Search

Cancellable biometrics is an important trend in biometric security systems, allowing for intentional distortions or variations in the original biometric data to be used for authentication, while preserving privacy of users and security of the original data. This paper presents two cancellable biometric recognition algorithms based on quaternion mathematics. The first algorithm depends on the Fractional Fourier transform (FRFT) with quaternion mathematics to induce intentional distortions in biometric data, while the second algorithm relies on quaternion rotation to achieve the desired level of distortion. Both algorithms are evaluated using Equal Error Rate (EER) and Area under Receiver Operating Characteristic curve (AROC). The simulation results indicate that both algorithms achieve EER values close to 0 and AROC values close to 1, demonstrating their effectiveness and reliability for cancellable biometric recognition. The proposed cancellable biometric recognition algorithms are intended to preserve privacy of users and security of biometric data, while maintaining high levels of accuracy and performance. The use of quaternion mathematics allows for intentional distortions to be introduced in a controlled and secure manner, ensuring that the original biometric data remains protected from either hacking or unauthorized access. In conclusion, the proposed cancellable biometric recognition algorithms based on quaternion mathematics are reliable and effective solutions for biometric security, providing both security and privacy preservation within the biometric authentication process. [ABSTRACT FROM AUTHOR]

Facial recognition is a rapidly growing field with applications in security, surveillance, and human-computer interaction. The performance of the Histogram of Oriented Gradients (HOG) algorithm, a popular feature extraction method for facial recognition, heavily relies on its parameter settings. Optimizing these parameters is crucial for achieving high accuracy. In this paper, we propose a novel approach to optimize HOG algorithm parameters and image size for facial recognition using a Tree-structured Parzen Estimator (TPE)-based Bayesian optimization technique. This optimization process effectively harnesses machine learning performance metrics as the objective function, enabling the algorithm to adapt and enhance its feature extraction capabilities. Extensive experiments conducted across multiple databases, including the AR Face Database, Extended Yale B Database, ORL Database, Yale Face Database, and Facepix, have yielded an exceptional recognition accuracy of 100%. Our optimized handcrafted HOG algorithm highlights the potential and continued relevance of parameter-based handcrafted feature extraction algorithms in computer vision, particularly in resource-constrained environments or applications requiring interpretability. [ABSTRACT FROM AUTHOR]

A large number of images are available on the Internet with the growth of social networking services, and many of them are face photos or contain faces. It is necessary to protect the privacy of face images to prevent their malicious use by face image de-identification techniques that make face recognition difficult, which prevent the collection of specific face images using face recognition. In this paper, we propose a face image de-identification method that generates a de-identified image from an input face image by embedding facial features extracted from that of another person into the input face image. We develop the novel framework for embedding facial features into a face image and loss functions based on images and features to de-identify a face image preserving its appearance. Through a set of experiments using public face image datasets, we demonstrate that the proposed method exhibits higher de-identification performance against unknown face recognition models than conventional methods while preserving the appearance of the input face images. [ABSTRACT FROM AUTHOR]

Face clustering has applications in organizing personal photo album, video understanding and automatic labeling of data for semi-supervised learning. Many existing methods cannot cluster millions of faces. They are either too slow, inaccurate, or need a lot memory. In our paper, we proposed a two stage unsupervised clustering algorithm which can cluster millions of faces in minutes. A rough clustering using greedy Transitive Closure (TC) algorithm to separate the easy to locate clusters, then a more precise non-greedy clustering algorithm is used to split the clusters into smaller clusters. We also developed a set of omni-supervised transformations that can produce multiple embeddings using a single trained model as if there are multiple models trained. These embeddings are combined using simple averaging and normalization. We carried out extensive experiments with multiple datasets of different sizes comparing with existing state of the art clustering algorithms to show that our clustering algorithm is robust to differences between datasets, efficient and outperforms existing methods. We also carried out further analysis on number of singleton clusters and variations of our model using different non-greedy clustering algorithms. We did trained our semi-supervised model using the cluster labels and shown that our clustering algorithm is effective for semi-supervised learning. [ABSTRACT FROM AUTHOR]

Facial recognition is a challenging pattern recognition problem in computer vision. This paper proposes a face recognition system that uses Empirical Mode Decomposition (EMD) and Local Binary Pattern (LBP) based feature extraction for a robust face recognition system. This scheme initially decomposes the image into 2N number of IMF (Intrinsic Mode Function) images, where N numbers of IMF images are estimated in the X direction and N number of IMF images are estimated in the Y direction. From the 2N number of IMFs, the M number of best matching IMF image pairs is estimated using 2D Discrete Fourier Transform (DFT). The IMF pair is added to extract the IC-LBP (Intensity Compensated-Local Binary Pattern) features. The IC-LBP features are extracted from the IMF images such that the center intensity is adjusted based on an adaptive intensity threshold. The use of EMD and IC-LBP features uses the essential descriptors that best represent a facial image. The same process is repeated in the testing phase where the test image is categorized from the trained images using the Naïve Bayes algorithm. The performance evaluation was done using the Yale, MORPH, and FGNET using metrics such as time complexity and recognition rate on different types of test face images like partial faces, different lightning, and rotation. Results show that the proposed face recognition system outperforms the traditional algorithms. Results show that the proposed face recognition system outperforms the traditional algorithms. [ABSTRACT FROM AUTHOR]

