Human Face Recognition Research Articles

Abstracting Injustice

In this paper, we explore how the neorepublican concepts of domination and antipower can contribute to the surveillance studies literature and a more democratic and participatory approach to technology development and deployment within the criminal justice system. We frame the neorepublican approach as an alternative to the predominant liberal paradigm, arguing that normative surveillance studies scholarship should emphasize the dominating potential of surveillance practices rather than merely trying to limit actual interference in peoples’ lives. To illustrate, we focus on the use of surveillance technologies that capture images of individuals within the US criminal justice system for recognition and/or identification. Facial or other biometric recognition technologies (FRTs) are increasingly built on artificial intelligence and machine learning algorithms (“AI”). Often seen as a faster, more accurate, and less labor-intensive alternatives to human cognition, AI-powered biometric and facial recognition and other image capture technologies have become widely used within public law enforcement agencies around the world. The deployment of these technologies within the US criminal justice system has produced significant forms of injustice, including faulty identification and the subsequent arrest, detention, and incarceration of innocent individuals. These forms of data injustice are often opaque, hidden behind secretive law enforcement practices or commercial secrecy agreements. We draw from neorepublican conceptions of domination and antipower to frame this legal and technological opacity as an abstraction of injustice. We argue that handing important criminal justice decision-making over to code and algorithms designed, owned, and maintained by private interests exacerbates the potential for the public deployment of unjust systems that subject individuals and communities to unwarranted, arbitrary, and uncontrolled state power. Such government interference represents clear forms of data injustice and domination.

Deep convolutional neural networks are sensitive to face configuration.

Deep convolutional neural networks (DCNNs) are remarkably accurate models of human face recognition. However, less is known about whether these models generate face representations similar to those used by humans. Sensitivity to facial configuration has long been considered a marker of human perceptual expertise for faces. We tested whether DCNNs trained for face identification "perceive" alterations to facial features and their configuration. We also compared the extent to which representations changed as a function of the alteration type. Facial configuration was altered by changing the distance between the eyes or the distance between the nose and mouth. Facial features were altered by replacing the eyes or mouth with those of another face. Altered faces were processed by DCNNs (Ranjan etal., 2018; Szegedy etal., 2017) and the similarity of the generated representations was compared. Both DCNNs were sensitive to configural and feature changes-with changes to configuration altering the DCNN representations more than changes to face features. To determine whether the DCNNs' greater sensitivity to configuration was due to a priori differences in the images or characteristics of the DCNN processing, we compared the representation of features and configuration between the low-level, pixel-based representations and the DCNN-generated representations. Sensitivity to face configuration increased from the pixel-level image to the DCNN encoding, whereas the sensitivity to features did not change. The enhancement of configural information may be due to the utility of configuration for discriminating among similar faces combined with the within-category nature of face identification training.

Syntax and the brain: language evolution as the missing link(ing theory)?

This paper provides proof of concept that neurolinguistic research on human language syntax would benefit greatly by expanding its scope to include evolutionary considerations, as well as non-propositional functions of language, including naming/nicknaming and verbal aggression. In particular, an evolutionary approach can help circumvent the so-called granularity problem in studying the processing of syntax in the brain, that is, the apparent mismatch between the abstract postulates of syntax (e.g. Tense Phrase (TP), Determiner Phrase (DP), etc.) and the concrete units of neurobiology (neurons, axons, etc.). First, we decompose syntax into its evolutionary primitives, identifying one of the earliest stages as a simple, flat combination of just one verb and one noun. Next, we identify proxies ("living fossils") of such a stage in present-day languages, including compounds and small clauses, lacking at least some layers of structure, e.g. TPs and DPs. These proxies of ancestral language have been subjected to fMRI neuroimaging experiments. We discuss the finding that less hierarchical small clauses, in contrast to full sentences with TPs and DPs, show reduced activation in the left Broca's area (BA) 44 and the right basal ganglia, consistent with the hypothesis that more recent, more elaborate syntax requires more connectivity in the Broca's-basal ganglia network, whose neuronal density has been significantly enhanced in recent evolution, implicating mutations in FOXP2 and other genes. We also discuss the finding that the processing of ancestral verb-noun compounds, which are typically used for (derogatory) naming and nicknaming, shows enhanced activation in the right fusiform gyrus area (BA 37), the area that is implicated in the processing of metaphoricity and imageability, but also in naming and face recognition, opening up an intriguing possibility that the enhanced face recognition in humans was facilitated by the early emergence of a simple syntactic strategy for naming. The considerations in this paper are consistent with the hypothesis of a gradual gene-culture co-evolution of syntax and the brain, targeting cortico-striatal brain networks. It is also of note that a sound grounding in neurobiology of language should in turn inform syntactic theories themselves.

