Face Recognition Accuracy Research Articles

Unleash the Power of Deep Neural Networks and Transfer Learning for Enhanced Face Recognition

Face recognition has become a crucial technology with diverse applications in various domains such as biometric security, healthcare, personal identification, and law enforcement. It stands out due to its high recognition rate, the richness of features, its universality, and its uniqueness. Having said that, challenges such as varying illumination, poses, facial expressions, face transformations, and backgrounds have hindered recognition accuracy, especially when using traditional techniques that rely on explicit feature extraction before the actual classification. The emergence of deep learning algorithms, such as Convolutional Neural Networks (CNNs), has exhibited prominent potential in image recognition capabilities, but building effective face recognition systems from scratch demands substantial labeled data and computational resources. To overcome these challenges, this paper proposes a novel approach that utilizes transfer learning and a pre-trained AlexNet CNN to improve face recognition capabilities. The model is trained with three different deep-learning optimizers, and the most suitable one is selected for the proposed system. For experiments, we created a custom database with images of five distinct individuals, generating over 1260 face images with each person having at least 250 samples. The dataset was further enriched using data augmentation technique. Using MATLAB with the Deep Learning Toolbox, the results demonstrate the model's recognition rate, peaking up to 100 per cent when the SGD optimizer is employed, 97.88 per cent when RMSProp is the optimizer, and 99.2 per cent for the Adam optimizer while using the same set of hyperparameters. These findings showcase the effectiveness of the approach and open doors for more efficient and accurate face recognition systems in real-world scenarios with large datasets.

MACHINE LEARNING-BASED FACIAL RECOGNITION FOR VIDEO SURVEILLANCE SYSTEMS

Video surveillance systems play a crucial role in ensuring public safety and security. However, the traditional methods of surveillance often fall short in effectively identifying individuals, particularly in crowded or dynamic environments. This research addresses the limitations of conventional video surveillance by proposing a machine learning-based facial recognition system. The increasing demand for robust security measures necessitates the development of advanced technologies in video surveillance. Facial recognition has emerged as a promising solution, but existing systems struggle with accuracy and efficiency. This research aims to bridge these gaps by leveraging machine learning techniques for facial recognition in video surveillance. Conventional video surveillance struggles with accurate and rapid identification of individuals, leading to potential security lapses. This research addresses the challenge of enhancing facial recognition accuracy in real-time video feeds, especially in scenarios with varying lighting conditions and occlusions. While facial recognition has gained traction, there is a significant research gap in the implementation of machine learning algorithms tailored for video surveillance. This study aims to fill this void by proposing a novel methodology that combines deep learning and computer vision techniques for robust facial recognition in dynamic environments. The proposed methodology involves training a deep neural network on a diverse dataset of facial images to enable the model to learn intricate facial features. Additionally, computer vision algorithms will be employed to handle challenges such as occlusions and varying lighting conditions. The model''''s performance will be evaluated using real-world video surveillance data. Preliminary results demonstrate a significant improvement in facial recognition accuracy compared to traditional methods. The machine learning-based system exhibits enhanced performance in challenging scenarios, showcasing its potential for practical implementation in video surveillance systems.

Enhancing Attendance Management through Real-Time Face Recognition using combination of LBP Histogram and Linear Discriminant Analysis

Face recognition technology's excellent accuracy and non-intrusiveness have made it a major player in the attendance management space. This research study presents an advanced method of tracking attendance through the integration of a Face Recognition System (FRS) with Linear Discriminant Analysis (LDA) and Local Binary Pattern (LBP) histogram analysis. The architecture of the suggested attendance system is described in the study, with an emphasis on how LDA and LBP techniques are used to increase the accuracy of face feature extraction and recognition. Through the use of LDA, the system improves face data's discriminative strength, producing attendance records that are more trustworthy. Robust facial texture and pattern identification are simultaneously made possible by LBP histogram analysis, particularly in a variety of environmental settings. To sum up, this study advances biometric attendance systems by demonstrating how LDA and LBP histogram analysis may improve the precision and dependability of face recognition systems used for attendance tracking

