Face Recognition Research Articles

Social Interaction Anxiety in Developmental Prosopagnosia: Prevalence, Severity, and Individual Differences.

Although elevated social anxiety in developmental prosopagnosia (DP) has been reported in anecdotal and qualitative studies, the current study sought to better quantify the prevalence, severity, and moderators of social anxiety in a large DP sample. A total of 88 DPs and 58 controls completed the validated Social Interaction Anxiety Scale and assessments of face recognition, autism traits, personality (Big Five Inventory), and coping strategies. DPs reported greater social anxiety symptoms (M = 30.25) than controls (M = 17.19), with 44% of DPs above a probable clinical cutoff compared with 14% of controls. Exploratory analyses revealed that DPs' social anxiety was more specific to items pertaining to mixing socially or interacting with unfamiliar people. Notably, several DPs reported minimal social anxiety, which was associated with being more extraverted and having fewer autism traits. A follow-up survey revealed that extraverted DPs more openly disclosed face recognition inabilities than introverted DPs, which may be a factor in their reduced social anxiety. These results better quantify the potential serious psychosocial consequences of DP and highlight the importance of individual differences as well as targeted intervention.

Serial Multimodal Biometrics Authentication and Liveness Detection Using Speech Recognition with Normalized Longest Word Subsequence Method

Biometric authentication aims to verify whether an entity matches the claimed identity based on biometric data. Despite its advantages, vulnerabilities, particularly those related to spoofing, still exist. Efforts to mitigate these vulnerabilities include multimodal approaches and liveness detection. However, these strategies may potentially increase resource requirements in the authentication process. This paper proposes a multimodal authentication process incorporating voice and facial recognition, with liveness detection applied to voice data using speech recognition. This paper introduces Normalized Longest Word Subsequence (NLWS), a combination of Intersection Over Union (IOU) and the longest common subsequence, to compare the prompted system sentence with the user's spoken sentence at speech recognition. Unlike the Word Error Rate (WER), NLWS has a measurable range between 1 and 0. Furthermore, the paper introduces decision-level fusion in the multimodal approach, employing two threshold levels in voice authentication. This approach aims to reduce resource requirements while enhancing the overall security of the authentication process. This paper uses cosine similarity, Euclidean distance, random forest, and extreme gradient boosting (XGBoost) to measure distance or similarity. The results show that the proposed method has better accuracy compared to unimodal approaches, achieving accuracies of 98.44%, 98.83%, 97.46%, and 99.22% using cosine similarity, Euclidean distance, random forest, and XGBoost calculations. The proposed method also demonstrates resource savings, reducing from 5.19 MB to 0.792 MB, from 7.3294 MB to 1.9437 MB, from 6.6512 MB to 1.3284 MB, and from 7.8632 MB to 2.1517 MB in different distance or similarity measurements

Enhancing cell phone security through finger vein biometric authentication systems

The growing demand for secure mobile devices has led to the widespread adoption of biometric technologies. While personal identification numbers (PINs), passwords, gridlock patterns to safeguard phones and facial recognition have become common, they have certain limitations in terms of security and user convenience. These conventional security measures are riddled with susceptibilities, such as password pilferage, memory lapses in authentication details, and user mistakes in grid pattern creation. Due to the rising occurrence of cell phone incursions and theft, there is an urgent requirement for a strong security system that not only defends data but also shields the device itself. This paper proposes a resilient finger vein biometric security system as a more effective substitute for knowledge-based and password-based authentication techniques. The implementation of finger vein biometrics as a novel approach to enhancing cell phone security. The method employs infrared (IR) light transmission to capture the vein patterns and shadows resulting from the different thicknesses of finger muscles, bones, and tissues. The unique vascular patterns in fingers are difficult to forge, offering a higher level of security compared to other biometric systems. The simulations we conducted indicate an identification accuracy rate of 93.82%, indicating that this technique provides a substantial enhancement in preventing unauthorized access and theft of cell phones. This study examines the technology behind finger vein biometrics, its integration into mobile devices, and the security advantages it offers.

Forensic facial identification – reconstruction of facial geometry and shape from dental dimensions

Human identification has always remained as a main task of forensic anthropology and forensic science for various purposes. The purpose of human identification may vary from legal identity to disaster victim identification, from criminal identity to unidentified deceased identification. The condition, such as putrefaction, charring and mutilation of corpse always become an obstacle during the process of identification. Due to surviving nature of teeth, they may serve as evidence for identification in highly decomposed conditions. Therefore, a cross-sectional study was conducted on 207 participants (93 males and 114 females) in the age range of 21 to 45 years with the aim of two-dimensional facial reconstruction. Dental casts, anthropometric facial measurements and facial photographs were obtained from the participants. Dental measurements were taken on the cast in the laboratory. Statistical analysis revealed a weak but statistically significant correlation between the dental and facial parameters. The geometrical faces and the shapes were reconstructed based on the dental dimensions. The reconstructed facial geometry and shapes were very similar to the true facial geometry and facial shapes of the individual. By improving identification of disaster victims and unidentified deceased, the results of the study can have considerable implications in forensic and medico-legal case-works.