Horizontal face information is the main gateway to the shape and surface cues to familiar face identity.

Humans preferentially rely on horizontal cues when recognizing face identity. The reasons for this preference are largely elusive. Past research has proposed the existence of two main sources of face identity information: shape and surface reflectance. The access to surface and shape is disrupted by picture-plane inversion while contrast negation selectively impedes access to surface cues. Our objective was to characterize the shape versus surface nature of the face information conveyed by the horizontal range. To do this, we tracked the effects of inversion and negation in the orientation domain. Participants performed an identity recognition task using orientation-filtered (0° to 150°, 30° steps) pictures of familiar male actors presented either in a natural upright position and contrast polarity, inverted, or negated. We modelled the inversion and negation effects across orientations with a Gaussian function using a Bayesian nonlinear mixed-effects modelling approach. The effects of inversion and negation showed strikingly similar orientation tuning profiles, both peaking in the horizontal range, with a comparable tuning strength. These results suggest that the horizontal preference of human face recognition is due to this range yielding a privileged access to shape and surface cues, i.e. the two main sources of face identity information.

Information sampling differences supporting superior face identity processing ability.

Face recognition in humans is often cited as a model example of perceptual expertise that is characterized by an increased tendency to process faces as holistic percepts. However emerging evidence across different domains of expertise points to a critical role of feature-based processing strategies during the initial encoding of information. Here, we examined the eye-movement patterns of super-recognisers-individuals with extremely high faceidentification ability compared with the average person-using gaze-contingent "spotlight" apertures that restrict visual face information in real time around their point of fixation. As an additional contrast, we also compared their performance with that of facial examiners-highly trained individuals whose superiority has been shown to rely heavily on featural processing. Super-recognisers and facial examiners showed equivalent facematching accuracy in both spotlight aperture and natural viewing conditions, suggesting that they were equally adept at using featural information for faceidentity processing. Further, both groups sampled more information across the face than controls. Together, these results show that the active exploration of facial features is an important determinant of facerecognition ability that generalizes across different types of experts.

Comparing Human Face and Body Recognition at Various Distance and Rotation Viewing Conditions.

Comparing Human Face and Body Recognition at Various Distance and Rotation Viewing Conditions.

Development of an Enhanced Human Face Recognition Model

Abstract Face recognition plays an important role in various areas of life and has attracted the interest of many scholars in the domain of computer vision, pattern recognition, and artificial intelligence. Most of the existing techniques adopted in the recognition of humans through facial images were found to be efficient but are computationally expensive due to the high dimension of facial images, which in turn increases processing speed and memory consumption. In this research, an enhanced model is proposed. Consequently, 6 facial images from 60 individuals were locally acquired using a Canon digital camera of default size 1200 × 1200. Thereafter, 240 images were used for training, while 120 images were used for testing. The enhanced model reduced the high dimension of images with improved feature extraction accuracy. Results showed significant improvement when compared to the existing ones.

Strengthening human‐centered face recognition in law enforcement: Combining the Zurich face cognition test with the holistic cognitive interview

AbstractIn 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.

Surveillance System with Impediment of Face Discovery Using Python

In recent years, It is an active area of research and development with there ongoing and active work on computer vision. This paper presents an empirical literature review of the existing research on human facial recognition as up-to-date. This research start providing the reader with a brief on the uses and working of face recognition. The most recent approaches to facial recognition are then reviewed in the literature. The performance and drawbacks of these face recognition algorithms are also tested through use of the Labelled Wild Face (LWF) face dataset images as well as real time images. With the increasing use of real-time facial recognition systems, it is important to examine the accuracy of these systems given the reliability and 94.23% accuracy are achieved for facial recognition by the proposed model.

Confusion and Diffusion Techniques for Image Encryption Process Based on Chaos System

Face recognition uses biometric technologies to identify humans based on their facial characteristics. This method is commonly used to restrict information access control. The benefits of face recognition systems encompass their ease of use and security. The human face recognition process consists of face detection, face tracking, and face recognition. The process uses some algorithms: the Viola-Jones for face detection, the Kanade-Lucas-Tomasi (KLT) for face tracking, and the principal component analysis (PCA) for face recognition. Furthermore, this research proposed face recognition with an encryption process to protect the data stored in a database. The encryption process consists of two main processes: confusion and diffusion. The confusion process is randomizing the position of the original image pixels. This research utilized the Arnold’s cat map (ACM) for the confusion process, and the diffusion process was performed using the XOR operation with the key generated from the 1D chaos system. Three different 1D chaos systems, namely logistic map, Bernoulli map, and tent map, were compared to see which chaos system had the best encryption results. Tests were conducted by comparing various parameters on the three proposed 1D chaos systems, including correlation coefficient, histogram analysis, entropy value, number of pixel rate changes (NPCR), and unified average change intensity (UACI). Based on testing the image encryption results, the diffusion process utilizing the tent map produced the best image encryption compared to other chaotic systems.