The limitations of Content Based Video Retrieval (CBVR), such as large pools of video data, selection of features, limited processing capacity, and content-related issues, can be overcome by Deep Belief Neural Networks (DBNs). The search engine does the processing, and the results are effectively returned to the users. The deep learning model also has some comparable challenges to be solved at various levels. Typically, the selection of frames is one of the most essential tasks for a face retrieval system which is efficiently accomplished by using deep learning models. Also, the performance of recognition models highly depends on the selection of frames that include both low-level and high-level features from the given video sequence. This paper proposes ALPHA-TO-OMEGA (ALMEGA-VIR) Visual Information Retrieval scheme that analyzes the contents of the video file for a particular face and retrieves the user's relevant videos. VIR aims to solve the challenge of locating relevant pictures and videos based on a query. VIR can be based on text-based search, content-based search, and Mixed based search. VIR here focuses on content-based search approach. The YouTube Celebrities (YTC) dataset, the Youtube Face (YTF) dataset, and Honda / UCSD dataset are used in this work. The used dataset addresses issues such as illumination changes, occlusion, rotation, and scale. We propose an ALMEGA-VIR framework for visual novelty face identification for specific investigation and evaluation. The classification accuracy of the proposed ALMEGA-VIR model shows that 4% is more effective than traditional classifier algorithms such as SVM, Naïve Bayesian classifier, MLP and Random Forest classifier. A comparative study is also implemented with other existing works to check the superiority of the proposed method. [ABSTRACT FROM AUTHOR]

This paper proposed a noble face recognition and biometric encryption technique for the biometric passport by applying encrypted biometric data encoded into the High-Capacity Color Two-Dimensional (HCC2D) Code to secure the biometric data. The proposed biometric encryption method is attained by applying the Secure Force (SF) algorithm and encoding it into the HCC2D code. The face recognition technology is achieved by combining the Viola-Jones (VJ) algorithm and the Local Binary Patterns (LBP) algorithm to extract the facial features and generate the template. This method will ensure the safety and security of a biometric passport from unauthorized access without knowing the passport holder. The proposed method will provide more security for border crossing and illegal immigrants for national security. [ABSTRACT FROM AUTHOR]

Employee attendance is crucial for a company because it is one indicator for determining an employee's salary or wages. Implementing the attendance process requires thoroughness so that it helps work activities in the company and produces accurate and correct attendance reports. Many companies have utilized technology that implements facial recognition to verify employee attendance. However, some companies still need to use the traditional method, which takes longer. Therefore, facial recognition is beneficial in terms of verifying attendance in the attendance system to speed up the process of recording and verifying the person. Tests were carried out on a total of 20 employees who took the attendance test using face recognition, all of them succeeded in carrying out attendance, and attendance data was recorded on the attendance website of PT. Srivijaya 87. In this study, we developed a website-based attendance system integrated with a facial recognition system using a deep learning method that can work in real-time to record employee attendance. This system is proven to simplify the attendance process and can recognize all employee data stored in the database with an average accuracy of 93. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel technique for face recognition under varying illumination. Our technique extracts twelve filter faces (FF) and computes their HOG features, and then finds the class label of the unknown face image according to each generated feature map. We perform majority voting from the found twelve class labels to determine the final class label of the input face image. By examining the structure of the FF's defined in this paper, we can see that our FF's can extract directional features from the input face images and they can supress random noise as well. This is the main reason why our new method performs so well for illumination invariant face recognition. Experimental results demonstrate that our new method achieves the highest correct recognition rate 99.3% (100%) for the Extended Yale Face B (CMU Pose, Illumination and Expression Face) dataset. [ABSTRACT FROM AUTHOR]

Micro‐expressions are spontaneous and unconscious facial movements that reveal individuals' genuine inner emotions. They hold significant potential in various psychological testing fields. As the face is a 3D deformation object, the emergence of facial expression leads to spatial deformation of the face. However, existing databases primarily offer 2D video sequences, limiting descriptions of 3D spatial information related to micro‐expressions. Here, a new micro‐expression database is proposed, which contains 2D image sequences and corresponding 3D point cloud sequences. These samples were classified using both an objective method based on the facial action coding system and a non‐objective emotion classification method that considers video contents and participants' self‐reports. A variety of feature extraction techniques are applied to 2D data, including traditional algorithms and deep learning methods. Additionally, a novel local curvature‐based algorithm is developed to extract 3D spatio‐temporal deformation features from the 3D data. The authors evaluated the classification accuracies of these two features individually and their fusion results under leave‐one‐subject‐out (LOSO) and tenfold cross‐validation. The results demonstrate that fusing 3D features with 2D features results in improved recognition performance compared to using 2D features alone. [ABSTRACT FROM AUTHOR]

Recently, IoT has been combined with artificial intelligence (AI) technology to develop into intelligent IoT (Artificial Intelligence of Things, AIoT) and can provide smart services to all industries. Generally, buildings with 30 or more floors are classified as high-rise apartments. There are high-rise apartments in many countries with small land areas and high population densities around the world, such as Hong Kong, Singapore, and Korea. Korea has many high-rise apartments and buildings with 30 or more floors, and residents there inevitably use elevators to move between floors. Because it is a high-rise apartment, it takes time for EVs to move, and a contactless method is needed when using EVs, especially due to COVID-19. In this study, we proposed a smart elevator system using AI that allows residents of high-rise apartments to conveniently shorten waiting and use times and use elevators without contact during rush hours due to the impact of COVID-19. The proposed system uses AI facial recognition to shorten EV waiting time and moving time and has a contactless floor selection function. As a result of the proposed system, it was confirmed that residents' EV waiting time and travel time were shortened compared to existing EV systems. [ABSTRACT FROM AUTHOR]

Face recognition is an essential feature required for a range of computer vision applications such as security, attendance systems, emotion detection, airport check‐in, and many others. The super‐resolution of subject images is an important and challenging element in numerous scenarios. At times the images are low resolution and need to be processed through super‐resolution techniques to gain more accurate results. For the problem of image super‐resolution, deep learning‐based face recognition systems have been explored in recent years; however, low‐resolution face recognition remains an arduous task. Generative adversarial network (GAN) based models are a promising approach to address this challenge. However, conventional GAN‐based models may generate images that differ significantly from an original high‐resolution image in the test set to the point that the identity of the target face may be changed. To address this shortcoming, we propose a novel U‐Net style generator architecture, where skip‐connections between the encoder and decoder layer can help in preserving the facial characteristics of the input image in the generated image, thus curbing the generator's ability to generate an entirely new image and training it to generate an image more similar in characteristics to the original image. In addition to statistical metrics like structural similarity index measure and Fréchet inception distance, we compute the pixel‐wise distance between the original and model‐generated images to ascertain that our model generates as close to the original images as possible. While we train the model for 4× super‐resolution (64 × 64 images to 256 × 256), our architecture can also be trained for an arbitrary resizing scale. Finally, the number of faces detected over high‐resolution images generated by our model is shown to be higher than state‐of‐the‐art high‐resolution image creation models for face recognition tasks. [ABSTRACT FROM AUTHOR]

