Biometric Identification Technology Research Articles

A Novel Technique for Handwritten Signature Recognition

Handwritten signature recognition (HSR) is a critical component of biometric systems, widely used for securing financial transactions and identity verification. However, the variability of handwritten signatures, influenced by individual writing styles, inconsistencies, and environmental factors, presents significant challenges for recognition systems. Despite these obstacles, signatures remain a reliable and popular biometric trait. This paper introduces a novel deep learning approach utilizing a convolutional neural network (CNN) architecture specifically designed for HSR. The proposed method was validated using two prominent datasets, MCYT-75 and GPDS-300, with detailed descriptions of the CNN structure. Experiments, conducted on a personal computer equipped with an NVIDIA Quadro M1200 GPU, an Intel i7 processor, and 32 GB of RAM, demonstrated the model’s exceptional performance, achieving validation accuracies of 99.60% on the MCYT-75 dataset and 99.80% on the GPDS-300 dataset. These results reflect the model’s robustness and minimized error rates, outperforming existing techniques and underscoring the effectiveness of deep learning for signature recognition. This study highlights the proposed model's potential for real-world applications and paves the way for further advancements in biometric authentication technologies.

Biometric Technology Based on Wireless Sensing: Principles, Applications, and Challenges

With the rapid advancement of computer technology, image processing, and artificial intelligence, biometric identification technology has seen widespread application, gradually permeating areas such as national security, public security, and home security. However, traditional biometric technologies exhibit certain limitations. In contrast, biometric identification based on wireless sensing offers distinct advantages, including non-contact operation and strong concealment, making it a promising alternative in various security applications. This paper provides a comprehensive overview of the history and current state of biometric technology, alongside the development background of wireless sensing technology. It details the principles of wireless sensing-based biometric identification, covering essential characteristics of wireless signals, and related technologies such as RFID, Wi-Fi, Bluetooth, and millimeter wave technology, as well as relevant signal processing algorithms. Furthermore, the paper analyzes the application of this technology in areas like human posture and motion recognition and physiological feature recognition, supported by practical case studies. Finally, it addresses the environmental dependencies, data privacy, and security concerns associated with this technology, while offering insights into future development directions.

Intelligent Fingerprint Recognition System Using Machine Learning

Secure authentication relies heavily on fingerprint recognition systems; however, conventional techniques are hindered by differences in image quality and possible security breaches. This study suggests a novel method for improving fingerprint recognition accuracy and robustness that makes use of machine learning techniques. By utilizing convolutional neural networks' (CNNs') capacity to deduce intricate patterns and representations from fingerprint photos, we investigate the use of CNNs for feature extraction and matching. Comparing our experimental results against conventional approaches, we find considerable improvements in accuracy and false acceptance rates on benchmark datasets. By advancing biometric authentication technologies, this research helps to improve security and dependability for a range of applications in law enforcement, access control, and personal identification.

EEG Data Augmentation Method for Identity Recognition Based on Spatial–Temporal Generating Adversarial Network

Traditional identity recognition methods are facing significant security challenges due to their vulnerability to leakage and forgery. Brainprint recognition, a novel biometric identification technology leveraging EEG signals, has emerged as a promising alternative owing to its advantages such as resistance to coercion, non-forgeability, and revocability. Nevertheless, the scarcity of high-quality electroencephalogram (EEG) data limits the performance of brainprint recognition systems, necessitating the use of shallow models that may not perform optimally in real-world scenarios. Data augmentation has been demonstrated as an effective solution to address this issue. However, EEG data encompass diverse features, including temporal, frequency, and spatial components, posing a crucial challenge in preserving these features during augmentation. This paper proposes an end-to-end EEG data augmentation method based on a spatial–temporal generative adversarial network (STGAN) framework. Within the discriminator, a temporal feature encoder and a spatial feature encoder were parallelly devised. These encoders effectively captured global dependencies across channels and time of EEG data, respectively, leveraging a self-attention mechanism. This approach enhances the data generation capabilities of the GAN, thereby improving the quality and diversity of the augmented EEG data. The identity recognition experiments were conducted on the BCI-IV2A dataset, and Fréchet inception distance (FID) was employed to evaluate data quality. The proposed method was validated across three deep learning models: EEGNET, ShallowConvNet, and DeepConvNet. Experimental results indicated that data generated by STGAN outperform DCGAN and RGAN in terms of data quality, and the identity recognition accuracies on the three networks were improved by 2.49%, 2.59% and 1.14%, respectively.

