approaches. However, due to several covariates’ effects, the competence of the approach has been compromised. Deep learning is an emerging algorithm in the biometrics field, which has the capability to tackle the covariates and produce highly accurate results. In this paper, a comprehensive overview of the existing deep learning-based gait recognition approach is presented. In addition, a summary of the performance of the approach on different gait datasets is provided.

Multi-Biometric Iris Recognition System Using Consensus Between Convolutional Neural Network Architectures

The field of biometrics represents an important domain and is currently undergoing extensive research to improve data security. Among the most used biometric modalities, we find the iris which, is specific and adequate. It is unique for each human being. Iris identification is used at international airports, sea, and land borders. In this article, we propose to use convolutional neural networks (CNN) with a consensus between the architectures (VGG, DenseNet, Resnet, Inception, MobileNet, and Xception). The goal is to classify and combine CNN architectures with the Softmax classifier focusing on consensus orientation using a voting system (Hard voting). In addition, the use of optimization techniques such as Transfer learning, Batch-normalization, Dropout, Data augmentation, Global average pooling, and Cross-validation will accelerate the learning process and avoid overfitting. Using the GPU with its parallelization will significantly speed up the processing of our program. The experiments of our approach were carried out on the MMU1 iris database with an accuracy reaching 100%.

Ear recognition system using random forest and histograms of oriented gradients techniques

In recent years, systems of ear recognition are considered a significant topic of research in the biometrics field. In such systems, the models of machine learning represent a principal part in order to recognise humans’ identities by using their ear images. In this paper, a system of ear recognition is proposed by using random forest (RF) and histograms of oriented gradients (HOG) techniques. The HOG is used to extract features from ear images. Subsequently, these extracted features will be fed to the RF classifier to classify the ear images with respect to the classes. In this study, the ear images have been selected from the Indian Institute of Technology Delhi, second version (IITD II). The performance of the proposed system has evaluated by using different evaluation measures such as accuracy, specificity, and G-mean. The experimental results show that the proposed system for ear recognition obtains accuracy up to 99.69%. Furthermore, this system archives 99.84% and 80.78% for specificity and G-mean, respectively. The proposed system has the ability to identify persons through their ear images effectively.