In this paper, an example of an intelligent security system based on deep learning approach has been analyzed and described. Security is an important element in many aspects of human life. Depending on customer requirements, different levels of security may be required and implemented. Nowadays, artificial intelligence is becoming an indispensable part in many areas of human life and accordingly security systems are also based on the new achievements in this field. In this paper, an intelligent security system based on two methods for identifying persons, gait recognition and face recognition, was described. The two methods mentioned above can be used to give persons access to different buildings, facilities, institutions, etc. or to different indoor or outdoor areas. In light of the above, the aforementioned system uses face and gait recognition to identify persons who should be granted access to a facility or a specific area within the facility. Accordingly, two deep learning models for gait and face recognition have been developed and described. The analysis, the settings defined and the results obtained in relation to the models developed were also described. [ABSTRACT FROM AUTHOR]

Age-invariant face recognition (AIFR) is a significant research task in general face recognition, and it aims at eliminating gradual discordance of individual's facial appearance caused by aging process. Previous discriminative methods decompose facial components over one-dimensional feature vectors which overlooks critical facial information and hypothesize linear relationships over aging process which is inadequate to describe complex correlations. In this paper, we propose an enhanced AIFR model, namely age-invariant face network (AFN), to eliminate the discrepancy of aging process over facial semblance. Specifically, we propose attentive factorization module (AFM) leveraging attention mechanism to decompose facial features into identity-related features and age-related features in two-dimensional space on both local and contextual levels. We take both linear and nonlinear correlation analyses into account for a better reflection of aging/rejuvenation process and hence propose a hybrid correlation regularizer (HCR) to supervise the decorrelation between factorized features. Both identity features and age features are supervised simultaneously in a multi-task learning framework where only identity features are used in test phase for evaluation of AIFR performance. Experiments across common cross-age datasets (e.g., FG-Net, CACD-VS, CALFW, AgeDB-30) show the effectiveness of proposed AFN. Further, our proposed AFN is validated over LFW dataset to demonstrate its effectiveness on general face recognition task. [ABSTRACT FROM AUTHOR]

Decoupling the mixed face features to obtain identity features that are not disturbed by age information is the key to achieving cross-age face recognition. Established mainstream identity feature extraction methods decouple facial representations into two components: age-related features and identity-related features, ignoring the fact that some identity-age shared features (ISF) exist, resulting in incomplete extracted identity features and limiting the further improvement of cross-age identity recognition accuracy. We redefine the component of facial representations and propose to introduce identity-age shared features to complement identity features. Specifically, the mixed face features are decoupled into pure age features, pure identity features, and identity-age shared features. The pure identity features and identity-age shared features are coupled to obtain the complete identity features. In addition, a two-stage constraint algorithm is developed to reduce the interference of age-related information on identity recognition and to enhance the independence between identity and age features. Experimental results on benchmark datasets for face aging (FG-NET, AGE-DB30, CALFW and CACD-VS) show that the proposed ISF outperforms state-of-the-art AIFR approaches, including DAL and MTLFace. [ABSTRACT FROM AUTHOR]

Advances in deep learning technology have enabled the generation of more realistic deepfakes, which not only endanger individuals' identities but also exploit vulnerabilities in face recognition systems. The majority of existing deepfake detection methods have primarily focused on RGB-based analysis, offering unreliable performance in terms of detection accuracy and time. To address the issue, a grayscale-based deepfake detection method has recently been proposed. This method significantly reduces detection time while providing comparable accuracy to RGB-based methods. However, despite its significant effectiveness, the "key components" that directly affect the performance of grayscale-based deepfake detection have not been systematically analyzed. In this paper, we target three key components: RGB-to-grayscale conversion method, brightness level in grayscale, and resolution level in grayscale. To analyze their impacts on the performance of grayscale-based deepfake detection, we conducted comprehensive evaluations, including component-wise analysis and comparative analysis using real-world datasets. For each key component, we quantitatively analyzed its characteristics' performance and identified differences between them. Moreover, we successfully verified the effectiveness of an optimal combination of the key components by comparing it with existing deepfake detection methods. [ABSTRACT FROM AUTHOR]

The performance of face recognition (FR) has reached a plateau for public benchmark datasets, such as labeled faces in the wild (LFW), celebrities in frontal‐profile in the wild (CFP‐FP), and the first manually collected, in‐the‐wild age database (AgeDB), owing to the rapid advances in convolutional neural networks (CNNs). However, the effects of faces under various fine‐grained conditions on FR models have not been investigated, owing to the absence of relevant datasets. This paper analyzes their effects under different conditions and loss functions using K‐FACE, a recently introduced FR dataset with fine‐grained conditions. We propose a novel loss function called MixFace, which combines classification and metric losses. The superiority of MixFace in terms of effectiveness and robustness was experimentally demonstrated using various benchmark datasets. [ABSTRACT FROM AUTHOR]

Copyright of Computer Measurement & Control is the property of Magazine Agency of Computer Measurement & Control and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The Internet of Things (IoT) has been widely employed in the development of smart locker systems over the last decade. However, some of these systems are based on authentication methods which lack flexibility. Such systems did not consider the possibility that an authentication method could be unavailable for different reasons, namely access card loss, camera or mice break, etc. Moreover, such systems do not consider dual-authentication methods that enhance security. This paper aims to develop a smart locker system that considers several authentication methods including dual authentication (phone number and One Time Password (OTP)), fingerprint, face recognition, and emergency code utilizing IoT technology. Dual authentication method is the considered base authentication method. The system has been fabricated and evaluated taking into account different scenarios including monitoring door status, ensuring access for authorized users, and denying access to unauthorized users. [ABSTRACT FROM AUTHOR]

