Face Recognition Techniques Research Articles

Enhanced facial expression recognition using transfer learning and M-CLAHE

In recent years, Facial Expression Recognition (FER) techniques have gained substantial attention within the realm of biometric technology due to their wide range of applications, including emotion analysis, human-computer interaction, and surveillance systems. This paper presents a robust and efficient FER system composed of three key steps. First, precise face detection is performed using the Viola-Jones algorithm, a well-established method for detecting facial features in real-time. Second, the detected images are enhanced using a Modified Contrast Limited Adaptive Histogram Equalization (M-CLAHE) technique to improve contrast and visibility. Finally, feature extraction and classification are carried out using three powerful Convolutional Neural Network (CNN) architectures: VGG16, ResNet50, and Inception-v3, all benefiting from Transfer Learning to boost performance. Experiments were conducted on two widely-used datasets, JAFEE and CK+, with Inception-v3 achieving remarkable accuracy, reaching 98.43% and 99.93% on the respective databases. These results underline the effectiveness and robustness of our approach, particularly through the use of Transfer Learning, which significantly enhances the overall performance of the model compared to existing methods.

Identity Instrumentalized: Pattern Recognition as an Epistemology of Surveillance, 1960-66.

The emergence of new surveillance practices is not solely a matter of technological and political developments. It is also intertwined with the production of scientific knowledge. This article traces how scientists in the 1960s developed some of the earliest computerized facial recognition techniques while covertly sponsored by a U.S. intelligence agency. The article situates their project within approaches from the technical field of pattern recognition. It demonstrates how the scientists, especially amid unsteady patronage relationships, reinforced a key assumption: that recognizing identity could be reduced to classifying specific features within a set of existing examples. As their ambitions grew over six years, the scientists transformed human identity into a scientific object tailored to their recognition techniques. How this transformation occurred foregrounds the epistemic underpinnings of surveillance technologies.

Face Recognition with Siamese Networks

Abstract Face recognition method is a common problem in modern Internet life. In this paper, face recognition will be designed based on Siamese network. The traditional methods have some problems, such as being greatly affected by environmental factors, insufficient processing of individual differences, lack of robustness and adaptability. However, the existing Siamese network based method has better recognition effect. In this paper, a face recognition technology based on Siamese network will be proposed. In this method, the features of two face images are extracted by the same neural network, and then these feature vectors are input into a distance metric model to calculate the similarity or distance between them, which is used to compare the similarity between faces. This method reduces the training parameters of the model, improves the utilization of parameters, and the average accuracy can reach 98%. Contrasted with traditional face recognition techniques, it offers enhanced accuracy and resilience, delivering favourable outcomes in real-world applications.

Emotion knowledge-based fine-grained facial expression recognition

Existing facial expression recognition (FER) techniques rely primarily on seven coarse-grained emotions as emotional labels, which are insufficient to cover the subtle changes in human emotions in the real world. We use 135 fine-grained emotions as emotional benchmarks to address the problem of highly semantically similar fine-grained emotion recognition. In this work, we propose a robust emotion knowledge-based fine-grained (EK-FG) emotion recognition network that captures inter-class relationships and discriminative representations of fine-grained emotions through two prior-based losses: coarse-grained hierarchical loss and fine-grained semantic loss. Specifically, the coarse-grained hierarchical loss obtains a structured semantic representation of fine-grained emotions based on prior knowledge, and captures inter-class relationships through effective category-level push-pull to obtain discriminative representations. The fine-grained semantic loss provides more accurate measurement information for semantic features based on prior knowledge, and enhances the model’s discriminative ability for subtle facial expression differences through regression constraints. Extensive experimental results on the Emo135 dataset demonstrate that EK-FG can effectively overcome the class ambiguity of fine-grained emotion.