RANCANG BANGUN APLIKASI PENGENALAN WAJAH UNTUK SISTEM PRESENSI DI PRODI TEKNIK INFORMATIKA UNIVERSITAS ISLAM RADEN RAHMAT MALANG MENGGUNAKAN METODE LBPH DAN LIBRARY OPENCV BERBASIS ANDROID

The attendance system is a mechanism to record the attendance of students in each class they take. The attendance system serves as evidence of students' presence in the learning process. In its journey, Universitas Islam Raden Rahmat has been using manual attendance through attendance journals in the learning process. However, with technological advancements, the attendance process has followed this trend, one of which is face recognition. In this research, the researcher designed a face recognition application for the attendance system that can be implemented on mobile platforms, especially Android. This application using the Local Binary Pattern Histogram (LBPH) method and the OpenCV library. The objective of this application is to enhance the flexibility and efficiency of the current attendance system by eliminating the need to repeatedly retrieve attendance forms, preventing fraud, and reducing paper usage. By using the waterfall system development method, testing showed a face recognition accuracy of 70%.

Pose aligned modality-invariant feature learning for NIR–VIS heterogeneous face recognition

Both pose disparities and modality differences with various modalities are significant difficulties that have an impact on recognition accuracy in heterogeneous face recognition. In this paper, we propose the pose aligned modality-invariant feature learning (PAMFL) method for NIR–VIS face recognition. This method disentangles the processing of the face pose and modality into independent stages. In the first phase, we construct the face pose alignment module (PAM). The built StyleGAN2-based generator incorporates pose estimation and feature mapping structures to alter the face shape in accordance with pose yaw angle instructions, eliminating the face pose misalignment. In the second phase, we build the modality-invariant feature learning module (MFLM). Modality-specific feature representations are learned using a pseudo-Siamese network in the shallow layer of the network, while modality-invariant feature representations are learned using a parameter sharing layer embedded in the deeper layer of the network. This module preserves all modality-invariant features while minimizing cross-modality variation. Finally, comparative experiments on BUAA VisNir, CASIA NIR–VIS 2.0 and Oulu CASIA NIR–VIS datasets validate that the proposed PAMFL shows advanced performance in overcoming face pose misalignment and improving heterogeneous face recognition accuracy.

Face recognition of remote monitoring under the Ipv6 protocol technology of Internet of Things architecture

Abstract With the advent of the Internet of Things (IoT) era, the application of intelligent devices in the network is becoming more and more extensive, and the monitoring technology is gradually developing towards the direction of intelligence and digitization. As a hot topic in the field of computer vision, face recognition faces problems such as low level of intelligence and long processing time. Therefore, under the technical support of the IoTs, the research uses internet protocol cameras to collect face information, improves the principal component analysis (PCA), poses a PLV algorithm, and then applies it to the face recognition system for remote monitoring. The outcomes demonstrate that in the Olivetti Research Laboratory face database, the accuracy of PLV is relatively stable, and the highest and lowest are 98 and 94%, respectively. In Yale testing, the accuracy of this algorithm is 12% higher than that of PCA algorithm; In the database of Georgia Institute of Technology (GT), the PLV algorithm requires a time range of 0.2–0.3 seconds and has high operational efficiency. In the selected remote monitoring face database, the accuracy of the method is stable at more than 90%, with the highest being 98%, indicating that it can effectively improve the accuracy of face recognition and provide a reference technical means for further optimization of the remote monitoring system.