Enhancing Facial Identification Systems with YOLOv8: A Cutting-Edge Approach

Face recognition and identification have recently become the most widely employed biometric authentication technologies, especially for access to persons and other security purposes. It represents one of the most significant pattern recognition technologies that uses characteristics included in facial images or videos to detect the identity of individuals. However, most of the traditional facial algorithms have faced limitations in identification and verification accuracy. As a result, this paper presents a sophisticated system for face identification adopting a novel algorithm of deep learning, namely, You Only Look Once version 8 (YOLOv8). This system can detect the face identity of different individuals with different positions with high accuracy. The YOLOv8 model has been trained for several target face images classified as training and validation images of 1190 and 255, respectively. The experimental results show a significant improvement in face identification accuracy of 99% of mean average precision, which outperforms many state-of-the-art face identification techniques.

Simple Siamese Model with Long Short-Term Memory for User Authentication with Field-Programmable Gate Arrays

Recent studies have focused on user authentication methods that use biometric signals such as electrocardiogram (ECG) and photo-plethysmography (PPG). These authentication technologies have advantages such as ease of acquisition, strong security, and the capability for non-aware authentication. This study addresses user authentication using electromyogram (EMG) signals, which are particularly easy to acquire, can be fabricated in a wearable form such as a wristwatch, and are readily expandable with technologies such as human–machine interface. However, despite their potential, they often exhibit lower accuracy (approximately 90%) than traditional methods such as fingerprint recognition. Accuracy can be improved using complex algorithms and multiple biometric authentication technologies; however, complex algorithms use substantial hardware resources, making their application to wearable devices difficult. In this study, a simple Siamese model with long short-term memory (LSTM) (SSiamese-LSTM) is proposed to achieve a high accuracy of over 99% with limited resources suitable for wearable devices. The hardware implementation was accomplished using field-programmable gate arrays (FPGAs). In terms of accuracy, EMG measurement results from Chosun University were used, and data from 100 individuals were employed for verification. The proposed digital logic will be integrated with an EMG sensor in the form of a watch that can be used for user authentication.

The Future Risk of Biometric Data Theft in Cybersecurity

The aim of this paper is to analyze the technical and engineering issues surrounding the future risk of biometric data theft in cyber security. Biometric data, such as fingerprints, facial recognition, and voice recognition, are increasingly being used as a means of authentication in various industries. However, the collection, storage, and transmission of biometric data present unique security challenges, as this data is highly personal and cannot be changed if compromised. In this paper, we will examine the vulnerabilities in biometric authentication technologies, the risks associated with the use of biometrics in various industries, and the measures that can be taken to mitigate these risks.

AI Powered Contactless Fingerprint Recognition

This comprehensive review delves into the realm of AI-powered contactless fingerprint recognition. We trace its evolution from traditional methods to modern contactless approaches, highlighting the pivotal role of AI and machine learning. Key topics include the principles of contactless fingerprint data acquisition, challenges like environmental variations, and privacy concerns. We examine the state-of-the-art AI techniques such as deep learning and convolutional neural networks, showcasing how they enhance accuracy and robustness in contactless fingerprint recognition. The paper also explores diverse applications, spanning security, access control, and healthcare, while addressing societal impacts and ethical considerations. Furthermore, we provide insights into ongoing research and future prospects, including potential improvements, emerging trends, and multi-modal authentication possibilities. This concise review serves as an essential resource for researchers, practitioners, and policymakers interested in the intersection of AI and biometric authentication technologies. Keywords: - AI-powered, Contactless fingerprint recognition, Biometrics, Artificial intelligence, Machine learning, Data acquisition, Deep learning, Convolutional neural networks

Meticulously designed red emission carbon dots as efficient and stable luminescent species for rapid latent fingerprint recognition and light emitting diodes

The preparation of carbon dots (CDs) emitting long wavelength has attracted more attentions due to their unique advantages in biological and optoelectronic fields, including the wide absorption, long PL lifetime and deep-tissue penetration. Herein, we prepare the nitrogen and sulfur co-doped red emission carbon dots (R-CDs) from the 2,4-diaminodiphenylamine (DDA) and thiourea via a solvothermal reaction, which exhibit reliable red emission at 613 nm and possess a high quantum yield (QY) of 34 %. Meanwhile, the structural analysis and theoretical calculation reveal that the sulfur doping from thiourea increases the nitrogen and oxygen content of CDs, leading to the red emission observed in R-CDs. Subsequently, we design an integrated fingerprints recognition system based on the R-CDs phosphors for the imaging of latent fingerprints (LFPs) and fast LFPs recognition, expanding the application of biometric identification and comparison technology based on fluorescence. Finally, we successfully apply the R-CDs into red and white light-emitting diodes, improving plant growth efficiency. As a result, this work provides a new in-depth insight of red emission CDs and expands the application in latent fingerprint recognition and light-emitting diodes.