This article examines augmented reality filters applied to users' faces, or ARFaces, a visual technology that has spread with increasing success since 2015, mainly through social media. In the first part, the article highlights four significant issues that have emerged about ARFaces: the risks of Body Dysmorphic Disorders linked to beautification filters; the new personal and immediate relationships with brands linked to branded ARFaces; the adoption of filters by a new generation of artists and creatives; and the risks of surveillance related to the face recognition technology on which they are based. The second part of the article argues that ARFaces represent a symptomatic example of 'algorithmic images'. This type of image modifies the logic of 'technical images' that characterised previous media as it shifts the centre of gravity of the processes of the visual constitution from the remote transfer of information to the automated extraction and processing of data. In its conclusions, the article outlines some conceptual tools for dealing with algorithmic images: the author proposes developing a political economy of light and analysing its transformation from a support infrastructure for a political economy of the visual to a supply structure for a data economy. [ABSTRACT FROM AUTHOR]

The following article presents the development of an algorithm embedded in a Raspberry Pi 3B board, where a user identification was made, using the convolutional neural network (CNN) for 5 predefined users, with the option of loading remotely a new network for a new user. Comparatively, the same application was programmed in MATLAB programming software to evaluate the results and identify the advantages between them. Networks were trained for 5 different users, using the Caffe library on the Raspberry Pi, and the MATLAB neural network package on the computer. Where it was found that the training made by Caffe on an embedded system is much slower and less efficient than the ones performed in MATLAB, obtaining less than 55% accuracy with Caffe networks and more than 90% with MATLAB networks, training with the same number of samples, the same architecture, and the same database. Finally, the accuracy obtained through confusion matrix is over 88% in each case of users identification. [ABSTRACT FROM AUTHOR]

By leveraging artificial intelligence and big data to analyze and assess classroom conditions, we can significantly enhance teaching quality. Nevertheless, numerous existing studies primarily concentrate on evaluating classroom conditions for student groups, often neglecting the need for personalized instructional support for individual students. To address this gap and provide a more focused analysis of individual students in the classroom environment, we implemented an embedded application design using face recognition technology and target detection algorithms. The Insightface face recognition algorithm was employed to identify students by constructing a classroom face dataset and training it; simultaneously, classroom behavioral data were collected and trained, utilizing the YOLOv5 algorithm to detect students' body regions and correlate them with their facial regions to identify students accurately. Subsequently, these modeling algorithms were deployed onto an embedded device, the Atlas 200 DK, for application development, enabling the recording of both overall classroom conditions and individual student behaviors. Test results show that the detection precision for various types of behaviors is above 0.67. The average false detection rate for face recognition is 41.5%. The developed embedded application can reliably detect student behavior in a classroom setting, identify students, and capture image sequences of body regions associated with negative behavior for better management. These data empower teachers to gain a deeper understanding of their students, which is crucial for enhancing teaching quality and addressing the individual needs of students. [ABSTRACT FROM AUTHOR]

Face recognition remains a crucial issue in computer vision with various applications. This paper introduces an adapted method to tackle the challenges posed by mask-wearing during the COVID-19 pandemic. We propose modifications to the bag of convolutional neural networks (BoCNN) framework, which combines CNNs and the bag of words (BoW) approach. Our main contribution is customizing the BoCNN algorithm to identify faces with masks by focusing on the visible facial regions, particularly the eyes and eyebrows. Facial landmarks are detected, and the region of interest (ROI) is extracted using techniques such as Media Pipe. A pre-trained CNN is then applied to sections within the ROI, enabling robust feature extraction that captures intricate details such as lighting variations and facial expressions while reducing the impact of mask occlusions. The extracted features are pooled to create a comprehensive representation for recognition. Extensive experiments on the labeled faces in the wild (LFW) dataset, including masked face images, demonstrate the superiority of our adapted BoCNN approach over traditional BoW and deep feature extraction methods, especially accurately recognizing masked faces. Additionally, we assess the generalizability of our method across multiple datasets and discuss potential limitations and future research directions. The proposed BoCNN-based solution proves effective in recognizing masked faces, making it highly relevant for applications in security, human-computer interaction, and various other domains affected by the COVID-19 pandemic. [ABSTRACT FROM AUTHOR]

We assembled a test battery to investigate developmental prosopagnosia (DP), a neurodevelopmental syndrome resulting in severe face recognition difficulties. To screen for general cognitive deficits that could explain poor face test performance, participants completed a fluid reasoning task using abstract shapes. This initial screening showed that DPs (n = 21) were more accurate than neurotypical controls (n = 90) but significantly slower, suggesting speed-accuracy trade-off. To address this, we calculated the Balanced Integration Score and found no group differences, highlighting that DPs clearly adopted a different strategy from controls. DPs’ longer response times (RT) on face tasks vs controls are commonly interpreted as evidence of impairment and of lengthy, atypical featural face processing. Our data suggest this interpretation may be unreliable since clear RT differences were also observed in two non-face tasks where DPs showed no accuracy impairment. Instead, slower RTs appear to reflect a strategy shift in DPs. [ABSTRACT FROM AUTHOR]

The faces we see in daily life exist on a continuum of familiarity, ranging from personally familiar to famous to unfamiliar faces. Thus, when assessing face recognition abilities, adequate evaluation measures should be employed to discriminate between each of these processes and their relative impairments. We here developed the Italian Famous Face Test (IT-FFT), a novel assessment tool for famous face recognition in typical and clinical populations. Normative data on a large sample (N = 436) of Italian individuals were collected, assessing both familiarity (d′) and recognition accuracy. Furthermore, this study explored whether individuals possess insights into their overall face recognition skills by correlating the Prosopagnosia Index-20 (PI-20) with the IT-FFT; a negative correlation between these measures suggests that people have a moderate insight into their face recognition skills. Overall, our study provides the first online-based Italian test for famous faces (IT-FFT), a test that could be used alongside other standard tests of face recognition because it complements them by evaluating real-world face familiarity, providing a more comprehensive assessment of face recognition abilities. Testing different aspects of face recognition is crucial for understanding both typical and atypical face recognition. [ABSTRACT FROM AUTHOR]