Gravitational Deep Convoluted Stacked Kernel Extreme Learning Based Classification for Face Recognition

In recent times, researchers have designed several deep learning (DL) algorithms and specifically face recognition (FR) made an extensive crossover. Deep Face Recognition systems took advantage of the hierarchical framework of the DL algorithms to learn discriminative face characterization. However, when handling severe occlusions in a face, the execution of present-day methods reduces appreciably. Several prevailing works regard that, when face recognition is taken into consideration, affinity materializes to be a pivotal recognition feature. However, the rate of affinity changes when the face image for recognition is found to be illuminated, and occluded, with changes in the age of the subject. Motivated by these issues, in this work a novel method called Gravitational Deep Convoluted Stacked Kernel Extreme Learning-based (GDC-SKEL) classification for face recognition is proposed for human face recognition problems in frontal views with varying age, illumination, and occlusion. First, with the face images provided as input, Gravitational Center Loss-based Face Alignment model is proposed to minimize the intra-class difference, which can overcome the influence of occlusion in face images. Second, Deep Convoluted Tikhonov Regularization-based Facial Region Feature extraction is applied to the occlusion-removed face images. Here, by employing the Convoluted Tikhonov Regularization function, salient features are said to be extracted with an age-invariant representation. Finally, Stacked Kernel Extreme Learning-based Classification is designed. The extracted features are given to the Stacked Kernel Extreme Learning-based Classification and to identify testing samples Stacked Kernel is utilized. The performance of GDC-SKEL is evaluated on Cross-Age Celebrity Dataset. Experimental results are compared with other state-of-the-art classifiers in terms of face recognition accuracy, face recognition time, PSNR, and False Positive Rate which shows the effectiveness of the proposed GDC-SKEL classifier.

Interactive Quadruped Felid Class Robot with a Neural Processing Unit

The authors consider the urgent task of developing bionic robots, in particular robots on four legs. Their advantages are the ability to move on uneven terrain, to perform reconnaissance, rescue and other dangerous work, where they could replace humans. A review of the existing best-known and most functional bionic four-legged robots is given, with descriptions of their strengths and weaknesses, as well as peculiarities of their movement and use. The main problems in the development of such devices and their control systems are highlighted. The article provides information on the research and development of an interactive bionic robot of the felid class, whose skeletal structure control implementation is deeply explored. The features of hardware and software implementation of the robot are considered, and schematic and real images of the construction are presented. The application of a microcomputer device with a neural processing unit to solve the problem of machine vision is highlighted. The results of testing machine vision using the Yolo3 neural network in streaming video mode are presented. The average accuracy of the open face recognition as a result of the tests was 95 %. For different degrees of occlusion, the average score was 80 %, and occlusion variants in which the neural network was unable to recognize faces were also identified. The article concludes with a discussion of the advantages and disadvantages of the proposed robot and the possibility of its application in human life, including the solution of various practical tasks.

DAFL: Domain adaptation-based federated learning for privacy-preserving biometric recognition

With the introduction of data protection regulation in various countries, traditional centralized learning for the exploitation of sensitive biological information will gradually become unsustainable. We take face and speaker recognition systems as examples, to consider the possibility of implementing them using federated learning. It is known that federated learning methods still have some issues to be solved, e.g., parameter updates delivered can still reveal user privacy. Besides, existing privacy-preserving methods such as encryption and perturbation could pose other problems, including low accuracy and high training overhead, which can be more prominent in biometric recognition scenarios. We adopt the idea of domain adaptation and propose a new federated learning framework, DAFL, focusing on the improvement of the training efficiency and model performance, to achieve a practical privacy-preserving biometric recognition scheme for the first time. We also design a special dropout method for it to address the possible imbalance of biometric samples across users. Experiments on real-world datasets show that our approach can achieve up to 95.6% and 97.9% accuracy in face recognition and speaker recognition tasks, respectively, under medium privacy settings. Compared with existing work, it can save 56.0% of training time with a 3.1% accuracy loss in the best case.

ResNet and PCA-Based Deep Learning Scheme for Efficient Face Recognition

Face recognition is an emerging field of research in recent days. With the rise of deep learning, face recognition has become efficient and precise, creating new milestones. The performance, accuracy, and computational time of the existing schemes can be enhanced by devising a new scheme. In this context, a multiclass classification framework for face recognition using residual network (ResNet) and principal component analysis (PCA) schemes of deep learning with Dlib library is proposed in this paper. The proposed framework produces face recognition accuracy of 99.6% and a reduction of computational time with 68.03% using principal component analysis.

