Field Of Biometrics Research Articles

Biometrics in extended reality: a review

AbstractIn the domain of Extended Reality (XR), particularly Virtual Reality (VR), extensive research has been devoted to harnessing this transformative technology in various real-world applications. However, a critical challenge that must be addressed before unleashing the full potential of XR in practical scenarios is to ensure robust security and safeguard user privacy. This paper presents a systematic survey of the utility of biometric characteristics applied in the XR environment. To this end, we present a comprehensive overview of the different types of biometric modalities used for authentication and representation of users in a virtual environment. We discuss different biometric vulnerability gateways in general XR systems for the first time in the literature along with taxonomy. A comprehensive discussion on generating and authenticating biometric-based photorealistic avatars in XR environments is presented with a stringent taxonomy. We also discuss the availability of different datasets that are widely employed in evaluating biometric authentication in XR environments together with performance evaluation metrics. Finally, we discuss the open challenges and potential future work that need to be addressed in the field of biometrics in XR.

Biometric access system with automatic registration and loyalty check in the system of recognition and database entry

ABSTRACT Against the backdrop of ongoing terrorist threats and uncontrolled migration flows, there is increased interest in biometric human recognition technology and barcoding technology combined with it. As a possible solution, a biometric access system is proposed, designed to implement three main urgent tasks – automatic registration of people crossing the border; recording registration information in a special biometric database; checking registration information and facial image on the database of wanted people. Effective biometric systems combine verification and identification tasks to increase the reliability of person identification and comparison with reference data sets. In the course of the study, various methods of information processing with its subsequent encoding were considered and analyzed, and the experience of previous systems of this type was investigated. As a result of the study, the effectiveness of using the latest biometric technologies in the migration sphere and in law enforcement agencies for the effective search of offenders has been substantiated. This paper will be useful as a material for further study of facial recognition technology and the integration of QR into the field of biometrics.

Hydrogel-Based Artificial Synapses for Sustainable Neuromorphic Electronics.

Hydrogels find widespread applications in biomedicine because of their outstanding biocompatibility, biodegradability, and tunable material properties. Hydrogels can be chemically functionalized or reinforced to respond to physical or chemical stimulation, which opens up new possibilities in the emerging field of intelligent bioelectronics. Here, the state-of-the-art in functional hydrogel-based transistors and memristors is reviewed as potential artificial synapses. Within these systems, hydrogels can serve as semisolid dielectric electrolytes in transistors and as switching layers in memristors. These synaptic devices with volatile and non-volatile resistive switching show good adaptability to external stimuli for short-term and long-term synaptic memory effects, some of which are integrated into synaptic arrays as artificial neurons; although, there are discrepancies in switching performance and efficacy. By comparing different hydrogels and their respective properties, an outlook is provided on a new range of biocompatible, environment-friendly, and sustainable neuromorphic hardware. How potential energy-efficient information storage and processing can be achieved using artificial neural networks with brain-inspired architecture for neuromorphic computing is described. The development of hydrogel-based artificial synapses can significantly impact the fields of neuromorphic bionics, biometrics, and biosensing.

A cancellable iris template protection scheme based on inverse merger and Bloom filter

Iris recognition has found extensive applications in real-world situations and financial contexts. However, Iris template protection schemes are highly vulnerable to well-planned attacks that can lead to the leakage of personal information. Once biological information is compromised, this loss is irreversible for the individual. Cancelable protection schemes for iris templates based on the Bloom filter have substantial attention in the field of iris biometrics. Nevertheless, Bloom filter-based template protection schemes face specific security challenges. Therefore, it is crucial to propose a method to protect iris templates that is both secure and efficient. To address irreversible limitations in security analysis, we propose a template protection scheme, a cancelable iris biometric protection scheme based on inverse merger and Bloom filter. The primary idea of the proposed scheme is to perform an inverse merger operation on the acquired codewords before mapping the iris templates to the Bloom filter specifically. Through a comparison of the sizes between the original templates and their inverted counterparts, the template with the smaller size is chosen as the definitive result, subsequently being mapped into the Bloom filter. Our proposed scheme exhibits significant advancements in accuracy across multiple datasets, as evidenced by empirical validations. In the optimal case, our model achieves an excellent performance of 98.04% in terms of GAR, while achieving a significant reduction of 0.51% in terms of EER. Furthermore, a comparative analysis with existing iris template protection methods is performed to evaluate its relative effectiveness in resisting the attack of averaging the columns of a block. The results demonstrate that the scheme exhibits robust resistance to such attacks. The experimental analysis demonstrated that the scheme provided a good balance between accuracy and safety.

