Face Recognition Research Articles

Regularized Xception for facial expression recognition with extra training data and step decay learning rate

<span lang="EN-US">Despite extensive research on facial expression recognition, achieving the highest level of accuracy remains challenging. The objective of this study is to enhance the accuracy of current models by adjusting the structure, the data used, and the training procedure. The incorporation of regularization into the Xception architecture, the augmentation of training data, and the utilization of step decay learning rate together address and surpass current constraints. A substantial improvement in accuracy is demonstrated by the assessment conducted on the facial expression recognition (FER2013) dataset, achieving a remarkable 94.34%. This study introduces potential avenues for enhancing facial expression recognition systems, specifically targeting the requirement for increased accuracy within this domain.</span>

IntelliDoor: Smart Access Control System with Automated Door Operation

Abstract: The Intelligent Access Control System with Automatic Door Operation is a project aimed at providing secure and efficient access control using artificial intelligence (AI) and automated door mechanisms. This system utilizes facial recognition technology for user identification, Firebase for data storage and management, and Arduino for controlling the automatic door operation. The objective is to develop a robust and intelligent access control system that automatically identifies authorized individuals through facial recognition and opens the door for them. The system also maintains a record of entry for each individual for attendance tracking or security purposes. The project features include facial recognition, automatic door operation, Firebase integration, an alert system, and real-time monitoring. The project workflow involves initialization, facial recognition, recognition results, database updates, and automatic door operation. The project report covers the introduction, literature review, methodology, implementation, results, and conclusion. The Intelligent Access Control System with Automatic Door Operation provides an efficient and secure solution for access control, enhancing security while offering convenience. With further refinement and integration, it has the potential to become a standard solution for access control in modern buildings and facilities.

Music Recommendation System Using Facial Emotion Gestures

Abstract: Music recommendation systems are transformingthe way users interact with music streaming servicesby personalizing experiences. This paper presents a novel approach that leverages facial emotion recognition (FER) to suggest music dynamically based on users' emotional states. Using machinelearning and deep learning models, facial expressions are analyzed in real-time through video input. The system integrates emotion-based recommendations with collaborative and content- based filtering techniques to enhance accuracy. Thisapproach offers a more intuitive and human-centered interaction compared to traditional systems. The proposed solution can be used across streaming platforms, personalized wellness apps, and therapeutic environments.

Review of Smart Office Assistant

AI is playing major role in every field now a days and have become widely accepted in our society than traditional methods. The Smart Office Assistant is an intelligent system made to automate office environment in which employee attendance tracking and visitor management in offices can be done. Using web cam face recognition is done for people entering the office, for employees greeting is done by calling the name also their check in time and attendance is marked. For unrecognized faces it acts as a smart receptionist, which can handle appointment bookings and provide general office information for unfamiliar visitors through a chatbot interface. The Smart Office Assistant is for offices of all sizes and of various fields. Automating the office enhances the overall workplace experience, ensuring secure and efficient interactions for both employees and visitors. It takes more time for employees to manually sign in. Also visitors can easily book meetings or get information without anyone’s help using this technology. It helps to reduce administrative workload and staff can focus on more important tasks. To conduct this literature review of papers, we narrowed down the following areas relating AI-driven Smart Office Assistants; face recognition for attendance, Chatbot systems for visitor, integration of Artificial Intelligence in offices. The following databases were used: IEEE Xplore and Google Scholar; keywords included “AI office automation,” “face recognition attendance,” and “chatbot visitor management.”

Enhancing Facial Recognition: A Comprehensive Review of Deep Learning Approaches and Future Perspectives

This paper presents a comprehensive review of the application of deep learning in facial recognition, covering fundamental aspects from neural network architectures to advanced training methods. It starts with an introduction to the basic architectures such as Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), including variations like Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) networks. The review extends to sophisticated architectures like AlexNet, GoogleNet, VGGNet, and ResNet, which have significantly pushed the boundaries of accuracy in face recognition tasks. The paper details the process of data preprocessing in face recognition, which involves critical steps such as face detection, alignment, and normalization to ensure uniformity in the input data, enhancing the accuracy of feature extraction. Various feature extraction methods are discussed, including CNN-based and Generative Adversarial Network (GAN)-based techniques, which have shown considerable promise in deriving complex facial features from raw images. Loss functions such as Euclidean distance loss, angular/cosine margin loss, and softmax loss variants are explored to understand their impact on enhancing the discriminative power of the facial recognition systems. The paper highlights the evolution from traditional models using eigenfaces and feature descriptors like Local Binary Patterns (LBP) to cutting-edge deep learning models that utilize deep identity features (DeepID) and triplet loss functions to improve recognition accuracy.