Racial discrimination in online booking: how profile pictures affect host behaviors and platform actions

ABSTRACT Research has shown that racial discrimination is detrimental to the ethnic minorities in accommodation and hospitality sectors. However, whether racial discrimination happens during the stage of online booking before check-in remains unclear. Leveraging a natural experiment of the anti-discrimination policy implemented on Airbnb and face recognition techniques to identify the racial information of hosts and guests, this study reveals that racism from hosts against ethnic guests indeed exists during the stage of online booking. The results indicate that the monthly proportion of ethnic guests increases 5% after the launch of anti-discrimination policy. We also find that discrimination exists between ethnic hosts and ethnic guests, which was not documented in previous studies. Moreover, the anti-discrimination policy in relieving racism plays a bigger role among hosts with severe racial discrimination. These findings are critical for online booking platforms to set anti-discrimination policies.

(Invited) Heavy-Metal-Free Quantum Dot Thin-Film Photodetectors for SWIR Imaging: A Comprehensive Analysis for Performance Enhancement

Various emerging technologies investigate the ability to sense and detect light in the shortwave infrared spectrum (wavelengths between 1100nm and 2500nm). Autonomous cars, smart agriculture, eye tracking for AR and VR applications, face recognition, surveillance, machine vision and new microscopy techniques can take advantage of additional information found in SWIR.Thin film photodetectors, based on quantum dot photodiodes, show promise in bringing SWIR sensing to the mass markets by offering simpler and cheaper processes and higher resolution than existing technologies. However, the prevalent use of lead (Pb), Cadmium (Cd) and mercury (Hg) in existing quantum dot thin film photodetectors poses safety, environmental and regulatory challenges, limiting their widespread adoption.InAs quantum dots emerge as a leading alternative, offering a heavy metal free solution and paving the way for the next generation of SWIR imaging devices. Nevertheless, a nuanced understanding of InAs-based devices is imperative for unlocking their full potential and optimizing performance. This work presents a meticulous and extensive analysis conducted in our laboratories, encompassing both devices and materials. The resulting insights empower an agile and informed redesign of the photodiode, showcasing tangible improvements in performance metrics.

A Comparison of CNN-based 2D Static Facial Emotion Recognition Techniques

A Comparison of CNN-based 2D Static Facial Emotion Recognition Techniques

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.

Advancing driver fatigue detection in diverse lighting conditions for assisted driving vehicles with enhanced facial recognition technologies.

Against the backdrop of increasingly mature intelligent driving assistance systems, effective monitoring of driver alertness during long-distance driving becomes especially crucial. This study introduces a novel method for driver fatigue detection aimed at enhancing the safety and reliability of intelligent driving assistance systems. The core of this method lies in the integration of advanced facial recognition technology using deep convolutional neural networks (CNN), particularly suited for varying lighting conditions in real-world scenarios, significantly improving the robustness of fatigue detection. Innovatively, the method incorporates emotion state analysis, providing a multi-dimensional perspective for assessing driver fatigue. It adeptly identifies subtle signs of fatigue in rapidly changing lighting and other complex environmental conditions, thereby strengthening traditional facial recognition techniques. Validation on two independent experimental datasets, specifically the Yawn and YawDDR datasets, reveals that our proposed method achieves a higher detection accuracy, with an impressive 95.3% on the YawDDR dataset, compared to 90.1% without the implementation of Algorithm 2. Additionally, our analysis highlights the method's adaptability to varying brightness levels, improving detection accuracy by up to 0.05% in optimal lighting conditions. Such results underscore the effectiveness of our advanced data preprocessing and dynamic brightness adaptation techniques in enhancing the accuracy and computational efficiency of fatigue detection systems. These achievements not only showcase the potential application of advanced facial recognition technology combined with emotional analysis in autonomous driving systems but also pave new avenues for enhancing road safety and driver welfare.