In the area of security, human cognition remains essential for face recognition despite advancements in technology. Law enforcement agencies (LEAs) are interested in harnessing these abilities, as recognizing people is a fundamental aspect of their work. We conducted two studies to support integrating human face recognition skills into police work. In study 1, we developed the Zurich Face Cognition Test (ZFCT), a self‐assessment tool that reliably measures the face cognition abilities of police officers with authentic police material. Our approach is complementary to the identification of super‐recognizers. In study 2, we evaluated the Holistic Cognitive Interview (HCI), a method successfully applied in the UK to recognize facial composites better. Our results indicate that the HCI provides an effective strategy for police officers to memorize images of unfamiliar faces more effectively, for example, for better recognition of wanted or missing persons. [ABSTRACT FROM AUTHOR]

As a cornerstone of democratic governance, elections hold unparalleled significance, shaping a nation's trajectory. However, the prevailing ballot-paper based voting systems continue to face trust issues among significant populations. As a result, e-Voting has emerged as an appealing alternative, with numerous countries opting for its implementation globally. While e-Voting systems offer several advantages, they also come with their own set of challenges. Even a minor vulnerability can lead to massive manipulations in voting results. In recent years, there have been efforts to revolutionize the e-Voting paradigm by harnessing the potential of emerging technologies such as biometrics and blockchain. This paper proposes a Internet-based voting that adopts blockchain technology and biometric identification techniques. We use biometric modalities, such as fingerprint and facial recognition, for voter authentication while leveraging Hyperledger Fabric framework as blockchain network and ensuring a secure, transparent, and tamper-evident voting record. We demonstrate the proposed system with 100 participants in a preset environment where we collect the biometrics data. The results indicate that 87% of participants successfully registered with biometrics, while 88% cast their votes with a combination of either voter ID and fingerprint or voter ID with facial recognition. Our findings suggest that the proposed system allows voters to access the system seamlessly and automate identity verification procedures while ensuring a secure, decentralized, and distributed database network that maintains transparency. Future research shall be carried out in collaboration with election officials and voters to improve the system in real-world scenarios. [ABSTRACT FROM AUTHOR]

Objective: To review scientific literature in which controlled cognitive tasks and recording of neurological activity are utilized to evaluate face recognition ability, considering the "other-race effect" (ORE). Methodology: Reflection article, whose methodology is based on a literature review; 15 studies were included for meta-synthesis. Results: It was found that subjective-recollection controlled cognitive tasks, electroencephalography technique, and event-related potentials predominate in face recognition research, considering the ORE. It was also found that oxytocin has no influence on face memory, and that difficulties in recognizing other-race blurred faces correlate with the activation of the fusiform face area (FFA). Conclusions: Neural processing of other-race faces requires more effort, evidenced by larger N250 amplitude, and it is related to N170 component. Furthermore, own-race face recognition is prolonged when these are inverted. of Other-race face processing may be increased by instruction, whereas anger does not improve other-race face memory. This review confirms that both neurophysiology and cultural factors play a crucial role in face recognition and suggests that ORE may be produced by the interaction between these factors. [ABSTRACT FROM AUTHOR]

Pocket Code is a visual programming-based mobile application for creating games, animations, music, videos, and other types of applications. This paper presents the integration of face recognition capabilities into Pocket Code through a visual programming interface based on the FaceNet architecture. The FaceNet dataset is used to train and deploy a face recognition model in Pocket Code visual programming. Integration of the FaceNet algorithm into Pocket Code aims to enhance the accessibility and simplicity of facial recognition technology for students and developers. Building face recognition applications typically involves writing complex code, which can be challenging for both beginners and experienced developers. The Pocket Code visual programming blocks have simplified the process, enabling anyone to easily incorporate face detection into their projects, irrespective of their coding experience. The article discusses the implementation and performance assessment of the FaceNet algorithm in Pocket Code visual programming. [ABSTRACT FROM AUTHOR]

One potential way to enhance the performance of facial expression recognition (FER) is to augment the training set by increasing the number of samples. By incorporating multiple FER datasets, deep learning models can extract more discriminative features. However, the inconsistent labeling criteria and subjective biases found in annotated FER datasets can significantly hinder the recognition accuracy of deep learning models when handling mixed datasets. Effectively perform joint training on multiple datasets remains a challenging task. In this study, we propose a joint training method for training an FER model using multiple FER datasets. Our method consists of four steps: (1) selecting a subset from the additional dataset, (2) generating pseudo-continuous labels for the target dataset, (3) refining the labels of different datasets using continuous label mapping and discrete label relabeling according to the labeling criteria of the target dataset, and (4) jointly training the model using multi-task learning. We conduct joint training experiments on two popular in-the-wild FER benchmark databases, RAF-DB and CAER-S, while utilizing the AffectNet dataset as an additional dataset. The experimental results demonstrate that our proposed method outperforms the direct merging of different FER datasets into a single training set and achieves state-of-the-art performance on RAF-DB and CAER-S with accuracies of 92.24% and 94.57%, respectively. [ABSTRACT FROM AUTHOR]