Challenges for automated face recognition systems

Challenges for automated face recognition systems

Flexible use of facial features supports face identity processing.

People prioritize diagnostic features in classification tasks. However, it is not clear whether this priority is fixed or is flexibly applied depending on the specific classification decision, or how feature use behavior contributes to individual differences in performance. Here we examined whether flexibility in features used in a face identification task supports face recognition ability. In Experiment 1, we show that the facial features most useful for identification vary-to a surprising degree-depending on the specific face identity comparison at hand. While the ears and eyes were the most diagnostic for face identification in general, they were the most diagnostic feature for just 22% and 14% of identity decisions, respectively. In three subsequent experiments, we find that flexibility in feature use contributes to an individual's face identity matching ability. Higher face identification accuracy was associated with being aware of (Experiments 2 and 4) and attending to (Experiments 3 and 4) the most diagnostic features for a specific facial comparison. This conferred an enhanced benefit relative to focusing on features that were diagnostic of face identity decisions in general (Experiment 4). We conclude that adaptability in information sampling supports face recognition ability and discuss theoretical and applied implications. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Validity Study of an Emotional Face-Database in Iranian Community

Objective: To investigate the accuracy of facial emotion recognition in the Iranian community, a face database validated in this community is required. To do this, we conducted a validation study on the Radboud face database. The primary objective of this study was to evaluate the accuracy of recognizing emotions through faces in an Iranian sample and then to choose the pictures with high agreement in terms of detecting emotions. Method: This is a cross sectional study recruiting a total number of 142 males and females aged between 20 and 50 years old (Mean ± SD of age 31.7 ± 7.07). The participants were instructed to detect the type of emotion of each face as well as its valence and arousal. The percentage of participants’ agreement on evaluating each picture was assessed. To evaluate the effect of different variables on participants’ accuracy, one way and repeated measure ANOVA analyses were also used. Results: Emotional faces were recognized by around 84% of the participants. The highest accuracy belongs to happy (Mean ± SD of 98 ± 6.1%) and the lowest one to neutral (75 ± 18.06%) faces. The accuracy for detecting other emotions were as follows: sad (91 ± 8.7%), surprised (87 ± 10.64%), angry (77 ± 15.6%), and fearful (76 ± 15.26%). Additionally, we found no differences between male and female participants in terms of recognizing emotions. Then we selected the pictures with high agreement (above 85 percent) in labeling emotions among the participants. Conclusion: The current study provided a valid emotional face database based on Iranian participants’ responses in terms of recognizing basic emotions. The selected pictures can be used in designing tasks to evaluate emotion recognition ability in clinical and nonclinical populations. It can also be used in designing applications to improve detecting emotion in clinical samples such as individuals with autism spectrum disorder.

A lightweight attention-based deep learning facial recognition system for multiple genetic syndromes

A lightweight attention-based deep learning facial recognition system for multiple genetic syndromes

A Comprehensive Survey of Masked Faces: Recognition, Detection, and Unmasking

Masked face recognition (MFR) has emerged as a critical domain in biometric identification, especially with the global COVID-19 pandemic, which introduced widespread face masks. This survey paper presents a comprehensive analysis of the challenges and advancements in recognizing and detecting individuals with masked faces, which has seen innovative shifts due to the necessity of adapting to new societal norms. Advanced through deep learning techniques, MFR, along with face mask recognition (FMR) and face unmasking (FU), represents significant areas of focus. These methods address unique challenges posed by obscured facial features, from fully to partially covered faces. Our comprehensive review explores the various deep learning-based methodologies developed for MFR, FMR, and FU, highlighting their distinctive challenges and the solutions proposed to overcome them. Additionally, we explore benchmark datasets and evaluation metrics specifically tailored for assessing performance in MFR research. The survey also discusses the substantial obstacles still facing researchers in this field and proposes future directions for the ongoing development of more robust and effective masked face recognition systems. This paper serves as an invaluable resource for researchers and practitioners, offering insights into the evolving landscape of face recognition technologies in the face of global health crises and beyond.