CCNN-SVM: Automated Model for Emotion Recognition Based on Custom Convolutional Neural Networks with SVM

The expressions on human faces reveal the emotions we are experiencing internally. Emotion recognition based on facial expression is one of the subfields of social signal processing. It has several applications in different areas, specifically in the interaction between humans and computers. This study presents a simple CCNN-SVM automated model as a viable approach for FER. The model combines a Convolutional Neural Network for feature extraction, certain image preprocessing techniques, and Support Vector Machine (SVM) for classification. Firstly, the input image is preprocessed using face detection, histogram equalization, gamma correction, and resizing techniques. Secondly, the images go through custom single Deep Convolutional Neural Networks (CCNN) to extract deep features. Finally, SVM uses the generated features to perform the classification. The suggested model was trained and tested on four datasets, CK+, JAFFE, KDEF, and FER. These datasets consist of seven primary emotional categories, which encompass anger, disgust, fear, happiness, sadness, surprise, and neutrality for CK+, and include contempt for JAFFE. The model put forward demonstrates commendable performance in comparison to existing facial expression recognition techniques. It achieves an impressive accuracy of 99.3% on the CK+ dataset, 98.4% on the JAFFE dataset, 87.18% on the KDEF dataset, and 88.7% on the FER.

Marine predators optimization with deep learning model for video‐based facial expression recognition

AbstractVideo‐based facial expression recognition (VFER) technique intends to categorize an input video into different kinds of emotions. It remains a challenging issue because of the gap between visual features and emotions, problems in handling the delicate movement of muscles, and restricted datasets. One of the effective solutions to solve this problem is the exploitation of efficient features defining facial expressions to carry out FER. Generally, the VFER find useful in several areas like unmanned driving, venue management, urban safety management, and senseless attendance. Recent advances in computer vision and deep learning (DL) techniques enable the design of automated VFER models. In this aspect, this study establishes a new Marine Predators Optimization with Deep Learning Model for Video‐based Facial Expression Recognition (MPODL‐VFER) technique. The presented MPODL‐VFER technique mainly aims to classify different kinds of facial emotions in the video. To accomplish this, the presented MPODL‐VFER technique derives features using the deep convolutional neural network based densely connected network (DenseNet) model. The presented MPODL‐VFER technique employs MPO technique for the hyperparameter adjustment of the DenseNet model. Finally, Elman Neural Network (ENN) model is exploited for emotion recognition purposes. For assuring the enhanced recognition performance of the MPODL‐VFER approach, a comparison study was developed on benchmark dataset. The comprehensive results have shown the significant outcome of MPODL‐VFER model over other approaches.

Intelligent Education Managemnt System Design for Universities based on MTCNN Face Recognition Algorithm

Face recognition technique has made significant advancements in security and attendance, but its application in teaching management is minimal. To address the issues of insufficient teacher resources and declining educational quality, the paper designs an intelligent education management system for colleges and universities based on improved Multi-task Cascaded Convolutional Neural Networks (MTCNN) face recognition. The purpose is to achieve accurate recognition of faces through improved facial recognition technology, thereby analyzing the attendance status of students, and improving the efficiency and quality of educational resource utilization. Firstly, an improved MTCNN facial recognition technology is adopted to achieve realtime monitoring of student status and attendance in the classroom through a B/S network structure. Secondly, through cluster deployment and load balancing, system stability and response speed can be improved. The results indicated that the improved MTCNN had better facial recognition accuracy and GPU utilization than traditional systems under different occlusion conditions. When there was no occlusion, recognition accuracy was 99.4%. However, when occlusion was presented at 10%, 20%, and 30%, the accuracy dropped to 92.3%, 84.25%, and 73.4%, respectively. Additionally, when the number of concurrent users was 1000, the maximum GPU utilization rate was 75%, which was 11% lower than traditional MTCNN systems. The use of an improved MTCNN facial recognition-based intelligent education management system in universities can effectively enhance the quality of classroom teaching and monitor the status of students. Further optimization of algorithm performance is needed in subsequent research to support larger-scale concurrent user usage while reducing hardware resource consumption.