Human Visual System applied to Facial Recognition

Research in the field of biometrics is constantly expanding. Numerous studies have been carried out to develop different techniques with the aim of ensuring reliable and efficient recognition systems. Of our five senses, vision takes up the most of the neurons in our brain. This makes the visual approach challenging. This paper proposes to develop a new facial recognition technique based on the concept of Human Visual System in order to simulate or imitate human perception. Our approach exploits the behavior of the Human Visual System in biometric systems to improve individual recognition. It focuses on Perceptual Channel Decomposition in order to generate images, confined around a certain frequency range, perfectly uncorrelated. For the extraction of characteristic vectors, our technique uses the Principal Component Analysis. The principle of the visual approach consists of exploiting one or more characteristics of the peripheral parts of the Human Visual System. These characteristics can integrate the sensitivity of the Human Visual System to spatial frequencies, its sensitivity to local contrast. The Principal Component Analysis uses a set of seventeen channels, each adjusted to a band of given radial frequencies and orientation. The seventeen output images contain the same spatial information but are perfectly uncorrelated from a spectral point of view. In the implementation phase, we limited ourselves to explore this technique by using only four frequency rings. The results obtained are conclusive and satisfactory.

Identification of Signature Authenticity Using Binary Extraction and K-nearest Neighbor Feature Methods

This research focuses on identifying the authenticity of signatures, which is an important part of the field of biometrics. Identification of signature authenticity has wide applications, including in document security, financial transactions, and identity verification in general. The problem to be resolved is the lack of an effective and efficient method for identifying signature authenticity. The method used is the binary extraction method and the K-nearest Neighbor feature. The main contribution of this research is to propose a new approach in identifying signature authenticity by combining binary extraction methods and K-nearest Neighbor features. This approach is expected to increase the accuracy and efficiency of the signature authenticity identification process. The results of this research are the development of a new model or algorithm for identifying the authenticity of signatures. After testing and validation, the accuracy level of the results of identifying the authenticity of this signature is 75%.

Palmprint Identification Using Dolphin Optimization

Palm print recognition is a rapidly evolving area in the field of biometrics, providing a high level of security for various applications Advances in scanning technology and software have led to faster and more accurate palm print analysis, we have proposed in this paper a system for palm recognition using the Dolphin Optimization Algorithm (DOA) as a computational technique inspired by nature aimed at solving complex improvement problems. We reduced the number of image features using the Histograms of oriented gradients (HOG) algorithm, we named this method as (DOA) and we also proposed a hybrid method by integrating the DOA algorithm with the Support Vector Machine (SVM) model to improve prediction accuracy by combining DSA's ability to search for global optimal solutions with the effective classification capabilities of SVM, this allows The hybrid approach creates a robust and the proposed hybrid method was named (SVM-DOA), and we also proposed a hybrid method by integrating the DOA algorithm with fuzzy c – mean (FCM) and we named the proposed hybrid method (DOA-fuzzy membership), we verified the validity of the proposed method on public database images of palm print. experiment show that the average accuracy rate of the dolphin swarm algorithm (DSO) is (96.8%), while the average accuracy rate of the proposed hybrid algorithm (DSO-SVM) is (97.8%), and the average accuracy of the proposed hybrid algorithm (DSO-fuzzy membership) is (98.1%).

Unsupervised Domain Adaptation of Object Detectors: A Survey.

Recent advances in deep learning have led to the development of accurate and efficient models for various computer vision applications such as classification, segmentation, and detection. However, learning highly accurate models relies on the availability of large-scale annotated datasets. Due to this, model performance drops drastically when evaluated on label-scarce datasets having visually distinct images, termed as domain adaptation problem. There are a plethora of works to adapt classification and segmentation models to label-scarce target dataset through unsupervised domain adaptation. Considering that detection is a fundamental task in computer vision, many recent works have focused on developing novel domain adaptive detection techniques. Here, we describe in detail the domain adaptation problem for detection and present an extensive survey of the various methods. Furthermore, we highlight strategies proposed and the associated shortcomings. Subsequently, we identify multiple aspects of the problem that are most promising for future research. We believe that this survey shall be valuable to the pattern recognition experts working in the fields of computer vision, biometrics, medical imaging, and autonomous navigation by introducing them to the problem, and familiarizing them with the current status of the progress while providing promising directions for future research.

