Face Verification Research Articles

A Review of Traditional Methods and Deep Learning for Face Recognition

Face recognition technology is a key research direction in artificial intelligence and computer vision. It first originated in the 1960s, when Bledsoe et al. proposed and studied computer programming based on face recognition. It is divided into three steps: face detection, feature extraction, and face verification. This paper briefly introduces the wide application of face recognition in various fields such as vulnerable groups, analyses its characteristics and progress from the viewpoints of traditional learning and deep learning, and focuses on the methods based on face feature extraction (including geometric features, texture features, local features, etc.). From the previous studies appear some problems connected to environmental changes, such as light change, facial occlusion, posture and privacy leakage, etc. This paper will give the possible reasons for these problems and give the possible development direction of the future by exploring the current face recognition technology to provide a reference for the related research of face recognition technology.

Parent GAN: image generation model for creating parent’s images using children’s images

AbstractIn the past decade, several applications have emerged in predicting children’s images using their parents via Generative Adversarial Networks (GANs). However, no one has tackled the problem of predicting one of the parents using the other parent and their children or answering the question of the possibility of deducing the parent images from the children and other parent image features. It could be used in parental identification cases. Moreover, it could help children who don’t know one of their parents to have a visual representation of their images. To perform this task, several obstacles were overcome, like the small number of parent pairs in the dataset and stabilizing the GANs to produce good-looking images. The proposed method depends on dual GAN architecture in addition to adaptive instance normalization layers and introducing a triple loss function to stabilize further and improve the resulting images. The results were proven using a kinship verification model, a face verification model, and other well-known evaluation metrics, which showed that the generated parent images are of decent quality compared to real parents’ images with affordable computational hardware. As a result, a novel method is developed that could produce unknown parent images.

Hybrid-Blockchain-Based Electronic Voting Machine System Embedded with Deepface, Sharding, and Post-Quantum Techniques

The integrity of democratic processes relies on secure and reliable election systems, yet achieving this reliability is challenging. This paper introduces the Post-Quantum Secured Multiparty Computed Hierarchical Authoritative Consensus Blockchain (PQMPCHAC-Bchain), a novel e-voting system designed to overcome the limitations of current Biometric Electronic Voting Machine (EVM) systems, which suffer from trust issues due to closed-source designs, cyber vulnerabilities, and regulatory concerns. Our primary objective is to develop a robust, scalable, and secure e-voting framework that enhances transparency and trust in electoral outcomes. Key contributions include integrating hierarchical authorization and access control with a novel consensus mechanism for proper electoral governance. We implement blockchain sharding techniques to improve scalability and propose a multiparty computed token generation system to prevent fraudulent voting and secure voter privacy. Post-quantum cryptography is incorporated to safeguard against potential quantum computing threats, future-proofing the system. Additionally, we enhance authentication through a deep learning-based face verification model for biometric validation. Our performance analysis indicates that the PQMPCHAC-Bchain e-voting system offers a promising solution for secure elections. By addressing critical aspects of security, scalability, and trust, our proposed system aims to advance the field of electronic voting. This research contributes to ongoing efforts to strengthen the integrity of democratic processes through technological innovation.

Subjective performance assessment protocol for visual explanations-based face verification explainability

The integration of Face Verification (FV) systems into multiple critical moments of daily life has become increasingly prevalent, raising concerns regarding the transparency and reliability of these systems. Consequently, there is a growing need for FV explainability tools to provide insights into the behavior of these systems. FV explainability tools that generate visual explanations, e.g., saliency maps, heatmaps, contour-based visualization maps, and face segmentation maps, show promise in enhancing FV transparency by highlighting the contributions of different face regions to the FV decision-making process. However, evaluating the performance of such explainability tools remains challenging due to the lack of standardized assessment metrics and protocols. In this context, this paper proposes a subjective performance assessment protocol for evaluating the explainability performance of visual explanation-based FV explainability tools through pairwise comparisons of their explanation outputs. The proposed protocol encompasses a set of key specifications designed to efficiently collect the subjects’ preferences and estimate explainability performance scores, facilitating the relative assessment of the explainability tools. This protocol aims to address the current gap in evaluating the effectiveness of visual explanation-based FV explainability tools, providing a structured approach for assessing their performance and comparing with alternative tools. The proposed protocol is exercised and validated through an experiment conducted using two distinct heatmap-based FV explainability tools, notably FV-RISE and CorrRISE, taken as examples of visual explanation-based explainability tools, considering the various types of FV decisions, i.e., True Acceptance (TA), False Acceptance (FA), True Rejection (TR), and False Rejection (FR). A group of subjects with variety in age, gender, and ethnicity was tasked to express their preferences regarding the heatmap-based explanations generated by the two selected explainability tools. The subject preferences were collected and statistically processed to derive quantifiable scores, expressing the relative explainability performance of the assessed tools. The experimental results revealed that both assessed explainability tools exhibit comparable explainability performance for FA, TR, and FR decisions with CorrRISE performing slightly better than FV-RISE for TA decisions.