INTRUDER DETECTION SYSTEM USING MACHINE LEARNING

The face is one of the easiest ways to distinguish the individual identity of each other. Face recognition is a personal identification system that uses personal characteristics of a person to identify the person's identity. Human face recognition procedure basically consists of two phases, namely face detection, where this process takes place very rapidly in humans, except under conditions where the object is located at a short distance away, the next is the introduction, which recognize a face as individuals. Stage is then replicated and developed as a model for facial image recognition (face recognition) is one of the much-studied biometrics technology and developed by experts. There are two kinds of methods that are currently popular in developed face recognition pattern namely, Eigenface method and Fisher face method. Facial image recognition Eigenface method is based on the reduction of face dimensional space using Principal Component Analysis (PCA) for facial features. The main purpose of the use of PCA on face recognition using Eigen faces was formed (face space) by finding the eigenvector corresponding to the largest eigenvalue of the face image. The area of this project face detection system with face recognition is Image processing. The software requirements for this project is MATLAB software. Keywords: Digital Image Processing, Face Detection, Face Recognition, Motion Detection

Attendance Management System Using Face Recognition

In the present academic system, regular class attendance of students’ plays a significant role in performance assessment and quality monitoring. The conventional methods are practiced in most of the institutions are by calling nadata reliability. The system is developed by the integration of ubiquitous components to make a portable device for managing the student’s attendance using Face Recognition technology. An automated attendance system for human face recognition in real time background for a college to mark the attendance of their employees and students. So Smart Attendance using Face Recognition is a real world solution which comes with day to day activities of handling employees. Here multiple user faces are detected and recognized with the trained data base multiple texture-based features.

Design and Fabrication of Unmanned Aerial Vehicle for Object Recognition

The innovative realm of unmanned aerial vehicle assisted human face recognition. By amalgamating unmanned aerial vehicle technology and advanced computer vision algorithms, the research presents a robust system capable of detecting and identifying human faces from aerial perspectives. Real-time image processing and artificial intelligence methodologies are harnessed to ensure accurate performance across diverse environmental conditions. The proposed framework showcases its potential in surveillance, search and rescue missions, and crowd monitoring. Ethical considerations, limitations, and effectiveness are scrutinized through empirical evaluations, contributing valuable insights to the discourse surrounding privacy, security, and responsible unmanned aerial vehicle utilization.

Mathematics for 2D face recognition from real time image data set using deep learning techniques

The recognition of human faces poses a complex challenge within the domains of computer vision and artificial intelligence. Emotions play a pivotal role in human interaction, serving as a primary means of communication. This manuscript aims to develop a robust recommendation system capable of identifying individual faces from rasterized images, encompassing features such as eyes, nose, cheeks, lips, forehead, and chin. Human faces exhibit a wide array of emotions, with some emotions, including anger, sadness, happiness, surprise, fear, disgust, and neutrality, being universally recognizable. To achieve this objective, deep learning techniques are leveraged to detect objects containing human faces. Every human face exhibits common characteristics known as Haar features, which are employed to extract feature values from images containing multiple elements. The process is executed through three distinct stages, starting with the initial image and involving calculations. Real-time images from popular social media platforms like Facebook are employed as the dataset for this endeavor. The utilization of deep learning techniques offers superior results, owing to their computational demands and intricate design when compared to classical computer vision methods using OpenCV. The implementation of deep learning is carried out using PyTorch, further enhancing the precision and efficiency of face recognition.

A Hybrid Approach based on Haar Cascade, Softmax, and CNN for Human Face Recognition

A Hybrid Approach based on Haar Cascade, Softmax, and CNN for Human Face Recognition

Effective approach of face mask position detection and recognition

During recent COVID-19 pandemic across the world, face masks became necessary to stop the spread of infection. This has led to challenges with effective detection and recognition of human faces using the existing face detection systems. This paper proposes a Convolutional Neural Network (CNN) based face mask recognition system, which offers two solutions—recognition of the person wearing face mask and position of face mask i.e., whether the mask is correctly worn or not. The proposed model could play instrumental role of face recognition. In the first stage, with the help of Viola-Jones algorithm, the model detects the position of the face mask. In the second stage, we identify the person with by a modified pre-trained face mask recognition DeepMaskNet model facilitates in identifying the person. The proposed model achieves an accuracy of 94% in detecting the face mask position and 99.96% in identifying the masked person. Lastly, a comparison with the existing models is detailed, proving that the proposed model achieves the highest greater performance.