Finger Print Voting System

The field of biometrics, or the identification of people based on physiological or behavioral characteristics [6], has recently received a significant amount of attention in current research as a result of its applicability in the fields of information technology and security. With the increased usage of PIN numbers and passwords in everyday life, the vulnerabilities of these two technologies are becoming more apparent (e.g. password-cracking). Biometric authorization’s strengths are that it requires the user to be present and that it eliminates the hassles of passwords and PIN’s (or can be used in parallel with these for added security). Specifically, online identity verification, ATM machines, and building entrance authorization, are all areas where it is very useful to implement an automatic identification system.

Design of Fingerprint-Based Gender Clustering Using Fuzzy C-Means Algorithm

Biometric systems, with fingerprint recognition as a cornerstone, play a crucial role in identity verification and access control. This paper introduces an innovative approach to gender clustering based on fingerprint data, leveraging the Fuzzy C-Means (FCM) algorithm. The proposed design aims to enhance the precision of gender classification by incorporating the inherent uncertainty in fingerprint features. Through the integration of FCM, which allows soft assignment of fingerprints to gender clusters, the system achieves a nuanced and adaptable classification. The study meticulously explores the design considerations, including the selection of features, data preprocessing, and the configuration of FCM parameters. Additionally, the paper discusses the experimental results, demonstrating the effectiveness of the proposed method in accurately clustering fingerprint data according to gender. The research contributes to the evolving field of biometrics, offering a novel perspective on gender classification that embraces the complexity of fingerprint patterns. The outcomes provide valuable insights for the development of reliable and versatile biometric systems, with potential applications in security, forensics, and personalized identification

A Comparative Study of Cross-Device Finger Vein Recognition Using Classical and Deep Learning Approaches

Finger vein recognition is gaining popularity in the field of biometrics, yet the inter-operability of finger vein patterns has received limited attention. This study aims to fill this gap by introducing a cross-device finger vein dataset and evaluating the performance of finger vein recognition across devices using a classical method, a convolutional neural network, and our proposed patch-based convolutional auto-encoder (CAE). The findings emphasise the importance of standardisation of finger vein recognition, similar to that of fingerprints or irises, crucial for achieving inter-operability. Despite the inherent challenges of cross-device recognition, the proposed CAE architecture in this study demonstrates promising results in finger vein recognition, particularly in the context of cross-device comparisons.

The utility of behavioral biometrics in user authentication and demographic characteristic detection: a scoping review

BackgroundObjective measures of screen time are necessary to better understand the complex relationship between screen time and health outcomes. However, current objective measures of screen time (e.g., passive sensing applications) are limited in identifying the user of the mobile device, a critical limitation in children’s screen time research where devices are often shared across a family. Behavioral biometrics, a technology that uses embedded sensors on modern mobile devices to continuously authenticate users, could be used to address this limitation.ObjectiveThe purpose of this scoping review was to summarize the current state of behavioral biometric authentication and synthesize these findings within the scope of applying behavioral biometric technology to screen time measurement.MethodsWe systematically searched five databases (Web of Science Core Collection, Inspec in Engineering Village, Applied Science & Technology Source, IEEE Xplore, PubMed), with the last search in September of 2022. Eligible studies were on the authentication of the user or the detection of demographic characteristics (age, gender) using built-in sensors on mobile devices (e.g., smartphone, tablet). Studies were required to use the following methods for authentication: motion behavior, touch, keystroke dynamics, and/or behavior profiling. We extracted study characteristics (sample size, age, gender), data collection methods, data stream, model evaluation metrics, and performance of models, and additionally performed a study quality assessment. Summary characteristics were tabulated and compiled in Excel. We synthesized the extracted information using a narrative approach.ResultsOf the 14,179 articles screened, 122 were included in this scoping review. Of the 122 included studies, the most highly used biometric methods were touch gestures (n = 76) and movement (n = 63), with 30 studies using keystroke dynamics and 6 studies using behavior profiling. Of the studies that reported age (47), most were performed exclusively in adult populations (n = 34). The overall study quality was low, with an average score of 5.5/14.ConclusionThe field of behavioral biometrics is limited by the low overall quality of studies. Behavioral biometric technology has the potential to be used in a public health context to address the limitations of current measures of screen time; however, more rigorous research must be performed in child populations first.Systematic review registrationThe protocol has been pre-registered in the Open Science Framework database (https://doi.org/10.17605/OSF.IO/92YCT).