Comprehensive comparison between vision transformers and convolutional neural networks for face recognition tasks

This paper presents a comprehensive comparison between Vision Transformers and Convolutional Neural Networks for face recognition related tasks, including extensive experiments on the tasks of face identification and verification. Our study focuses on six state-of-the-art models: EfficientNet, Inception, MobileNet, ResNet, VGG, and Vision Transformers. Our evaluation of these models is based on five diverse datasets: Labeled Faces in the Wild, Real World Occluded Faces, Surveillance Cameras Face, UPM-GTI-Face, and VGG Face 2. These datasets present unique challenges regarding people diversity, distance from the camera, and face occlusions such as those produced by masks and glasses. Our contribution to the field includes a deep analysis of the experimental results, including a thorough examination of the training and evaluation process, as well as the software and hardware configurations used. Our results show that Vision Transformers outperform Convolutional Neural Networks in terms of accuracy and robustness against distance and occlusions for face recognition related tasks, while also presenting a smaller memory footprint and an impressive inference speed, rivaling even the fastest Convolutional Neural Networks. In conclusion, our study provides valuable insights into the performance of Vision Transformers for face recognition related tasks and highlights the potential of these models as a more efficient solution than Convolutional Neural Networks.

Analisis Efektivitas Penggunaan E-Wallet dalam Pembayaran Digital Bagi Mahasiswa Program Studi Manajemen Bisnis Syariah UMSU

This research aims to determine the motives, impacts and experiences of FAI UMSU Sharia Business Management students in using E-Wallets for Digital Payments. Based on the results of observations and interviews based on this title, researchers found that there are many factors that influence students to use E-Wallets for digital payments, including: promos, ease of use, service features, security of the e-wallet digital product. Almost all provinces in Indonesia have touched digital e-wallet applications (OVO, Gopay, Link Aja, Flip, DANA, Shopeepay and so on). E-wallet users are increasing rapidly and are widely used by various groups, including students. Although e-wallet service providers offer a variety of products, not all of them are used by students. E-wallet is a digital payment transaction method that includes features such as balance top-ups, bill payments, inter-bank transfers, money withdrawals, and so on. The use of digital e-wallets is still dominated by payments for online transportation transactions, purchases via e-commerce, and food and beverage delivery services. Security is also one of the factors that makes students interested and interested in using E-Wallet. Meanwhile, the existence of a security verification system makes consumers feel protected regarding the security of their personal data information when using E-Wallet. One of them is by launching fingerprint and facial verification features to validate every transaction.

Residual feature decomposition and multi-task learning-based variation-invariant face recognition

AbstractFacial identity is subject to two primary natural variations: time-dependent (TD) factors such as age, and time-independent (TID) factors including sex and race. This study aims to address a broader problem known as variation-invariant face recognition (VIFR) by exploring the question: “How can identity preservation be maximized in the presence of TD and TID variations?" While existing state-of-the-art (SOTA) methods focus on either age-invariant or race and sex-invariant FR, our approach introduces the first novel deep learning architecture utilizing multi-task learning to tackle VIFR, termed “multi-task learning-based variation-invariant face recognition (MTLVIFR)." We redefine FR by incorporating both TD and TID, decomposing faces into age (TD) and residual features (TID: sex, race, and identity). MTLVIFR outperforms existing methods by 2% in LFW and CALFW benchmarks, 1% in CALFW, and 5% in AgeDB (20 years of protocol) in terms of face verification score. Moreover, it achieves higher face identification scores compared to all SOTA methods. Open source code.