A Degraded Finger Vein Image Recovery and Enhancement Algorithm Based on Atmospheric Scattering Theory.

With the development of biometric identification technology, finger vein identification has received more and more widespread attention for its security, efficiency, and stability. However, because of the performance of the current standard finger vein image acquisition device and the complex internal organization of the finger, the acquired images are often heavily degraded and have lost their texture characteristics. This makes the topology of the finger veins inconspicuous or even difficult to distinguish, greatly affecting the identification accuracy. Therefore, this paper proposes a finger vein image recovery and enhancement algorithm using atmospheric scattering theory. Firstly, to normalize the local over-bright and over-dark regions of finger vein images within a certain threshold, the Gamma transform method is improved in this paper to correct and measure the gray value of a given image. Then, we reconstruct the image based on atmospheric scattering theory and design a pixel mutation filter to segment the venous and non-venous contact zones. Finally, the degraded finger vein images are recovered and enhanced by global image gray value normalization. Experiments on SDUMLA-HMT and ZJ-UVM datasets show that our proposed method effectively achieves the recovery and enhancement of degraded finger vein images. The image restoration and enhancement algorithm proposed in this paper performs well in finger vein recognition using traditional methods, machine learning, and deep learning. The recognition accuracy of the processed image is improved by more than 10% compared to the original image.

Finger Vein Identification Based on Large Kernel Convolution and Attention Mechanism.

FV (finger vein) identification is a biometric identification technology that extracts the features of FV images for identity authentication. To address the limitations of CNN-based FV identification, particularly the challenge of small receptive fields and difficulty in capturing long-range dependencies, an FV identification method named Let-Net (large kernel and attention mechanism network) was introduced, which combines local and global information. Firstly, Let-Net employs large kernels to capture a broader spectrum of spatial contextual information, utilizing deep convolution in conjunction with residual connections to curtail the volume of model parameters. Subsequently, an integrated attention mechanism is applied to augment information flow within the channel and spatial dimensions, effectively modeling global information for the extraction of crucial FV features. The experimental results on nine public datasets show that Let-Net has excellent identification performance, and the EER and accuracy rate on the FV_USM dataset can reach 0.04% and 99.77%. The parameter number and FLOPs of Let-Net are only 0.89M and 0.25G, which means that the time cost of training and reasoning of the model is low, and it is easier to deploy and integrate into various applications.

A Framework for Saudi Uniform Gait Recognition Based on Kinect Skeletal Tracking

Due to its robustness in challenge variation in gait recognition domain, gait recognition is considered as one of the popular remote biometric identification technologies. Gait data may be reliably collected from a long distance and is difficult to conceal or copy. This article investigated the use of Kinect to identify gait in Saudis wearing loose-fitting apparel that conceals the majority of body shapes, such as thobes or abayas. Because these clothes cover the majority of the joints, it is difficult to determine gait. This research uses the Kinect sensor version 2 as a technique to choose the top three joints with the greatest identification results, which are then used for gait recognition. The Y coordinates of joints are used as features, which are then put into the K Nearest Neighbor classification algorithm. Several experiments were carried out, and the results demonstrate that the system has a promising identification rate and is capable of achieving a high recognition performance when identifying or recognizing a person while also dealing with obstacles associated with the types of loose clothing worn by the participants.

Test

Due to its robustness in challenge variation in gait recognition domain, gait recognition is considered as one of the popular remote biometric identification technologies. Gait data may be reliably collected from a long distance and is difficult to conceal or copy. This article investigated the use of Kinect to identify gait in Saudis wearing loose-fitting apparel that conceals the majority of body shapes, such as thobes or abayas. Because these clothes cover the majority of the joints, it is difficult to determine gait. This research uses the Kinect sensor version 2 as a technique to choose the top three joints with the greatest identification results, which are then used for gait recognition. The Y coordinates of joints are used as features, which are then put into the K Nearest Neighbor classification algorithm. Several experiments were carried out, and the results demonstrate that the system has a promising identification rate and is capable of achieving a high recognition performance when identifying or recognizing a person while also dealing with obstacles associated with the types of loose clothing worn by the participants.