Ape recognition of familiar human faces changed by time and COVID-19 face masks

Reports of primates being able to recognise familiar humans are rare in the literature and tend to be regarded as anecdotal. The COVID-19 pandemic created two unique conditions facilitating the observation of spontaneous face recognition in zoo apes: i) lengthy gaps in contact with human visitors due to lockdowns and zoo closures, and ii) the wearing of face masks obscuring at least half the face of familiar individuals. Here, I report on the historical context of the familiarity between a primatologist and individual apes of two species, how those apes consistently showed recognition of this particular human over a time span of up to thirty years, how facial recognition was extended to family members, and how recognition persisted even when a significant portion of the face was obscured by a mask. This constitutes, to my knowledge, the first documented cases of recognition of familiar human faces changed by time and COVID-19 face masks in two great ape species. Although based on just two individuals, the documentation of this ability is important because it arose in a more naturalistic and spontaneous context compared to typical face processing research in which primates are tested with experimental stimuli in a laboratory setting. Implications for face processing theory and applications for the therapeutic utility of faces are discussed. These observations provide insight into the evolutionary origins of face recognition and, sitting at the interface of science and society, are of interest to a wide audience.

Facial mask-wearing prediction and adaptive gender classification using convolutional neural networks

The world has lived an exceptional time period caused by the Coronavirus pandemic. To limit Covid-19 propagation, governments required people to wear a facial mask outside. In facial data analysis, mask-wearing on the human face creates predominant occlusion hiding the important oral region and causing more challenges for human face recognition and categorisation. The appropriation of existing solutions by taking into consideration the masked context is indispensable for researchers. In this paper, we propose an approach for mask-wearing prediction and adaptive facial human-gender classification. The proposed approach is based on convolutional neural networks (CNNs). Both mask-wearing and gender information are crucial for various possible applications. Experimentation shows that mask-wearing is very well detectable by using CNNs and justifies its use as a prepossessing step. It also shows that retraining with masked faces is indispensable to keep up gender classification performances. In addition, experimentation proclaims that in a controlled face-pose with acceptable image quality' context, the gender attribute remains well detectable. Finally, we show empirically that the adaptive proposed approach improves global performance for gender prediction in a mixed context.

Disentangled deep generative models reveal coding principles of the human face processing network.

Despite decades of research, much is still unknown about the computations carried out in the human face processing network. Recently, deep networks have been proposed as a computational account of human visual processing, but while they provide a good match to neural data throughout visual cortex, they lack interpretability. We introduce a method for interpreting brain activity using a new class of deep generative models, disentangled representation learning models, which learn a low-dimensional latent space that "disentangles" different semantically meaningful dimensions of faces, such as rotation, lighting, or hairstyle, in an unsupervised manner by enforcing statistical independence between dimensions. We find that the majority of our model's learned latent dimensions are interpretable by human raters. Further, these latent dimensions serve as a good encoding model for human fMRI data. We next investigate the representation of different latent dimensions across face-selective voxels. We find that low- and high-level face features are represented in posterior and anterior face-selective regions, respectively, corroborating prior models of human face recognition. Interestingly, though, we find identity-relevant and irrelevant face features across the face processing network. Finally, we provide new insight into the few "entangled" (uninterpretable) dimensions in our model by showing that they match responses in the ventral stream and carry information about facial identity. Disentangled face encoding models provide an exciting alternative to standard "black box" deep learning approaches for modeling and interpreting human brain data.

Analysis of Human Facial Emotion Recognition along with sound Recognition Using VGG Face and MFCC

The identification of human emotions is pivotal in several domains, including interactions between humans and computers, medical settings, and the entertainment industry. Lately, combining the study of facial expressions with the examination of emotions through voice has attracted considerable interest for its ability to improve the precision and reliability of emotion detection systems. This project suggests an in-depth examination of recognizing human emotional states through facial expressions alongside auditory signal analysis, utilizing the VGG Face model and the technique of Mel-Frequency Cepstral Coefficients (MFCC) for feature extraction, all driven by algorithms based on machine learning