Occluded Face Recognition based on Deep Learning

Compared to the traditional sparse representation and the dictionary processing method of occlusion, deep learning-based face recognition methods are being used more and more widely in the field of face recognition. However, in practice, face recognition results are greatly influenced by light intensity, shooting Angle, mask and sunglasses occlusion and other factors. Therefore, this paper will discuss the face recognition under the occlusion situation. In order to solve the problem of large pose change of human face and local occlusion respectively, an offset network and a weight network was introduced into the convolutional neural network. In the following paper, the facial recognition accuracy of the introduction of the offset network, the facial recognition accuracy of the weight network and the recognition accuracy of the unification of the two are compared with the traditional facial recognition model VGG16.

Face Detection and Recognition Using Raspberry Pi

: The face detection and recognition system using Raspberry Pi is a security system that uses advanced algorithms to detect and recognize faces. The system is designed to authorize access to individuals with authorized faces and deny access to unauthorized individuals. The system integrates with a door lock, and if an authorized face is detected, the door lock is automatically opened. If an unauthorized face is detected, a buzzer is activated to notify security personnel, and an email is sent to an authorized person to alert them of the security breach. The system requires high accuracy in face detection and recognition, and it is essential to ensure the system's privacy compliance. The integration of the system with hardware components requires programming skills, and regular maintenance and updates are necessary to ensure the system operates correctly and remains secure.

Development of Deep Learning Algorithms for Improved Facial Recognition in Security Applications

This research aims to develop artificial intelligence (AI) algorithms in the context of facial recognition with a focus on increasing accuracy in difficult environmental conditions. Although facial recognition technology has made great progress, challenges such as poor lighting, variations in facial expressions, and head rotation are still problems that must be overcome. The research methodology involved collecting a wide dataset covering a wide variety of faces under various environmental conditions. This data is then processed and its features are extracted using computer image processing techniques. Furthermore, several deep neural network architectures, such as Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), were developed, trained, and evaluated for face recognition tasks. The expected result is the development of an AI algorithm that is able to overcome challenges in facial recognition with higher accuracy than existing methods. In particular, significant improvements in facial recognition accuracy are expected especially under low lighting conditions and variations in facial expressions. This research has a major impact in a variety of security applications, such as border surveillance, building access control, and corporate security. With higher facial recognition accuracy, security risks can be significantly reduced, resulting in safer and more efficient security solutions. In conclusion, this research aims to bring innovation in facial recognition technology through advanced AI approaches, with the potential to improve security in various contexts.

Face recognition technology based on low-rank joint sparse representation algorithm

With the improvement of computer computing power and the development of artificial intelligence technology, face recognition technology has made a major breakthrough, and has been popularized and applied in all areas of life. However, different face structure and pose will affect the accuracy of face recognition. To overcome the problem, a low rank joint sparse representation algorithm for face recognition is proposed. The low rank features of images are extracted by structure independent and pairwise rank decomposition methods. The extracted low rank features of the first level image and the low rank features of the second level image are sparsely represented. Finally, the residual rate model is used to classify the images, and the final result of face recognition is obtained. The experimental results show that the proposed SRP algorithm has a recognition accuracy of more than 92% in two different face recognition tests. In the mixed multi face pose test, PRS algorithm performs best in the recognition of 1, 2, 3, 4, and 5 multi face pose types, with recognition rates of 95%, 94%, 93%, 91%, and 90% respectively. The algorithm also has excellent recognition performance and robustness in identifying harsh environments such as fuzzy environments. The research content focuses on complex face recognition scenes, innovatively uses low rank to complete the extraction of face feature data, and combines sparse selection of classification features to improve the overall effect of face recognition. It has important reference value for improving the overall security and recognition rate of face recognition.

Optimized Classifier Learning for Face Recognition Performance Boost in Security and Surveillance Applications.