Facial expressions are important nonverbal behaviors that humans use to express their feelings. Clinical research have shown that depressed patients have poor facial expressiveness and mimicry. As a result, we propose a VFEM experiment with seven expressions to explore variations in facial expression features between depressed patients and normal people, including anger, disgust, fear, happiness, neutrality, sadness, and surprise. It has been discovered through VFEM experiments that depressed patients frequently exhibit negative facial expressions. Meanwhile, we propose a depression facial expression recognition (Dep-FER) model in this research. Dep-FER involves three innovative and crucial components: Mask Multi-head Self-Attention (MMSA), facial action unit similarity loss function (AUs Loss), and case-control loss function (CC Loss). MMSA can filter out disturbing samples and force to learn the relationship between different samples. AUs Loss utilizes the similarity between each expression AU and the model output to improve the generalization ability of the model. CC Loss addresses the intrinsic link between the depressed and normal patient categories. Dep-FER achieves excellent performance in VFEM and outperforms existing comparative models. [ABSTRACT FROM AUTHOR]

As a fine-grained and local expression behavior measurement, facial action unit (FAU) analysis (e.g., detection and intensity estimation) has been documented for its time-consuming, labor-intensive, and error-prone annotation. Thus a long-standing challenge of FAU analysis arises from the data scarcity of manual annotations, limiting the generalization ability of trained models to a large extent. Amounts of previous works have made efforts to alleviate this issue via semi/weakly supervised methods and extra auxiliary information. However, these methods still require domain knowledge and have not yet avoided the high dependency on data annotation. This article introduces a robust facial representation model MAE-Face for AU analysis. Using masked autoencoding as the self-supervised pre-training approach, MAE-Face first learns a high-capacity model from a feasible collection of face images without additional data annotations. Then after being fine-tuned on AU datasets, MAE-Face exhibits convincing performance for both AU detection and AU intensity estimation, achieving a new state-of-the-art on nearly all the evaluation results. Further investigation shows that MAE-Face achieves decent performance even when fine-tuned on only 1% of the AU training set, strongly proving its robustness and generalization performance. The pre-trained model is available at our GitHub repository. [ABSTRACT FROM AUTHOR]

Personality determines various human daily and working behaviours. Recently, a large number of automatic personality computing approaches have been developed to predict either the apparent or self-reported personality of the subject based on non-verbal audio-visual behaviours. However, most of them suffer from complex and dataset-specific pre-processing steps and model training tricks. In the absence of a standardized benchmark with consistent experimental settings, it is not only impossible to fairly compare the real performances of these personality computing models but also makes them difficult to be reproduced. This paper presents the first reproducible audio-visual benchmark to provide a fair and consistent evaluation of eight existing personality computing models (e.g., audio, visual and audio-visual) and seven standard deep learning models on both self-reported and apparent personality recognition tasks. Building upon a set of benchmarked models, we also investigate the impact of two previously-used long-term modelling strategies for summarising short-term/frame-level predictions on personality computing results. We comprehensively investigate all benchmarked models on two publicly available datasets, ChaLearn First Impression and UDIVA self-reported personality datasets, and conclude: (i) apparent personality traits, inferred from facial behaviours by most benchmarked deep learning models, show more reliability than self-reported ones; (ii) visual models frequently achieved superior performances than audio models on personality recognition; (iii) non-verbal behaviours contribute differently in predicting different personality traits; and (iv) our reproduced personality computing models generally achieved worse performances than their original reported results. [ABSTRACT FROM AUTHOR]

One of the most important subconscious reactions, micro-expression (ME), is a spontaneous, subtle, and transient facial expression that reveals human beings’ genuine emotion. Therefore, automatically recognizing ME (MER) is becoming increasingly crucial in the field of affective computing, providing essential technical support for lie detection, clinical psychological diagnosis, and public safety. However, the ME data scarcity has severely hindered the development of advanced data-driven MER models. Despite the recent efforts by several spontaneous ME databases to alleviate this problem, there is still a lack of sufficient data. Hence, in this paper, we overcome the ME data scarcity problem by collecting and annotating a dynamic spontaneous ME database with the largest current ME data scale called DFME (Dynamic Facial Micro-expressions). Specifically, the DFME database contains 7,526 well-labeled ME videos spanning multiple high frame rates, elicited by 671 participants and annotated by more than 20 professional annotators over three years. Furthermore, we comprehensively verify the created DFME, including using influential spatiotemporal video feature learning models and MER models as baselines, and conduct emotion classification and ME action unit classification experiments. The experimental results demonstrate that the DFME database can facilitate research in automatic MER, and provide a new benchmark for this field. [ABSTRACT FROM AUTHOR]

Micro-expression recognition (MER) holds significance in uncovering hidden emotions. Most works take image sequences as input and cannot effectively explore ME information because subtle ME-related motions are easily submerged in unrelated information. Instead, the facial landmark is a low-dimensional and compact modality, which achieves lower computational cost and potentially concentrates on ME-related movement features. However, the discriminability of facial landmarks for MER is unclear. Thus, this article investigates the contribution of facial landmarks and proposes a novel framework to efficiently recognize MEs with facial landmarks. First, a geometric two-stream graph network is constructed to aggregate the low-order and high-order geometric movement information from facial landmarks to obtain discriminative ME representation. Second, a self-learning fashion is introduced to automatically model the dynamic relationship between nodes even long-distance nodes. Furthermore, an adaptive action unit loss is proposed to reasonably build a strong correlation between landmarks, facial action units and MEs. Notably, this work provides a novel idea with much higher efficiency to promote MER, only utilizing graph-based geometric features. The experimental results demonstrate that the proposed method achieves competitive performance with a significantly reduced computational cost. Furthermore, facial landmarks significantly contribute to MER and are worth further study for high-efficient ME analysis. [ABSTRACT FROM AUTHOR]