Secure Facial Verification: A hybrid model for detecting Spoof Attacks with ResNet50-DenseNet121

Secure Facial Verification: A hybrid model for detecting Spoof Attacks with ResNet50-DenseNet121

Mobilefacenet-Based Facial Recognition System for Contactless Access Control

Conventional access control systems require physical contact, such as pressing buttons, using fingerprints, or employing radio-frequency identification (RFID). These interactions increase the risk of transmitting diseases like COVID-19 through surface contact. To mitigate this risk, a contactless identification method becomes imperative. Hence, this study proposes an adaptive and seamless dual-mode mobile facial recognition-based access control system. Specifically, the proposed system uses a convolutional neural network (CNN) algorithm (MobileFaceNet) to develop high-precision facial verification on mobile devices with a dual-mode (real-time and offline) facial recognition system. The system is implemented on Raspberry Pi, running an Android Operating System equipped with camera functionality. The system instantaneously operates by detecting human faces, compares the faces with a pre-existing database, and grants access to successful matches. The system underwent preliminary testing on an Android 9 device with an 8-megapixel camera. Faces were detected and recognised in a record time (within seconds), showcasing commendable accuracy. The system achieved a recognition accuracy of 95% under varied lighting conditions and distances. The proposed system can be seamlessly integrated with electronic doors, ensuring optimal access control for smart homes and restricted facilities.Keywords: Access control, convolutional neural network, face recognition, firebase, mobilefacenet

Robust Hybrid Texture Descriptor (HTD) and a parallel score based fusion for face verification and liveness detection system

Robust Hybrid Texture Descriptor (HTD) and a parallel score based fusion for face verification and liveness detection system

Age and Gender voice Recognition using Deep learning

Since the advent of social media, there has been an increased interest in automatic age and gender classification through facial images. So, the process of age and gender classification is a crucial stage for many applications such as face verification, aging analysis, ad targeting and targeting of interest groups. Yet most age and gender classification systems still have some problems in real-world applications. This work involves an approach to age and gender classification using multiple convolutional neural networks (CNN). The proposed method has 5 phases as follows: face detection, remove background, face alignment, multiple CNN and voting systems. The multiple CNN model consists of three different CNN in structure and depth; the goal of this difference It is to extract various features for each network. Each network is trained separately on the AGFW dataset, and then we use the Voting system to combine predictions to get the result.

Towards efficient and robust face recognition through attention-integrated multi-level CNN

AbstractThe rapid advancement of deep Convolutional Neural Networks (CNNs) has led to remarkable progress in computer vision, contributing to the development of numerous face verification architectures. However, the inherent complexity of these architectures, often characterized by millions of parameters and substantial computational demands, presents significant challenges for deployment on resource-constrained devices. To address these challenges, we introduce RobFaceNet, a robust and efficient CNN designed explicitly for face recognition (FR). The proposed RobFaceNet optimizes accuracy while preserving computational efficiency, a balance achieved by incorporating multiple features and attention mechanisms. These features include both low-level and high-level attributes extracted from input face images and aggregated from multiple levels. Additionally, the model incorporates a newly developed bottleneck that integrates both channel and spatial attention mechanisms. The combination of multiple features and attention mechanisms enables the network to capture more significant facial features from the images, thereby enhancing its robustness and the quality of facial feature extraction. Experimental results across state-of-the-art FR datasets demonstrate that our RobFaceNet achieves higher recognition performance. For instance, RobFaceNet achieves 95.95% and 92.23% on the CA-LFW and CP-LFW datasets, respectively, compared to 95.45% and 92.08% for very deep ArcFace model. Meanwhile, RobFaceNet exhibits a more lightweight model complexity. In terms of computation cost, RobFaceNet has 337M Floating Point Operations Per Second (FLOPs) compared to ArcFace’s 24211M, with only 3% of the parameters. Consequently, RobFaceNet is well-suited for deployment across various platforms, including robots, embedded systems, and mobile devices.

YOLO-FaceNet Fusion: Innovative System for Facial Recognition and Feature Extraction

Facial verification is vital in domains like Heathcare, Identity verification, etc. study presents a sophisticated facial verifying system utilizing state-of-the-art technologies: ArcFace is utilized for the edification of the model, while FaceNet is employed for the elicitation of facial characteristics. Initially, YOLO is deployed to discern and extricate visages from the input effigies. Subsequently, FaceNet is utilized to derive high-caliber facial attributes. In the final stage, ArcFace is employed for the model's edification, thus augmenting its robustness and precision. The apparatus gauges facial resemblance employing the Euclidean distance metric and is appraised through measures such as recall, accuracy, and precision. This approach yields a dependable and accurate facial verification system, thereby enhancing operational efficiency in practical applications.. Keywords – You Only Look Once (YOLO), ArcFace, Convolutional Neural Network (CNN), FaceNet, Machine Learning, Deep Learning, Euclidean Distance.