Improving Similar Face Recognition Using ResNet-50 and FPN with Triplet Loss

Improving Similar Face Recognition Using ResNet-50 and FPN with Triplet Loss

Research Advances in Facial Expression Recognition Technology

As a key area in artificial intelligence and computer vision, facial expression analysis technology has been taking hold rapidly, yielding dazzling advances. This technology extracts even the subtlest facial movements to identify when a human is sad, happy, or angry. It has extensive application value in markets like mental diagnosis, secure monitoring, and intelligent interaction. The paper will provide a brief overview of the kernel technology of facial expressions recognition: geometric features, appearance features, and deep learning. And compared the experimental results of different experiments, as a goal, the experiments compare functions of several methods in a multi-dataset context, concentrating the primary problems in the tasks like dataset bias, real-time requirements, and different light levels and partial occlusions in various environments. Eventually, the paper forecasts the imminent growth trend in data fusion and deep learning improvement. This also indicates that emerging technologies, especially in terms of applications, will have the upper hand.

Application of big data and artificial intelligence in visual communication art design

In the era of continuous development of computer technology, the application of artificial intelligence (AI) and big data is becoming more and more extensive. With the help of powerful computer and network technology, the art of visual communication (VISCOM) has ushered in a new chapter of digitalization and intelligence. How vision can better perform interdisciplinary and interdisciplinary artistic expression between art and technology and how to use more novel technology, richer forms, and more appropriate ways to express art has become a new problem in visual art creation. This essay aims to investigate and apply VISCOM art through big data and AI methods. This essay proposed the STING algorithm for big data for multi-resolution information clustering in VISCOM art. In addition, the convolutional neural network (CNN) in AI technology was used to identify the conveyed objects or scenes to achieve the purpose of designing art with different characteristics for different scenes and groups of people. STING is a multi-resolution clustering technique for big data, with the advantage of efficient data processing. In the experimental part, this essay selected a variety of design contents in VISCOM art, including logo design, text design, scene design, packaging design and poster design. STING and CNN algorithms were used to cluster and AI-identify the design elements 16 of the design projects might contain. The results showed that the overall average clustering accuracy was above 82%, the accuracy of scene element recognition mainly was above 80%, and the accuracy of facial recognition was above 80%; this showed that this essay applied AI and big data to the design of VISCOM, and had a good effect on the clustering and identification of design elements. According to expert scores, these applications’ reliability and practicality scores were above 70 points, with an average of about 80 points. Therefore, applying big data and AI to VISCOM in this essay is reliable and feasible.

Chemotherapy-Induced Fingerprint Effacement Leading to Deprivation of Health Insurance: A Case Series and Review of Literature

AbstractAyushman Bharat Pradhan Mantri Jan Arogya Yojana (PMJAY) is a game changer for the Indian health care system, where patients with cancer are the major beneficiaries. Some intrinsic procedural shortcomings are restricting the beneficiaries to utilize it optimally. We report a case series of patients receiving chemotherapy who had developed adermatoglyphia because of chemotherapeutic treatment. Therefore, these patients became ineligible for getting the benefits of PMJAY, because of failure of the biometric system to recognize their fingerprints. Hence, patient treatment could not be completed. As a solution, we suggest that the alternatives to fingerprint recognition like face recognition and iris scanning be incorporated into the biometric system to ensure continuous benefit of PMJAY to such patients.