Face recognition has become an integral part of modern security processes. This paper introduces an optimization approach for the quantile interval method (QIM), a promising classifier learning technique used in face recognition to create face templates and improve recognition accuracy. Our research offers a three-fold contribution to the field. Firstly, (i) we strengthened the evidence that QIM outperforms other contemporary template creation approaches. For this reason, we investigate seven template creation methods, which include four cluster description-based methods and three estimation-based methods. Further, (ii) we extended testing; we use a nearly four times larger database compared to the previous study, which includes a new set, and we report the recognition performance on this extended database. Additionally, we distinguish between open- and closed-set identification. Thirdly, (iii) we perform an evaluation of the cluster estimation-based method (specifically QIM) with an in-depth analysis of its parameter setup in order to make its implementation feasible. We provide instructions and recommendations for the correct parameter setup. Our research confirms that QIM's application in template creation improves recognition performance. In the case of automatic application and optimization of QIM parameters, improvement recognition is about 4-10% depending on the dataset. In the case of a too general dataset, QIM also provides an improvement, but the incorporation of QIM into an automated algorithm is not possible, since QIM, in this case, requires manual setting of optimal parameters. This research contributes to the advancement of secure and accurate face recognition systems, paving the way for its adoption in various security applications.

Face Recognition Method Based on Lightweight Network SE-ShuffleNet V2

<p>We develop a more efficient lightweight network based on SE-ShuffleNet V2 to address the issues of large parameter sizes and sluggish feature extraction rates in large networks in the field of face recognition. First, to increase the network’s accuracy and inference speed, the ReLU activation function of the original ShuffleNet V2 basic unit is swapped out for a segmented linear activation function. Second, the SE attention mechanism is added to the lightweight network ShuffleNet V2, which may improve the effective feature weights and decrease the invalid feature weights, and the SE attention causes the network to focus on more helpful features. Finally, the addition of the Arcface loss function enhances the face recognition network’s capacity for categorization. Experiments indicate that the SE-ShuffleNet V2 network that we created achieves superior performance under the parameters of position and age. Particularly, the LFW accuracy is 99.38%. The algorithm presented in this research significantly increases face recognition accuracy when compared to the original ShuffleNet V2 network, therefore the additional parameters and longer inference times can be disregarded. To match the accuracy of substantial convolutional networks, we developed the lightweight SE-ShuffleNet V2.</p> <p> </p>

Joint Image-to-Image Translation for Traffic Monitoring Driver Face Image Enhancement

The real traffic monitoring driver face (TMDF) images are with complex multiple degradations, which decline face recognition accuracy in real intelligent transportation systems (ITS). This paper is the first to propose joint image-to-image (I2I) translation to enhance TMDF images of ITS. First, as TMDF images are without corresponding clear ones, identity preserving is critical for TMDF images under unpaired I2I translation. This paper proposes a fast diagonal symmetry pattern (FDSP) to preserve identity structure under unpaired I2I translation. Second, FDSP is introduced into CycleGAN to form FDSP-CG, which aims to learn the degradation mapping (i.e., FDSP-CG-d) from the clarity domain to the degradation domain. FDSP-CG-d can generate massive degradation/clarity image pairs for paired I2I translation training. Third, this paper proposes the dual residual block (DRB) to strengthen Pix2pix for rich face detail features learning (i.e., DRB-P2P), which learns the enhancement mapping from the degradation image to its clear version under paired I2I translation. Finally, the experiments on TMDF (i.e., the brevity name of the face database collected from real ITS) and Chinese famous face (CFF) databases, as well as CelebA and MegaFace databases, indicate that the proposed method can efficiently enhance TMDF images whose degradation variations are learned by FDSP-CG.

Enhancing Face Recognition Accuracy Using Data Pre-processing Method and YOLO

The recognition of objects is an essential aspect of visual perception and finds extensive usage in diverse fields such as self-driving vehicles, security, robotics, and image retrieval. In this study, we investigate the performance of the YOLOv5 (You Only Look Once) algorithm for object detection on the VOC2007 dataset. The YOLOv5 model achieved a moderate overall accuracy and precision, demonstrating its potential for object detection tasks. However, the performance varied across different categories, with lower accuracy observed for less frequent categories and difficulties in distinguishing between closely related categories. We identify potential improvements to the YOLOv5 model's performance, including class balancing using weighted sampling and data augmentation, which may help the model to better learn to detect objects from under-represented categories and improve its ability to distinguish between similar objects. The results of our study imply that the YOLO algorithm has potential for object detection and classification projects in computer vision, however further study and refinement are necessary to broaden its efficacy across a greater variety of object classes and real-world scenarios.