The effect of cerebellar lesıons on language in Turkısh speakıng indıvıduals

ABSTRACT Background The cerebellum is approximately 10% of the brain volume and is responsible for attention, language, emotion and cognitive functions. Linguistic processing difficulties and cognitive impairments may be observed in individuals with cerebellar lesions depending on the location and severity of the damage. There is no study evaluating language in Turkish-speaking individuals with cerebellar lesions. Objective To determine the differences in linguistic and visuospatial skills of Turkish speaking individuals with cerebellar lesions compared to control groups, including a right hemisphere lesion group and a healthy control group. Method Fifteen patients with cerebellar lesion (without hemispatial neglect and dysarthria), 15 patients with right hemisphere lesion due to right arter cerebri media (without hemispatial neglect) and 15 healthy control were included. To clarify the language impairment specific to cerebellar lesions, we also included individuals with right hemisphere lesions, which are typically assumed not to present with aphasia. The Language Assessment Test for Aphasia (ADD), Benton Judgment of Line Orientation Test, Benton Facial Recognition Test, Single Letter Deletion Test were used. The “Accident Scene” picture was used for collecting narrative speech samples. After a three group comparison a post-hoc pairwise analysis was performed. Results Among the microstructural parameters in the narrative language analysis, the effort ratio was significantly higher in the cerebellar lesion group compared to the healthy control group. Among the non-verbal cognitive tests, the Benton Facial Recognition Test score was significantly lower in the cerebellar and right hemisphere lesion group compared to the healthy control group. Total score, naming and grammar scores in the ADD test were significantly lower in the cerebellar lesion group compared with the healthy control group. There was no difference between cerebellar and right hemisphere lesions in terms of ADD score, ADD subtests and narrative parameters. Conclusion In Turkish-speaking individuals with cerebellar lesions, verbal productivity may be interrupted by effort behaviours, and standard aphasia assessment tests may reveal impaired grammar and naming performance without a diagnosis of aphasia. In addition to reduced efficiency in verbal production, facial recognition may be impaired. We found no difference between individuals with lesions in the cerebellum and right hemisphere. This suggests that ischemic damage may affect different components of language independently of the diagnosis of aphasia.

Preventing Impersonation in Exams through Face Recognition Technology

Preventing Impersonation in Exams through Face Recognition Technology

RFID-transformer recognition system (RTRS): enhancing privacy in facial recognition with transformer models

RFID-transformer recognition system (RTRS): enhancing privacy in facial recognition with transformer models

Masked face recognition based on knowledge distillation and convolutional self-attention network

Masked face recognition based on knowledge distillation and convolutional self-attention network

Face recognition method based on fusion of improved MobileFaceNet and adaptive Gamma algorithm

MobileFaceNet face recognition algorithm is a relatively mainstream face recognition algorithm at present. Its advantages of small memory and fast running speed make it widely used in embedded devices. Due to the limited face image acquisition capability of embedded devices, the accuracy of face recognition is often reduced due to uneven illumination and poor exposure quality. In order to solve this problem, a face recognition algorithm based on the fusion of MobileFaceNet and adaptive Gamma algorithm is proposed. The application of the algorithm proposed in this paper in image preprocessing is as follows. Firstly, adaptive Gamma correction is used to improve the brightness of the face image. Then, the edge of the face image is enhanced by the Laplace operator. Finally, a linear weighted fusion was performed between the Gamma corrected image and the enhanced edge image to obtain the pre-processed face image. At the same time, we have improved the traditional MobileFaceNet network. The feature extraction network MobileFaceNet has been improved by adding a Stylebased Recall Module (SRM) attention mechanism to its bottom neck layer, utilizing the mean and standard deviation of input features to improve the ability to capture global information and enhance more important feature information. Finally, the proposed method was verified on the LFW and Agedb face test set. The experimental results show that the adaptive Gamma algorithm proposed in this paper and the improvement of MobileFaceNet can achieve a face recognition accuracy of 99.27 % on LFW dataset and 90.18 % on Agedb dataset while only increasing the model size by 0.4 M and the processing speed for each image is enhanced by 4 ms. which can effectively improve the accuracy of face recognition and better application prospects on embedded devices. The method presented in this article has certain practical significance.

Dynamic Routing and Knowledge Re-Learning for Data-Free Black-Box Attack.