Channel and Spatial Attention in Chest X-Ray Radiographs: Advancing Person Identification and Verification with Self-Residual Attention Network

Background/Objectives: In contrast to traditional biometric modalities, such as facial recognition, fingerprints, and iris scans or even DNA, the research orientation towards chest X-ray recognition has been spurred by its remarkable recognition rates. Capturing the intricate anatomical nuances of an individual’s skeletal structure, the ribcage of the chest, lungs, and heart, chest X-rays have emerged as a focal point for identification and verification, especially in the forensic field, even in scenarios where the human body damaged or disfigured. Discriminative feature embedding is essential for large-scale image verification, especially in applying chest X-ray radiographs for identity identification and verification. This study introduced a self-residual attention-based convolutional neural network (SRAN) aimed at effective feature embedding, capturing long-range dependencies and emphasizing critical spatial features in chest X-rays. This method offers a novel approach to person identification and verification through chest X-ray categorization, relevant for biometric applications and patient care, particularly when traditional biometric modalities are ineffective. Method: The SRAN architecture integrated a self-channel and self-spatial attention module to minimize channel redundancy and enhance significant spatial elements. The attention modules worked by dynamically aggregating feature maps across channel and spatial dimensions to enhance feature differentiation. For the network backbone, a self-residual attention block (SRAB) was implemented within a ResNet50 framework, forming a Siamese network trained with triplet loss to improve feature embedding for identity identification and verification. Results: By leveraging the NIH ChestX-ray14 and CheXpert datasets, our method demonstrated notable improvements in accuracy for identity verification and identification based on chest X-ray images. This approach effectively captured the detailed anatomical characteristics of individuals, including skeletal structure, ribcage, lungs, and heart, highlighting chest X-rays as a viable biometric tool even in cases of body damage or disfigurement. Conclusions: The proposed SRAN with self-residual attention provided a promising solution for biometric identification through chest X-ray imaging, showcasing its potential for accurate and reliable identity verification where traditional biometric approaches may fall short, especially in postmortem cases or forensic investigations. This methodology could play a transformative role in both biometric security and healthcare applications, offering a robust alternative modality for identity verification.

Effects of Facial Recognition and Text Semantic Recognition on Affective Tutoring System

Facial recognition is the fastest method to detect emotions, and it can be combined with text semantic recognition to increase the accuracy of emotion detection. Emotions and creativity have often been discussed in recent years. A student will be interested in learning as long as he or she enjoys learning. Mind mapping is an active and simultaneous use of the left and right brains to stimulate the creativity and imagination of the learner, which is complementary to positive emotion. This study constructed an affective adaptive learning system that combines text emotions and facial clues in chatbot conversations to understand the emotional responses of learners during the learning process. The system is tailored to accommodate diverse learners through modules of varying difficulty scales, the incorporation of mind maps to support teaching and learning, and the implementation of asynchronous online discussion forums for discourse and feedback on course-related topics. The results revealed significant differences in critical thinking, reflective thinking, and problem-solving skills between the experimental and control groups, and students in the experimental group outperformed those in the control group on the creation of mind maps.

Real-Time Facial Emotion Detection Application with Image Processing Based on Convolutional Neural Network (CNN)

Facial Emotion Recognition (FER) is a key technology for identifying emotions based on facial expressions, with applications in human-computer interaction, mental health monitoring, and customer analysis. This study presents the development of a real-time emotion recognition system using Convolutional Neural Networks (CNNs) and OpenCV, addressing challenges such as varying lighting and facial occlusions. The system, trained on the FER2013 dataset, achieved 85% accuracy in emotion classification, demonstrating high performance in detecting happiness, sadness, and surprise. The results highlight the system's effectiveness in real-time applications, offering potential for use in mental health and customer behavior analysis.

Quantification of Facial Geometrical Dimension for Student Attendance Tracking

The traditional method of manual attendance-taking has been used in educational institutions for decades which have consumed one-sixth amount of class time for attendance marking. Great research on attendance systems has come up with techniques like biometrics, NFC’s and QR codes. Moreover, with advancements in technology, this research project can provide a more efficient and effective solution. This research project utilizes image processing, computer vision and facial recognition technology to mark the attendance of the students in class. The objectives of the system are registration of facial image, perform landmarking of the facial image and develop automated attendance system. As a result, this project works by installing a camera on top of the board which detects the student faces and performs attendance marking. Now is the time to implement this system in schools, institutions, colleges, and universities to streamline the attendance-taking process. This automated system will not only save time and effort but will also provide accurate attendance records, which will benefit both management and students.