Facial expression recognition (FER) attracts much attention in computer vision. Previous works mostly study the single-label FER problem. The more complex multi-label facial expression recognition task is underexplored. Multi-label FER is more challenging than single-label task due to two primary causes. On one hand, there are less available multi-label facial expression data for analysis. On the other hand, the entanglement of expressions makes recognition more difficult. In this work, we leverage class activation map (CAM) to improve the performance of multi-label FER. Firstly, considering the shortage of training data, an attention flipping consistency (AFC) loss equipped with random rotation augmentation is proposed. It restrains the network to produce consistent CAMs under horizontally flipping transformation and thus improves the stability of network without any extra data. Secondly, based on the prior knowledge that different emotions have different predominant activated facial regions, we propose a label-guided spatial attention dispersing (SAD) loss to enable the model to learn from distinct expression-related regions. By combining the widely used multi-label classification loss (i.e., binary cross-entropy loss) and proposed AFC loss and SAD loss, our method achieves state-of-the-art performance on multi-label FER databases and the model’s interpretability is improved. [ABSTRACT FROM AUTHOR]

Currently, much progress has been achieved on adult facial expressions recognition. Few attentions have been paid to child facial expression analysis. A lack of publicly available large-scale child facial expression databases hinders the development of automatic coding for child facial expression behaviors. In this work, we constructed a new face database for understanding Child Facial Expression in real World (CFEW). The database contains three novelties: (1) the largest publicly available child facial expression database (11,000+ images); (2) covering full developmental range of 0–18-year-old child subjects; (3) rich annotations for facial expression labels, including discrete expression categories aka happy, neutral, disgust, angry, sad, cry, fear, surprise, sleepy and others, intensity of arousal and valence, and several types of facial action units (AUs). In addition, the images in this database cover several challenging conditions in real world, including frontal and non-frontal head poses, facial occlusions, various illuminations and low image resolution. Three dominant deep convolutional neural networks (i.e., VGG11bn, ResNet18 and DenseNet121) were used to conduct extensive baseline experiments for discrete facial expression classification, arousal and valence estimation and facial action units detection within database, and cross-database seven facial expressions recognition. [ABSTRACT FROM AUTHOR]

Although facial expression recognition based on deep learning has become a major trend, existing methods have been found to prefer learning spurious statistical correlations and non-robust features during training. This degenerates the model's generalizability in practical situations. One of the research fields mitigating such misperception of correlations as causality is causal reasoning. In this article, we propose a learnable counterfactual attention mechanism, CA-FER, that uses causal reasoning to simultaneously optimize feature discrimination and diversity to mitigate spurious correlations in expression datasets. To the best of our knowledge, this is the first work to study the spurious correlations in facial expression recognition from a counterfactual attention perspective. Extensive experiments on a synthetic dataset and four public datasets demonstrate that our method outperforms previous methods, which shows the effectiveness and generalizability of our learnable counterfactual attention mechanism for the expression recognition task. [ABSTRACT FROM AUTHOR]

Imaging of facial affects may be used to measure psychophysiological attributes of children through their adulthood for applications in education, healthcare, and entertainment, among others. Deep convolutional neural networks show promising results in classifying facial expressions of adults. However, classifier models trained with adult benchmark data are unsuitable for learning child expressions due to discrepancies in psychophysical development. Similarly, models trained with child data perform poorly in adult expression classification. We propose domain adaptation to concurrently align distributions of adult and child expressions in a shared latent space for robust classification of either domain. Furthermore, age variations in facial images are studied in age-invariant face recognition yet remain unleveraged in adult-child expression classification. We take inspiration from multiple fields and propose deep adaptive FACial Expressions fusing BEtaMix SElected Landmark Features (FACE-BE-SELF) for adult-child expression classification. For the first time in the literature, a mixture of Beta distributions is used to decompose and select facial features based on correlations with expression, domain, and identity factors. We evaluate FACE-BE-SELF using 5-fold cross validation for two pairs of adult-child data sets. Our proposed FACE-BE-SELF approach outperforms transfer learning and other baseline domain adaptation methods in aligning latent representations of adult and child expressions. [ABSTRACT FROM AUTHOR]

Automatic depression diagnosis is a challenging problem, that requires integrating spatial-temporal information and extracting features from audio-visual signals. In terms of privacy protection, the development trend of recognition algorithms based on facial landmarks has created additional challenges and difficulties. In this article, we propose an audio-visual attention network (AVA-DepressNet) for depression recognition. It is a novel multimodal framework with facial privacy protection, and uses attention-based modules to enhance audio-visual spatial and temporal features. In addition, an adversarial multistage (AMS) training strategy is developed to optimize the encoder-decoder structure. Additionally, facial structure prior knowledge is creatively used in AMS training. Our AVA-DepressNet is evaluated on popular audio-visual depression datasets: AVEC 2013, AVEC 2014, and AVEC 2017. The results show that our approach reaches the state-of-the-art performance or competitive results for depression recognition. [ABSTRACT FROM AUTHOR]

The images in high resolution contain more useful information than the images in low resolution. Thus, high-resolution digital images are preferred over low-resolution images. Image super-resolution is one of the principal techniques for generating high-resolution images. This research investigates the impact of image resolution on the performance of face recognition systems and proposes methods to enhance recognition accuracy on low-resolution face databases. In the first phase, several holistic face recognition algorithms, including Support Vector Machine (SVM), Convolutional Neural Networks (CNN), Artificial Neural Networks (ANN), and RESNET50, are evaluated for their performance on low-resolution face images. Subsequently, three interpolation techniques - nearest neighbor, bilinear, and bicubic interpolant - are applied as preprocessing steps to increase the resolution of the input images. The study aims to determine the effectiveness of these techniques in improving recognition accuracy. Various evaluation metrics, including accuracy, precision, sensitivity, specificity, Peak Signal-to-Noise Ratio (PSNR), Mean Squared Error (MSE), and Structural Similarity Index (SSIM), are employed to assess the performance of the recognition systems. The results demonstrate the efficacy of the proposed approach in enhancing recognition accuracy on low-resolution face datasets, thereby contributing to the advancement of face recognition technology in practical applications. [ABSTRACT FROM AUTHOR]