Construction And Performance Evaluation of Big Data Prediction Model Based on Fuzzy Clustering Algorithm in Cloud Computing Environment

In the evolving landscape of biomedical biometrics, where multimodal approaches are increasingly crucial for reliable user authentication, this research presents a comprehensive study. The primary focus is on the construction and performance evaluation of a robust big data prediction model within a cloud computing environment. The advent of big data and cloud computing has revolutionized the field of biomedical biometrics, offering immense potential for advanced data analysis and prediction. This research presents the development and evaluation of a robust prediction model for multimodal biometric data in biomedical applications. The proposed model incorporation of Reliable Discrete Variable Topology (RDVT) into the prediction model. RDVT introduces a topological data structure that enhances data reliability and ensures the integrity of multimodal biometric information. The construction and training of the prediction model are meticulously detailed, encompassing data preprocessing, feature extraction, clustering, classification, and model evaluation. Additionally, the integration of a fuzzy clustering algorithm enhances the model's ability to handle uncertainty and imprecision in biometric data. The advancement of multimodal biometrics in the biomedical field by introducing the Reliable Discrete Variable Topology (RDVT) and a big data prediction model based on a fuzzy clustering algorithm in a cloud computing environment. The model's performance is rigorously assessed through extensive experimentation, including accuracy, precision, recall, and F1-score measurements.

Multilingual Speaker Recognition using Mel-frequency Cepstral Coefficients and Gaussian Mixture Model

Introduction: People can recognize a speaker with the help of their voice via mobile or digital devices. Method: To obtain this congenital human being ability, authentication techniques based on speaker biometrics like automated speaker recognition (ASR) have been proposed. An ASR identifies speakers by speech signals analysis and salient feature extraction from their voices. Result: This will become an important part of recent research in the voice biometrics field. This paper proposes multilingual speaker recognition with the help of MFCC as feature extraction and GMM as classification techniques using various available datasets such as TIMIT, librespeech, etc. Conclusion: The results achieved from the given datasets enhance the recognition rate of 70.98% with MFCC.

From understanding to justifying: Computational reliabilism for AI-based forensic evidence evaluation

Techniques from artificial intelligence (AI) can be used in forensic evidence evaluation and are currently applied in biometric fields. However, it is generally not possible to fully understand how and why these algorithms reach their conclusions. Whether and how we should include such ‘black box’ algorithms in this crucial part of the criminal law system is an open question that has not only scientific but also ethical, legal, and philosophical angles. Ideally, the question should be debated by people with diverse backgrounds.Here, we present a view on the question from the philosophy of science angle: computational reliabilism (CR). CR posits that we are justified in believing the output of an AI system, if we have grounds for believing its reliability. Under CR, these grounds are classified into ‘reliability indicators’ of three types: technical, scientific, and societal. This framework enables debates on the suitability of AI methods for forensic evidence evaluation that take a wider view than explainability and validation.We argue that we are justified in believing the AI's output for forensic comparison of voices and forensic comparison of faces. Technical indicators include the validation of the AI algorithm in itself, validation of its application in the forensic setting, and case-based validation. Scientific indicators include the simple notion that we know faces and voices contain identifying information along with operationalizing well-established metrics and forensic practices. Societal indicators are the emerging scientific consensus on the use of these methods, as well as their application and interpretation by well-educated and certified practitioners. We expect expert witnesses to rely more on technical indicators to be justified in believing AIsystems, and triers-of-fact to rely more on societal indicators to believe the expert witness supported by the AIsystem.

Design And Build Door Security Using Fingerprint

Today's technology has undergone many developments, with the development of these technologies can be put to good use. One technology that is currently being developed is in the field of security. Especially in the field of Biometrics because there are two functions, namely identification and verification. Biometrics have characteristics that are not lost, cannot be forgotten, and are not easily faked. Its existence is very close to humans, and one another is not the same so that uniqueness and security can be guaranteed. One of the biometrics that is easy to use is fingerprint, because this fingerprint pattern has high security and the fingerprint pattern is also easy to use. In increasing security, fingerprints can be applied as house door locks, because everyone's fingerprints are different so security will increase and it is not easy to access. The purpose of this tool is made so that it can be applied in the community, with this tool homeowners do not need to carry a key and only require fingerprints, so as to reduce the risk of crime that is rife in the community.