Face Recognition Based on Deep Learning: A Comprehensive Review

Face recognition technology has undergone transformative changes with the advent of deep learning techniques. This review paper provides a comprehensive examination of the development and current state of face recognition techniques influenced by deep learning. We begin by discussing the fundamental deep learning models that have dramatically enhanced the accuracy and efficiency of face recognition, highlighting pivotal architectures such as convolutional neural networks (CNNs) and autoencoders. Subsequent sections delve into the application of these models in various environments and challenges, such as different lighting conditions, occlusion, and facial expressions. We also address the integration of deep learning with emerging technologies such as 3D facial reconstruction and multimodal biometrics. Furthermore, the review explores the ethical, privacy, and bias concerns inherent in facial recognition systems, focusing on the need for responsible and fair practices in AI. Finally, future directions are suggested, focusing on the need for robust, adaptable, and ethical face recognition systems. This paper aims to provide an important resource for researchers and practitioners in the field of computer vision, providing insight into the technological advances and ongoing challenges in deep learning-based face recognition.

A Novel Technique for Facial Recognition Based on the GSO-CNN Deep Learning Algorithm

Face recognition is one of the important elements that can be used for securing the facilities, emotion recognition, sentiment exploration, fraud analysis, and traffic pattern analysis. Intelligent face recognition has yielded excellent accuracy in a controlled environment whereas vice versa in an uncontrolled environment. However, conventional methods can no longer satisfy the demand at present due to their low recognition accuracy and restrictions on many occasions. This study proposed an optimal deep learning-based face recognition system that improves the security of the model developed in the IoT cloud environment. Initially, the dataset of images was gathered from the public repository. The captured images are explored using image processing techniques like image preprocessing employing the Gaussian filter technique for removing the noise and smoothing the image. The histogram of oriented gradients (HOGs) is used for the image segmentation. The processed images are preserved at the cloud service layer. Extract features were linked to facial activities using the spatial-temporal interest point (STIP). On the other hand, the extracted feature vectors are investigated using galactic swarm optimization (GSO) techniques that give optimized feature vectors. The necessary features are selected using the gray level co-occurrence matrix (GLCM), which separates the statistical texture features. The GSO output is fed into the deep convolutional neural network (DCNN) that effectively trains the captured face images. This will allow the effectiveness of the GSO-CNN technique to be assessed in terms of recognition accuracy, recall, precision, and error rate.

Predictive Music Based on Mood

It is often difficult for a person to choose which mu- sic to listen to from a vast array of available options. Relatively, this paper focuses on building an efficient music recommendation system based on the user’s mood which determines the emotion of user using Facial Recognition technique. The model is build using the transfer learning approach for which MobileNet model and Cascade classifier are used. Analyzing the user’s face expression might help you better comprehend their current emotional or mental condition. Music and video are one area where there is a lot of potential to present clients with a variety of options depending on their interests and data. More than 60% of users anticipate that the number of songs in their music collection will grow to the point where they will be unable to find the song they need to play at some point in the future. The user would save time by not having to search for or look up tunes. The image of the user is captured using a webcam. Then, depending on the user’s mood, an appropriate song from the user’s playlist or a movie is shown.

A novel relation‐aware global attention network for sentiment analysis of students in the wisdom classroom

SummaryThe ability of facial expression recognition, the ability to decipher human emotions from facial features, and we can judge the emotional state of human beings by analysing facial expressions. Empowered by this technology, the related research of student sentiment analysis has become a focal point in the realm of educational technology. Teachers can now read the emotional state of their students and estimate the effectiveness of their teaching strategies, enabling them to implement appropriate intervention techniques to enhance teaching outcomes. However, facial expression recognition techniques are currently limited by their shortcomings. Network performance degradation and loss of feature information are key issues that hinder the effectiveness of sentiment analysis of student feedback. To overcome these limitations, in this paper, we propose RFMNet, a novel network model based on deep learning theory. RFMNet, with its higher extraction capability, is designed to accurately analyse student expressions. It introduces a relation‐aware global attention (RGA) module, which facilitates the integration of more discriminative expression features in the image, leading to more refined sentiment analysis. This innovative model also employs a Mish activation function and a focal loss function. The Mish activation function is of particular interest because it helps to avoid the loss of feature information due to neuron deactivation when the ReLU gradient is . This approach results in a more robust and accurate facial expression recognition model. Our model was tested on the FERPlus public dataset. The model achieved an average recognition accuracy of 89.62%, which is a testament to its performance in decoding the facial expressions of students. This precision allows for intelligent processing of teaching information and real‐time feedback, enabling teachers to adapt their teaching strategies to better suit the needs of their students.