The role of biometric identification on the quality of life of older adults

The use of biometric identification technology has become increasingly prevalent in modern society, with potential benefits for various populations. However, despite the widespread adoption of biometric identification, there is still a significant gap in research on the benefits that older adults may derive from this technology and how it may improve their quality of life. This study draws on a mixed methodology and the flow theory to understand how biometric identification improves the quality of life of older adults. The findings show that older adults obtain socio-economic impacts, social inclusion, improved access to healthcare and access to information that serves their health, psychological, emotional and mental needs through the use of biometric identification. Drawing on artificial neural network, we ranked the derived benefits and used partial least square-structural equation modelling (PLS-SEM) to investigate how these benefits translate to the quality of life of older adults. The results showed that the most significant biometric factor that promotes the quality of life of older adults is improved healthcare access, followed by information access and socio-economic development. The PLS-SEM results show that social inclusion is essential but does not improve the quality of life of older adults. The findings of this study offer valuable information for policy-makers, technology developers and practitioners working to improve the lives of older adults.

The impact of digitalization on the Kazakhstan banking services market

Main problem: In recent years, the world has seen the widespread impact and implementation of digitalization in all areas of activity. The financial sector is increasingly feeling the impact of this trend. Today, banks are the leaders in this sector in the use of digital innovations. In connection with current events in the world, banks needed to resort to transformation of their products. Products and services such as Internet banking, chat bots, contactless payment systems, biometric identification technologies, etc. appear and are constantly updated. The article discusses the main trends in the development of digital banking products and their impact on the performance of banks. Purpose: is to study and evaluate new digital banking products and their impact on the key performance indicators of the banking sector. Results and their significance: The directions and trends in the development of new digital banking products were studied and the performance indicators of the banking sector of the Republic of Kazakhstan were compared.

Biometric m-payment systems: A multi-analytical approach to determining use intention

Although mobile payment systems offer countless advantages, they do present certain drawbacks, mainly associated with security and privacy concerns. The inclusion of biometric authentication technologies seeks to minimise such drawbacks. The aim of this article is to examine the effect of key antecedents of the Unified Theory of Acceptance and Use of Technology 2 (UTAUT2) and perceived risk on the intention to use a mobile payment system featuring biometric identification. A new hybrid analytical approach is taken. A sample of more than 2500 smartphone users was obtained through an online panel-based survey. Two techniques were used: first, structural equation modelling (PLS-SEM) was conducted to determine which variables had a significant influence on the adoption of the mobile payment system, and second, an artificial neural network (ANN) model was used, taking a deep learning approach, to rank the relative influence of significant predictors of use intention obtained via PLS-SEM. The study found that the most significant variables affecting use intention were performance expectancy, effort expectancy, facilitating conditions, hedonic motivation and risk. In contrast, subjective norms, price value and habit were found to be weak predictors of use intention. The results of the ANN analysis confirmed almost all SEM findings but yielded a slightly different order of influence among the least significant predictors. A review of the extant scientific literature revealed a paucity of published studies dealing with the adoption and use of mobile payment systems featuring biometric identification. The conclusions and managerial implications point to new business opportunities that can be exploited by firms through the use of this technology.

Innovations in the Security of Banking Operations

The contemporary changing technological environment forces all economic units to go through a digital transformation. The banking industry is in the epicenter of this change. Credit institutions seek to adapt a business model that is increasingly customer-oriented, providing new services with greater transparency and levels of security. The growing demand for more effective protection against fraud, phishing attacks, theft of identities and ensuring better levels of security in a timely manner is increasingly central topic in retail banking. The issue of security, as in the territory of bank branches, ATM-devices, as well as in the provision of online and mobile services, arouses the interest of credit institutions to the use of biometric identification technology. Biometric technologies are becoming an indispensable part of the means of personal verification and secure identification activities in banking institutions.