Enhanced face morphing attack detection using error-level analysis and efficient selective kernel network

Face morphing attack detection is a research hotspot in the field of biometrics. However, existing methods cannot balance accuracy and complexity well due to their inability to effectively capture crucial feature distinctions. To solve this problem, this paper proposes a detection method based on error-level analysis and an efficient selective kernel network. Specifically, the proposed method performs error-level analysis on the R, G, and B color channels to accurately capture crucial feature differences and enhance face detection accuracy. Meanwhile, an efficient selective kernel network is designed with further improvements and optimizations. This network can adaptively adjust the size of the receptive field, thereby providing higher classification accuracy without significantly increasing the number of parameters. Besides, the shallow feature enhancement module and feature fusion module are designed to improve the model's detection performance. Finally, the proposed method is evaluated on standard databases and compared to existing detection methods. The results demonstrate that the proposed method achieves superior detection performance to existing methods.

DT2F-TLNet: A novel text-independent writer identification and verification model using a combination of deep type-2 fuzzy architecture and Transfer Learning networks based on handwriting data

Identifying and verifying the identity of people based on scanned images of handwritten documents is an applicable biometric modality with applications in forensic and historic document investigation, and it is an important study area within the research field of behavioral biometrics. Despite this, there are few studies in this field. Furthermore, there are very few standard datasets for identifying and verify handwritten documents. Also, handwritten documents lose their character during time because of ink spread and drying. Therefore, it is necessary to provide a method that can identify and verify handwritten documents under various uncertainties. In this study, a text-independent writer identification and verification model in offline state under different experimental conditions is developed using a combination of Deep Type-2 Fuzzy architecture and Transfer Learning networks (DT2F-TLNet). So, a right-to-left dataset has been collected. The proposed DT2F-TLNet model is validated using both the designed dataset and other benchmark datasets. The proposed model is distinguished by the fact that it is developed to be independent of the textual content of the handwritten cases and can be used for various languages. The study's findings show that the developed DT2F-TLNet model can learn properties from heterogeneous handwriting data and results in higher accuracy than other comparable approaches.

Anthropometric Study of the Cephalic Index of Anambra State Students in Madonna University Nigeria

Background: Cephalometry is a subfield of anthropometry that involves the estimation of the cephalic index. The cephalic index is a significant metric used to ascertain the race and sex of an unidentified individual. Materials and Methods: This study was descriptive and cross-sectional and was conducted on Anambra State students at Madonna University. Elele campus, Rivers State, aged 16–24 years. The cephalic index was determined by applying the following formula: the maximum breadth of the head divided by the maximum length of the head, multiplied by 100. Hundred subjects, comprising 150 males and 150 females from Anambra State at Madonna University, were measured. Anthropometrical parameters measured were maximum head breadth and maximum head length. Results and Discussion: The analysis shows that there is no significant difference in the age groups with the cephalic indices of males and females. The prevalence of hyperbrachycephaly is significantly higher in males and females, while dolicocephaly is observed infrequently. Conclusion: This study shows that the males and females showed no differences on the basis of the cephalic index. It also reveals that the students in this study share similarities with Urhobo males and females based on their head types. The findings of this study will hold significant implications for the fields of forensics, medicine, and biometrics.

Performance Evolution Ear Biometrics Based on Features from Accelerated Segment Test

In the field of image processing, feature extraction is very important. Various image pre-processing procedures, including scaling, downscaling, resizing, normalization, etc., are applied to the sampled image before features are acquired. Features that would be relevant for image classification and recognition are then extracted using feature extraction methods. Many problems arose in biometric methods (fingerprint, iris, face), which led to the search for new biometrics to identify a person, avoid disease obstacles, continuous change with age, and others. The aim of this work is to present an ear system based on the power extraction of biometric field features of the ear. The proposed system will extract the robust features using the FAST method. This system reduces sprint time while maintaining its accuracy. This is done in two stages, the first stage, is the application of several pre-processing techniques which included the process of a) conversion to grayscale, b) binary filter, c) image brightness, histogram equalization, and image noise reduction. In the second stage, the method of transforming the fixed attribute variable FAST is used to determine the extraction of the force field feature. Where 70 % images were used for the purpose of training and 30 %for the purpose of testing. The accuracy of these figures was tested, reaching 95%, and therefore they can be adopted in the classification process in the future by choosing any algorithm.