In recent years, a rise in missing person cases has posed challenges for law enforcement. This paper explores the various issues surrounding many unresolved cases and aims to uncover the contributing factors. Using a detailed analysis of police records, the study identifies patterns and challenges in resolving missing person cases. By understanding these dynamics, law enforcement agencies can refine strategies to enhance the likelihood of resolution, emphasizing the critical need for effective measures in addressing the growing issue of missing persons. Additionally, the paper proposes an innovative approach to locating missing persons using machine learning (ML) algorithms, specifically support vector machine (SVM) and K-nearest neighbors (KNN). Utilizing facial expressions as the basis for model training, the system swiftly and accurately identifies known individuals. The system, fed with a missing person dataset from Kaggle, outputs the person's identity based on features like gender, age and location. The results are then communicated to the police for further investigation. This streamlined approach enhances the efficiency of the search and identification process, contributing to more effective resolutions of missing person cases. The proposed system serves as a valuable tool for law enforcement in expediting investigations and addressing the critical issue of missing persons in a timely and efficient manner. [ABSTRACT FROM AUTHOR]

To enhance the performance and reliability of the face recognition algorithm that is based on deep learning technology, this study utilizes a density-based noise-applied spatial clustering algorithm to cluster a large-scale face image dataset, resulting in a self-constructed dataset. A deep separable center differential convolutional network algorithm is utilized for face recognition. The impact of convolutional parameters on the algorithm's performance is verified through experiments with ablated convolutional parameters. The study found that the density-based noise-applied spatial clustering algorithm resulted in time savings of 43.66% and 51.22% compared to the K-means clustering algorithm and the hierarchical clustering algorithm, respectively, when analyzing 8000 images. Additionally, the depth-separable center difference convolutional network algorithm had a lower average classification error rate compared to the other two algorithms, with reductions of 2.49% and 17.01%, respectively. The depth-separable center difference convolutional network technique is an advanced method for identifying the faces of people of different races, according to the experimental investigation. It can provide efficient and accurate services for the face recognition needs of various races. [ABSTRACT FROM AUTHOR]

In this article, we present an optimal edge-weighted graph semantic correlation (EWGSC) framework for multi-view feature representation learning. Different from most existing multi-view representation methods, local structural information and global correlation in multi-view feature spaces are exploited jointly in the EWGSC framework, leading to a new and high-quality multi-view feature representation. Specifically, a novel edge-weighted graph model is first conceptualized and developed to preserve local structural information in each of the multi-view feature spaces. Then, the explored structural information is integrated with a semantic correlation algorithm, labeled multiple canonical correlation analysis (LMCCA), to form a powerful platform for effectively exploiting local and global relations across multi-view feature spaces jointly. We then theoretically verified the relation between the upper limit on the number of projected dimensions and the optimal solution to the multi-view feature representation problem. To validate the effectiveness and generality of the proposed framework, we conducted experiments on five datasets of different scales, including visual-based (University of California Irvine (UCI) iris database, Olivetti Research Lab (ORL) face database, and Caltech 256 database), text-image-based (Wiki database), and video-based (Ryerson Multimedia Lab (RML) audio-visual emotion database) examples. The experimental results show the superiority of the proposed framework on multi-view feature representation over state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

With the advancement of intelligent technology, CNN-based recognition technology has been integrated into public English teaching in universities. This implementation contributes to enhancing teaching quality, nurturing students' English proficiency, and holds significant educational and practical value. To address the issue of low traditional attendance efficiency in intelligent classrooms for public English teaching, a face recognition model based on CNN recognition technology has been developed. R-CNN is utilized for object detection, along with pyramid pooling and non-maximum suppression to acquire the optimal candidate region for face detection. Furthermore, K-Means clustering is combined to enhance Fast R-CNN, thereby improving detection accuracy. Experimental results demonstrated that among the three networks--Fast R-CNN, Faster R-CNN, and CNN-- Faster R-CNN maintained a high recognition rate and exhibited faster convergence speed, showcasing superior overall performance. Specifically, at 500 iterations, the three networks require 23.7 seconds, 26.8 seconds, and 34.2 seconds, respectively. For facial expression recognition, Faster R-CNN achieved the highest recognition rate, indicating its exceptional detection efficiency and potential for aiding teaching management. This study offers novel technical support for public English teaching in intelligent university classrooms, effectively enhancing teaching efficacy and learning experiences. Its practical significance extends to promoting educational reform and improvement. [ABSTRACT FROM AUTHOR]

In recent times, companies and institutions globally are increasingly adopting automated systems for recording employee attendance due to the inefficiency and error-prone nature of traditional methods. Face recognition is the fastest, most natural, and most accurate way to identify someone, despite its difficulty. Remote deployment and control of the technology using internet of things (IoT) protocols provides real-time attendance data worldwide. We use the Haar-cascade algorithm to detect and extract features and the adaptive boost algorithm confused with convolutional neural network (CNN) algorithm to recognize the face in our proposed smart attendance system. Per frame, the proposed system recognizes multiple faces. Face recognition in 18 conditions was designed into the proposed system to ensure its versatility. The system's graphical user interface (GUI) was made for average users. This work is more important because IoT technology records student attendance and sends data to authorities. We use Raspberry Pi 4 and camera module for our suggested system. Python and OpenCV libraries tested the multiple face image recognition proposal in 18 situations under four conditions. Single-face image recognition was compared to other methods. In most cases, the proposed method was 100% accurate and outperformed related methods. [ABSTRACT FROM AUTHOR]

Abstract A large number of images are available on the Internet with the growth of social networking services, and many of them are face photos or contain faces. It is necessary to protect the privacy of face images to prevent their malicious use by face image de-identification techniques that make face recognition difficult, which prevent the collection of specific face images using face recognition. In this paper, we propose a face image de-identification method that generates a de-identified image from an input face image by embedding facial features extracted from that of another person into the input face image. We develop the novel framework for embedding facial features into a face image and loss functions based on images and features to de-identify a face image preserving its appearance. Through a set of experiments using public face image datasets, we demonstrate that the proposed method exhibits higher de-identification performance against unknown face recognition models than conventional methods while preserving the appearance of the input face images.