Random hand gesture authentication via efficient Temporal Segment Set Network

Biometric authentication technologies are rapidly gaining popularity, and hand gestures are emerging as a promising biometric trait due to their rich physiological and behavioral characteristics. Hand gesture authentication can be categorized as defined hand gesture authentication and random hand gesture authentication. Unlike defined hand gesture authentication, random hand gesture authentication is not constrained to specific hand gesture types, allowing users to perform hand gestures randomly during enrollment and verification, thus more flexible and friendly. However, in random hand gesture authentication, the model needs to extract more generalized physiological and behavioral features from different viewpoints and positions without gesture templates, which is more challenging. In this paper, we present a novel efficient Temporal-Segment-Set-Network (TS2N) that directly extracts both behavioral and physiological features from a single RGB video to further enhance the performance of random hand gesture authentication. Our method adopts a new motion pseudo-modality and leverages a set-based representation to capture behavioral characteristics online. Additionally, we propose a channel-spatial attention mechanism, Contextual Squeeze-and-Excitation Network (CoSEN), to better abstract and understand physiological characteristics by explicitly modeling the channel-spatial interdependence, thereby adaptively recalibrating channel-specific and spatial-specific responses. Extensive experiments on the largest public hand gesture authentication dataset SCUT-DHGA demonstrate TS2N’s superiority against 21 state-of-the-art models in terms of EER (5.707% for full version and 6.664% for lite version) and computational cost (98.9022G for full version and 46.3741G for lite version). The code is available at https://github.com/SCUT-BIP-Lab/TS2N.

A robust brain pattern for brain-based authentication methods using deep breath

Security authentication involves the process of verifying a person's identity. Authentication technology has played a crucial role in data security for many years. However, existing typical biometric authentication technologies exhibit limitations related to usability, time efficiency, and notably, the long-term viability of the method. Recent technological advancements have led to the development of specific devices capable of reproducing human biometrics due to their visibility and tactile nature. Consequently, there is a demand for a new biometric method to address the limitations of current authentication systems. Human brain signals have been utilized in various Brain-Computer Interface (BCI) applications. Nevertheless, this approach also faces challenges related to usability, time efficiency, and most importantly, the stability of the method over time. Studies reveal that the stability of brain patterns poses a significant challenge in EEG-based authentication techniques. Stability refers to the capacity to withstand changes or disruptions, while permanency implies a lasting and unchanging state. Notably, stability can be temporary and subject to fluctuations, whereas permanency suggests a more enduring condition. Research demonstrates that utilizing alpha brainwaves is a superior option for authentication compared to other brainwave types. Many brain states lack stability in different situations. Interestingly, deep breathing can enhance alpha waves irrespective of the brain's current state. To explore the potential of utilizing deep breathing as a security pattern for authentication purposes, an experiment was conducted to investigate its effects on brain activity and its role in enhancing alpha brainwaves. By focusing on bolstering the permanency of brain patterns, our aim is to address the challenges associated with stability in EEG-based authentication techniques. The experimental results exhibited a high success rate of 91 % and 90 % for Support Vector Machine and Neural Network classifiers, respectively. These results suggest that deep breathing not only enhances permanency but could also serve as a suitable option for a brainwave-based authentication method.

Finger Print Sensing Vehicle Starter

The fingerprint vehicle starter project aims to increase the security of vehicles by using biometric authentication technology. Biometrics system can be used as a good and effective security option. An important and very reliable human identification method is fingerprint identification. Vehicle safety has become a serious problem as the frequency of crime has increased. Vehicle keys are a big concern these days since they are easily forgotten or lost when carried. At start, this technology lets the customer to authenticate by scanning their unique fingerprint. The system uses a fingerprint scanner to identify the authorized user of the vehicle, allowing them to start the engine. This project is designed to prevent car theft and improve user convenience, as drivers will not need to carry keys with them. The system allows multiple users to register as authorized users. When into monitoring mode, the system checks for users to scan. On scanning, the system checks if user is authorized user. The system is implemented using an Arduino microcontroller and a fingerprint sensor module, which communicate with the vehicle's ignition system. The project's success is evaluated based on its accuracy in identifying the authorized user and its reliability in preventing unauthorized access to the vehicle. This project has the potential to significantly improve vehicle security and enhance user experience. This provides safe and worry-free way to begin the engine or automobile. The fingerprint vehicle starter project aims to increase the security of vehicles by using biometric authentication technology. Biometrics system can be used as a good and effective security option. An important and very reliable human identification method is fingerprint Identification.