A DEEP LEARNING POWERED SMART PARKING SYSTEM BASED ON FACIAL RECOGNITION AND LICENSE PLATE ANALYSIS

In today's urban landscapes, parking congestion has become a pervasive challenge, leading to wasted time, increased emissions, and driver frustration. The ever-growing urban population, coupled with the increasing number of vehicles, has led to a severe shortage of parking spaces in metropolitan areas. This scarcity has not only made finding a parking spot a time-consuming and frustrating experience but has also contributed to traffic congestion and environmental pollution. Traditional parking management systems, which often rely on manual ticketing or physical barriers, are becoming inadequate in addressing these challenges. To address this issue, innovative solutions that combine technology and automation are on the rise. Traditional parking management systems often rely on physical infrastructure and human intervention, resulting in inefficiencies and limited scalability. In contrast, the integration of deep learning techniques and advanced computer vision technology into parking management opens up new possibilities for a smarter, more efficient, and user-friendly experience. This system leverages two key components: facial recognition technology to identify vehicle occupants and automatic recognition of license plate numbers for vehicle identification. By seamlessly integrating these technologies, the system not only facilitates effortless parking but also enhances security and optimizes parking space utilization.we will explore the fundamental components, benefits, and potential impact of the Face and Number Plate-Based Smart Parking System. Experimental results shows that improved efficiency in smart parking system using face and number plate verification system.

Leveraging Face Recognition Technology for Secure ATM Transaction

ATM or Automated Teller Machines are widely used by people nowadays. Performing cash withdrawal transactions with ATMs is increasing day by day. ATMs are a very important device throughout the world. The existing conventional ATM is vulnerable to crimes because of the rapid technology development. A total of 270,000 reports have been reported regarding debit card fraud and this was the most reported form of identity theft in 2021. A secure and efficient ATM is needed to increase the overall experience, usability, and convenience of the transaction at the ATM. In today's world, the area of computer vision is advancing at a breakneck pace. The recent progress in biometric identification techniques, including fingerprinting, retina scanning, and facial recognition has made a great effort to rescue the unsafe situation at the ATM. Specifically, the goal of this project is to give a computer vision method to solve the security risk associated with accessing ATM machines. This project proposes an automatic teller machine security model that uses electronic facial recognition using Deep Convolutional Neural Network. If this technology becomes widely used, faces would be protected as well as their accounts. Face Verification Clickbait Link will be generated and sent to bank account holders to verify the identity of unauthorized users through some dedicated artificial intelligent agents, for remote certification. However, it is obvious that man’s biometric features cannot be replicated, this proposal will go a long way to solve the problem of account safety making it possible for the actual account owner alone to have access to his accounts. This eliminates the possibility of fraud resulting from ATM card theft and copying. The experimental results on real-time datasets demonstrate the superior performance of the proposed approach over state-of-the-art deep learning techniques in terms of both learning efficiency and matching accuracy

Multitask Learning Strategy with Pseudo-Labeling: Face Recognition, Facial Landmark Detection, and Head Pose Estimation

Most facial analysis methods perform well in standardized testing but not in real-world testing. The main reason is that training models cannot easily learn various human features and background noise, especially for facial landmark detection and head pose estimation tasks with limited and noisy training datasets. To alleviate the gap between standardized and real-world testing, we propose a pseudo-labeling technique using a face recognition dataset consisting of various people and background noise. The use of our pseudo-labeled training dataset can help to overcome the lack of diversity among the people in the dataset. Our integrated framework is constructed using complementary multitask learning methods to extract robust features for each task. Furthermore, introducing pseudo-labeling and multitask learning improves the face recognition performance by enabling the learning of pose-invariant features. Our method achieves state-of-the-art (SOTA) or near-SOTA performance on the AFLW2000-3D and BIWI datasets for facial landmark detection and head pose estimation, with competitive face verification performance on the IJB-C test dataset for face recognition. We demonstrate this through a novel testing methodology that categorizes cases as soft, medium, and hard based on the pose values of IJB-C. The proposed method achieves stable performance even when the dataset lacks diverse face identifications.