Deep learning models have emerged as strong and efficient tools that can be applied to a broad spectrum of complex learning problems and many real-world applications. However, more and more works show that deep models are vulnerable to adversarial examples. Compared to vanilla attack settings, this paper advocates a more practical setting of data-free black-box attack, for which the attackers can completely not access the structures and parameters of the target model, as well as the intermediate features and any training data associated with the model. To tackle this task, previous methods generate transferable adversarial examples from a transparent substitute model to the target model. However, we found that these works have the limitations of taking static substitute model structure for different targets, only using hard synthesized examples once, and still relying on data statistics of the target model. This may potentially harm the performance of attacking the target model. To this end, we propose a novel Dynamic Routing and Knowledge Re-Learning framework (DraKe) to effectively learn a dynamic substitute model from the target model. Specifically, given synthesized training samples, a dynamic substitute structure learning strategy is proposed to adaptively generate optimal substitute model structure via a policy network according to different target models and tasks. To facilitate the substitute training, we present a graph-based structure information learning to capture the structural knowledge learned from the target model. For the inherent limitation that online data generation can only be learned once, a dynamic knowledge re-learning strategy is proposed to adjust the weights of optimization objectives and re-learn hard samples. Extensive experiments on four public image classification datasets and one face recognition benchmark are conducted to evaluate the efficacy of our Drake. We can obtain significant improvement compared with state-of-the-art competitors. More importantly, our DraKe consistently achieves attack superiority for different target models (e.g., residual networks, and vision transformers), showing great potential for complex real-world applications.

Exploring Machine Learning and Deep Learning Techniques for Occluded Face Recognition: A Comprehensive Survey and Comparative Analysis

Face recognition occluded by occlusions, such as glasses or shadows, remains a challenge in many security and surveillance applications. This study aims to analyze the performance of various machine learning and deep learning techniques in face recognition scenarios with occlusions. We evaluate KNN (standard and FisherFace), CNN, DenseNet, Inception, and FaceNet methods combined with a pre-trained DeepFace model using three public datasets: YALE, Essex Grimace, and Georgia Tech. The results show that KNN maintains the highest accuracy, reaching 100% on two datasets (Essex Grimace and YALE), even in the presence of occlusions. Meanwhile, CNN shows strong performance, with accuracy remaining 100% on YALE, both with and without occlusions, although its performance drops slightly on Essex Grimace (94% with occlusion). DenseNet and Inception show a more significant drop in accuracy when faced with occlusion, with DenseNet dropping from 81% to 72% on Essex Grimace and Inception dropping from 100% to 92% on the same dataset. FaceNet + DeepFace excels on more large dataset (Georgia Tech) with 98% accuracy, but its performance drops dramatically to 53% and 70% on Essex Grimace and YALE with occlusion. These findings indicate that while deep learning methods show high accuracy under ideal conditions, machine learning methods such as KNN are more flexible and robust to occlusion in face recognition.

Comparative Dissection of Local Binary Pattern Using Face Recognition System Survey

Comparative Dissection of Local Binary Pattern Using Face Recognition System Survey

Face Recognition Technology Ethical Governance Issues

Face Recognition Technology Ethical Governance Issues

Advancing Face Recognition Technologies: The Role of Decision Trees in Classifying Complex Image Pairs

The advancement of face recognition technologies has been pivotal in various applications, from security systems to personalized user experiences. There are significant efforts already devoted to solving challenges of multimodality and pose variation in face recognition. Some studies focus on multimodality but pose-invariant, and other studies focus on pose variation but single modality. Despite significant progress, various face recognition algorithms do not consider both multimodality and pose variation constraints in their proposed methods. Recognizing face images presented both in a different modality and in a different pose presents serious challenges to current algorithms. This paper proposes an algorithm that combines the strengths of deep learning with decision trees to improve face recognition performance across modalities and poses in constrained and unconstrained environments. This hybrid approach leverages the representational power of deep learning and the interpretability and simplicity of decision trees. The findings indicate significant improvements over existing methodologies, particularly in challenging conditions like when multimodality and pose variation constraints are compounded together in the input face images in both constrained and unconstrained environments. The proposed algorithm not only addresses the limitations of current face recognition systems but also offers scalable, efficient solutions suitable for real-world applications.

A Domain Generalized Face Anti-Spoofing System Using Domain Adversarial Learning

This research addresses the enhancement of face anti-spoofing (FAS) in facial recognition systems (FRS) against sophisticated fraudulent activities. Prior methods primarily focus on extracting facial features like color, texture, and dynamic variations, yet these methods struggle to accurately identify common characteristics of forged faces, thereby limiting generalization in practical scenarios. This study aims to propose a novel representation learning framework incorporating adversarial learning algorithms, to segregate features into liveness-specific and domain-specific categories, emphasizing liveness-specific features for FAS advancement. Feature disentanglement is central to this approach, enabling the deep learning models to effectively discern separable latent generating factors, such as identity, liveness, appearance, and texture. This methodology enhances model interpretability, explainability, and generalization. Additionally, Grad-CAM is employed to elucidate the basis for classifications made by the architecture, increasing explainability and trustworthiness. Empirical evaluation across panoply available FAS datasets confirms the superiority, significantly improving performance and robustness over existing technologies.