Subjective evaluation of facial asymmetry with three-dimensional simulated images among the orthodontists and laypersons: a cross-sectional study

ObjectivesWe used three-dimensional (3D) virtual images to undertake a subjective evaluation of how different factors affect the perception of facial asymmetry among orthodontists and laypersons with the aim of providing a quantitative reference for clinics.Materials and methodsA 3D virtual symmetrical facial image was acquired using FaceGen Modeller software. The left chin, mandible, lip and cheek of the virtual face were simulated in the horizontal (interior/exterior), vertical (up/down), or sagittal (forward or backward) direction in 3, 5, and 7 mm respectively with Maya software to increase asymmetry for the further subjective evaluation. A pilot study was performed among ten volunteers and 30 subjects of each group were expected to be included based on 80% sensitivity in this study. The sample size was increased by 60% to exclude incomplete and unqualified questionnaires. Eventually, a total of 48 orthodontists and 40 laypersons evaluated these images with a 10-point visual analog scale (VAS). The images were presented in random order. Each image would stop for 30 s for observers with a two-second interval between images. Asymmetry ratings and recognition accuracy for asymmetric virtual faces were analyzed to explore how different factors affect the subjective evaluation of facial asymmetry. Multivariate linear regression and multivariate logistic regression models were used for statistical data analysis.ResultsOrthodontists were found to be more critical of asymmetry than laypersons. Our results showed that observers progressively decreased ratings by 1.219 on the VAS scale and increased recognition rates by 2.301-fold as the degree of asymmetry increased by 2 mm; asymmetry in the sagittal direction was the least noticeable compared with the horizontal and vertical directions; and chin asymmetry turned out to be the most sensitive part among the four parts we simulated. Mandible asymmetry was easily confused with cheek asymmetry in the horizontal direction.ConclusionsThe degree, types and parts of asymmetry can affect ratings for facial deformity as well as the accuracy rate of identifying the asymmetrical part. Although orthodontists have higher accuracy in diagnosing asymmetrical faces than laypersons, they fail to correctly distinguish some specific asymmetrical areas.

Repurposing Artificial Intelligence Tools for Disease Modeling: Case Study of Face Recognition Deficits in Neurodegenerative Diseases.

Face recognition deficits occur in diseases such as prosopagnosia, autism, Alzheimer's disease, and dementias. The objective of this study was to evaluate whether degrading the architecture of artificial intelligence (AI) face recognition algorithms can model deficits in diseases. Two established face recognition models, convolutional-classification neural network (C-CNN) and Siamese network (SN), were trained on the FEI faces data set (~ 14 images/person for 200 persons). The trained networks were perturbed by reducing weights (weakening) and node count (lesioning) to emulate brain tissue dysfunction and lesions, respectively. Accuracy assessments were used as surrogates for face recognition deficits. The findings were compared with clinical outcomes from the Alzheimer's Disease Neuroimaging Initiative (ADNI) data set. Face recognition accuracy decreased gradually for weakening factors less than 0.55 for C-CNN, and 0.85 for SN. Rapid accuracy loss occurred at higher values. C-CNN accuracy was similarly affected by weakening any convolutional layer whereas SN accuracy was more sensitive to weakening of the first convolutional layer. SN accuracy declined gradually with a rapid drop when nearly all nodes were lesioned. C-CNN accuracy declined rapidly when as few as 10% of nodes were lesioned. CNN and SN were more sensitive to lesioning of the first convolutional layer. Overall, SN was more robust than C-CNN, and the findings from SN experiments were concordant with ADNI results. As predicted from modeling, brain network failure quotient was related to key clinical outcome measures for cognition and functioning. Perturbation of AI networks is a promising method for modeling disease progression effects on complex cognitive outcomes.