Nebulized vasopressin penetrates CSF and improves social cognition without inducing aggression in a rhesus monkey model of autism

Low cerebrospinal (CSF) arginine vasopressin (AVP) concentration is a biomarker of social impairment in low-social monkeys and children with autism, suggesting that AVP administration may improve primate social functioning. However, AVP administration also increases aggression, at least in “neurotypical” animals with intact AVP signaling. Here, we tested the effects of a voluntary drug administration method in low-social male rhesus monkeys with high autistic-like trait burden. Monkeys received nebulized AVP or placebo, using a within-subjects design. Study 1 (N = 8) investigated the effects of AVP administration on social cognition in two tests comparing responses to social versus nonsocial stimuli. Test 1: Placebo-administered monkeys lacked face recognition memory, whereas face recognition memory was “rescued” following AVP administration. In contrast, object recognition memory was intact and did not differ between administration conditions. Test 2: Placebo-administered monkeys did not respond to conspecific social communication cues, whereas following AVP administration, they reciprocated affiliative communication cues with species-typical affiliative responses. Importantly, AVP administration did not increase aggressive responses to conspecific aggressive or affiliative overtures. Study 2 (N = 4) evaluated the pharmacokinetics of this administration method. Following AVP nebulization, we observed a linear increase in cisternal CSF AVP levels, and a quadratic rise and fall in blood AVP levels. These findings indicate that nebulized AVP likely penetrates the central nervous system, selectively promotes species-typical responses to social information, and does not induce aggression in low-social individuals. Nebulized AVP therefore may hold promise for managing similar social symptoms in people with autism, particularly in very young or lower functioning individuals.

Improved facial emotion recognition model based on a novel deep convolutional structure

Facial Emotion Recognition (FER) is a very challenging task due to the varying nature of facial expressions, occlusions, illumination, pose variations, cultural and gender differences, and many other aspects that cause a drastic degradation in quality of facial images. In this paper, an anti-aliased deep convolution network (AA-DCN) model has been developed and proposed to explore how anti-aliasing can increase and improve recognition fidelity of facial emotions. The AA-DCN model detects eight distinct emotions from image data. Furthermore, their features have been extracted using the proposed model and numerous classical deep learning algorithms. The proposed AA-DCN model has been applied to three different datasets to evaluate its performance: The Cohn-Kanade Extending (CK+) database has been utilized, achieving an ultimate accuracy of 99.26% in (5 min, 25 s), the Japanese female facial expressions (JAFFE) obtained 98% accuracy in (8 min, 13 s), and on one of the most challenging FER datasets; the Real-world Affective Face (RAF) dataset; reached 82%, in low training time (12 min, 2s). The experimental results demonstrate that the anti-aliased DCN model is significantly increasing emotion recognition while improving the aliasing artifacts caused by the down-sampling layers.

Racial Bias within Face Recognition: A Survey

Racial Bias within Face Recognition: A Survey

Convenient or risky? Investigating the behavioral intention to use facial recognition payment in smart hospitals

This study investigates the factors influencing users’ behavioral intention to adopt facial recognition payment (FRP) in smart hospitals, considering convenience and potential risks. The unified theory of acceptance and use of technology (UTAUT), the diffusion of innovations theory, and trust theory are employed to identify critical factors for promoting FRP adoption. A quantitative cross-sectional survey is conducted among smart hospital users in China, collecting 811 valid questionnaires, and the partial least squares structural equation method (PLS-SEM) is utilized for analysis. The results show that performance expectancy, effort expectancy, social influence, and facilitating conditions positively affect behavioral intention. Privacy concerns and perceived risks negatively impact trust in FRP, while familiarity enhances trust. Trust in FRP and personal innovativeness positively influence behavioral intention, with personal innovativeness moderating the trust-behavioral intention relationship. The findings emphasize the mediating role of trust in FRP and the importance of familiarity and personal innovativeness in driving FRP adoption. Gender (male or female) does not significantly impact the relationships and path coefficients in the model. However, slight discrepancies are observed between the permutation test and Henseler’s MGA in terms of the effect of privacy concerns on trust in FRP. This research contributes to the literature on users’ behavioral intentions, aiding smart hospitals in promoting FRP adoption while considering user concerns.