Age-Invariant Cross-Age Face Verification using Transfer Learning

The integration of face verification technology has become indispensable in numerous safety and security software systems. Despite its promising results, the field of face verification encounters significant challenges due to age-related disparities. Human facial characteristics undergo substantial transformations over time, leading to diverse variations including changes in facial texture, morphology, facial hair, and eyeglass adoption. This study presents a pioneering methodology for cross-age face verification, utilizing advanced deep learning techniques to extract resilient and distinctive facial features that are less susceptible to age-related fluctuations. The feature extraction process combines handcrafted features like Local Binary Pattern/Histogram of Oriented Gradients with deep features from MobileNetV2 and VGG-16 networks. As the texture of the facial skin defines the age related characteristic the well-known texture feature extractors like LBP and HoG is preferred. These features are concatenated to achieve fusion, and subsequent layers fine-tune them. Experimental validation utilizing the Cross-Age Celebrity Dataset demonstrates remarkable efficacy, achieving an accuracy of 98.32%.

Masked face recognition using domain adaptation

Wearing facial masks has become a must in our daily life due to the global COVID-19 pandemic. However, the performance of a face recognition system is severely degraded due to the fact that the face images in the gallery are unmasked faces while the probe face images captured by the camera are masked faces, making the probe face images different from gallery face images in the activated region and the distribution domain. In this paper, we propose a novel face recognition system to address the issue. The system is integrated with a domain adaptation layer and a feature refinement layer. The feature refinement layer is based on the structure of the self-attention mechanism to align activated regions of unmasked faces with those of masked faces. The domain adaptation layer works by adapting the system from the unmasked face domain to the synthetically masked face domain and the real- world masked face domain. The system is tested on real-world data through face verification and face identification. The face verification accuracy is improved by 6.83% for the RMFD_FV dataset and 4.2% for the MFR2 dataset, and the face identification accuracy is improved by 15.43% for the MFRFI dataset.

Development of a phantom for assessing the precision of setup in skin mark-less surface-guided radiotherapy.

Surface-guided radiotherapy (SGRT) is adopted by several institutions; however, reports on the phantoms used to assess the precision of the SGRT setup are limited. The purpose of this study was to develop a phantom to verify the accuracy of the irradiation position during skin mark-less SGRT. An acrylonitrile butadiene styrene (ABS) plastic cube phantom with a diameter of 150mm on each side containing a dummy target of 15mm and two types of body surface-shaped phantoms (breast/face shape) that could be attached to the cube phantom were fabricated. Films can be inserted on four sides of the cubic phantom (left, right, anterior and posterior), and the center of radiation can be calculated by irradiating the dummy target with orthogonal MV beams. Three types of SGRT using a VOXELAN-HEV600M (Electronics Research&Development Corporation, Okayama, Japan) were evaluated using this phantom: (i) SGRTCT-a SGRT set-up based solely on a computed tomography (CT)-reference image. (ii) SGRTCT + CBCT-a method where cone beam computed tomography (CBCT) matching was performed after SGRTCT. (iii) SGRTScan-a resetup technique using a scan reference image obtained after completing the (ii) step. Both the breast and face phantoms were recognized in the SGRT system without problems. SGRTScan ensure precision within 1mm/1° for breast and face verification, respectively. All SGRT methods showed comparable rotational accuracies with no significant disparities. The developed phantom was useful for verifying the accuracy of skin mark-less SGRT position matching. The SGRTScan demonstrated the feasibility of achieving skin-mark less SGRT with high accuracy, with deviations of less than 1mm. Additional research is necessary to evaluate the suitability of the developed phantoms for use in various facilities and systems. This phantom could be used for postal surveys in the future.

Coordinate-wise monotonic transformations enable privacy-preserving age estimation with 3D face point cloud.

The human face is a valuable biomarker of aging, but the collection and use of its image raise significant privacy concerns. Here we present an approach for facial data masking that preserves age-related features using coordinate-wise monotonic transformations. We first develop a deep learning model that estimates age directly from non-registered face point clouds with high accuracy and generalizability. We show that the model learns a highly indistinguishable mapping using faces treated with coordinate-wise monotonic transformations, indicating that the relative positioning of facial information is a low-level biomarker of facial aging. Through visual perception tests and computational 3D face verification experiments, we demonstrate that transformed faces are significantly more difficult to perceive for human but not for machines, except when only the face shape information is accessible. Our study leads to a facial data protection guideline that has the potential to broaden public access to face datasets with minimized privacy risks.