Development of Face Recognition System Using Support Vector Machine Algorithm

This research paper describes a face recognition system constructed with the Support Vector Machine (SVM) method. The technique implements the Convolutional Neural Network (CNN) approach for extracting features, which improves the accuracy of recognising faces. The method confirms an efficient and accurate facial recognition procedure by utilising SVM's ability to detect complex patterns within retrieved characteristics. The article explores how the system is implemented and optimised performance, with a focus on obtaining performance in real time. The experimental findings demonstrate the practical application of the SVM-based facial recognition system, emphasising its numerous potential applications in security, the authentication process, as well as interaction between humans and computers. The implementation of CNN for extracting features provides refinement to the system, proving its flexibility to complex face characteristics and confirming its feasibility in actual applications. The results indicate that the suggested system is an effective facial recognition technique. Furthermore, the system is computationally efficient, taking just a few seconds to evaluate an individual face for extracting features and recognition. The system for identifying faces uses modern approaches to enhance both speed and precision, making it a potential option for a variety of applications. Its capacity to swiftly and correctly detect faces in real-time circumstances is a substantial development in facial identification technologies. The system's capability has been comprehensively evaluated, and it satisfies the essential criteria for practical implementation in real-world situations, making it an important addition to the continued development of secure and efficient face recognition systems.

Image Separation and Sharing Application

A state-of-the-art project created as part of a program is the Image Separation and Sharing Application, which aims to transform the way A cutting-edge project developed as part of a program is the Image Separation and Sharing Application. The users interact with their image collections. Image separation and sharing Applications help users leverage facial recognition and machine learning techniques to build a smooth and effective image separation system. Key Words: image separation, image sharing, machine learning, user interface, Face net library, Face recognition

Portable smart attendance system on Jetson Nano

The masked face recognition-based attendance management system is an important biometric-based attendance tracking solution, especially in light of the COVID-19 pandemic. Despite the use of various methods and techniques for face detection and recognition, there currently needs to be a system that can accurately recognize individuals while they are wearing a mask. This system has been designed to overcome the challenges of widespread mask use, impacting the effectiveness of traditional face recognition-based attendance systems. The proposed system uses an innovative method that recognizes individuals even while wearing a mask without the need for removal. With its high compatibility and real-time operation, it can be easily integrated into schools and workplaces through an embedded system like the Jetson Nano or conventional computers executing attendance applications. This innovative approach and its compatibility make it a desirable solution for organizations looking to improve their attendance-tracking process. The Experimental results indicates using maximum resources possible the execution time needed on Jetson Nano is 15 to 22 seconds and 14 to 18 seconds respectively and the average frame capture if there are at least one face detected on Jetson Nano is 3-4 frames.

Innovative Integration of Convolutional Neural Networks for Enhanced Face Recognition

The face Recognition technique is important in Computer Vision nowadays. The research study focuses on a Face Recognition system that uses deep learning to identify face photos. Face detection and categorization are carried out using various Convolutional neural network (CNN) models using deep learning methods. Prior research has mostly focused on either the ResNet or DenseNet-based CNN models. The current study combines ResNet and DenseNet to create a hybrid model. The suggested work aims to improve efficiency and accuracy. During the simulation's training and testing phases, categories are taken into account. The present study is centered on the Labeled Faces in the Wild (LFW) dataset. The photos go through an initial noise reduction procedure. Picture quality assessment involves considering measures like MSE, PSNR, and SSIM. Once the suggested model has completed training, it produces high-quality images. The suggested system includes the Innovative CNN approach framework, which combines DenseNet with a noise reduction approach, a segmentation mechanism, and a ResNet model based on CNN. Comparative research was performed to assess the precision of several filtered image collections using different convolutional neural network models. The simulation results show that the proposed model had higher performance and accuracy than traditional ResNet and DenseNet models.