Cannabis use and cognitive biases in people with first-episode psychosis and their siblings.

Cannabis use and familial vulnerability to psychosis have been associated with social cognition deficits. This study examined the potential relationship between cannabis use and cognitive biases underlying social cognition and functioning in patients with first episode psychosis (FEP), their siblings, and controls. We analyzed a sample of 543 participants with FEP, 203 siblings, and 1168 controls from the EU-GEI study using a correlational design. We used logistic regression analyses to examine the influence of clinical group, lifetime cannabis use frequency, and potency of cannabis use on cognitive biases, accounting for demographic and cognitive variables. FEP patients showed increased odds of facial recognition processing (FRP) deficits (OR = 1.642, CI 1.123-2.402) relative to controls but not of speech illusions (SI) or jumping to conclusions (JTC) bias, with no statistically significant differences relative to siblings. Daily and occasional lifetime cannabis use were associated with decreased odds of SI (OR = 0.605, CI 0.368-0.997 and OR = 0.646, CI 0.457-0.913 respectively) and JTC bias (OR = 0.625, CI 0.422-0.925 and OR = 0.602, CI 0.460-0.787 respectively) compared with lifetime abstinence, but not with FRP deficits, in the whole sample. Within the cannabis user group, low-potency cannabis use was associated with increased odds of SI (OR = 1.829, CI 1.297-2.578, FRP deficits (OR = 1.393, CI 1.031-1.882, and JTC (OR = 1.661, CI 1.271-2.171) relative to high-potency cannabis use, with comparable effects in the three clinical groups. Our findings suggest increased odds of cognitive biases in FEP patients who have never used cannabis and in low-potency users. Future studies should elucidate this association and its potential implications.

End-to-End CNN conceptual model for a biometric authentication mechanism for ATM machines

People commonly use automated teller machines, also known as ATMs, in contemporary culture. The use of ATMs for currency withdrawal is becoming increasingly widespread in the modern world. Furthermore, attacks and break-ins have increased, highlighting the need for an ATM that is more secure and equipped with extra safety measures. The existing method of confirming these transactions through credit cards and ATMs carries a high level of risk. Card trapping, cash larceny, shoulder surfing, and ATM skimming are among the examples. The proposed system, which is based on biometrics and deep convolutional neural networks, can effectively resolve the problems associated with conventional ATM cards and PINs. The proposed method relies on face biometrics, which offers a novel technique to address the current challenge. This article presents a novel end-to-end multiscale attention-based light-weighted deep convolutional neural network (MA-LW-DCNN) framework for enhancing the accuracy of recognizing faces. The multiscale attention mechanism in face recognition enhances feature extraction by applying convolution filters at various scales, allowing the network to capture detailed and global facial features. It generates an attention map by normalizing characteristic maps and refining them using activation functions, improving recognition accuracy by focusing on essential face regions. The suggested system is assessed using a synthetic dataset against conventional machine and deep learning-based face recognition techniques. The experiment results for different individuals demonstrate an accuracy rate of around 99.84% in authenticating test samples. The proposed approach produced significantly improved evaluation measures precision, recall, and loss by 0.99, 0.99, and 0.16, respectively.

Early diagnostic value of home video-based machine learning in autism spectrum disorder: a meta-analysis.

Remote video-based ML may improve clinical practice and future research, particularly by combining advanced technologies such as facial recognition. It is a potential tool for diagnosing ASD in children. • The incidence of pediatric ASD has increased in recent years. • ML based on remote video has shown ideal early diagnostic value. • The first systematic review and meta-analysis evaluating the diagnostic performance of remote video-based ML for ASD. • Home video-based ML is a valuable diagnostic tool for the early diagnosis of ASD. • Remote video-based ML is convenient and simple to utilize.