Facial Expressions Research Articles

Eye closures in spoken Hebrew

Abstract The present study focuses on eye closure (EC) as a communicative facial gesture in Israeli Hebrew media talk and pays particular attention to its coordination with co-expressive verbal, prosodic, and embodied resources. Drawing on the interactional approach to language and embodied action, the study demonstrates that EC can convey four contextual meanings — concentration, hedging, negation, and totality — depending on the context in which it occurs and the verbal material with which it is co-produced. The paper proposes that these contextual meanings are derived from the more general meaning of disengagement conveyed by EC. Moreover, the present paper suggests several potential semiotic connections between the basic physiological use of EC as a reflex of self-protection and evasion and its observed contextual meanings. This provides evidence for the co-optation of the basic functions of facial gestures for communicative purposes via metaphorical-metonymical extensions.

Automatic Facial Expression Recognition Using Modified LPQ and HOG Features with Stacked Deep Convolutional Autoencoders

Automatic Facial Expression Recognition Using Modified LPQ and HOG Features with Stacked Deep Convolutional Autoencoders

The Power of a Smile: Exploring the Connection between Teacher Facial Expressions and ESL Learning

This research was designed to determine the impact of smiling by an ESL teacher on students' learning achievement. Ten males and six females were interviewed using semi-structured interviews. All of them were students of a higher education program in the United Arab Emirates for the study. The findings suggested that a smile is a major part that can lead to better learning outcomes and affirmed the positive psychology theory. In addition, it was ascertained that a smiling teacher leads to positive changes in attitude; learning climate; motivation and involvement; rapport with the subject; reduction in stress; anxiety; fear and anger; and an improvement in trust and respect. Higher learning outcomes may be achieved through any of these ways. This conceptual model is conducive to empirical research study as presented in this research.

Enhanced facial expression recognition using transfer learning and M-CLAHE

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

Gesture Imitation Performance and Visual Exploration in Young Children with Autism Spectrum Disorder.

Most studies in children with autism spectrum disorder (ASD) support a decrement in imitation performance. Factors related to visual attention and motor execution have been proposed to explain this phenomenon in ASD. However, studies investigated imitation with various methods, leading to inconsistent findings. Here, we examine imitation performance related to visual attention and motor execution. We focused on the imitation of meaningful and meaningless gestures, consistently reported as more affected than imitation of actions with objects in ASD. The imitation eye-tracking task consisted of a video of an actor demonstrating gestures and prompting children to imitate them. The demonstrations comprised meaningful and meaningless hand gestures, and meaningless facial gestures. We measured the fixation duration to the actor' face during child-directed speech and gesture demonstrations. We video-recorded children to assess their performance. Our sample comprised 100 participants (3.55 ± 1.11years old), including 84 children with ASD. The ASD and typically developing groups displayed the same visual attention toward gesture demonstrations, although children with ASD spent less time looking at the face during facial stimuli. Visual exploration of actors' gestures did not influence imitation performance. Imitation of meaningful gestures was associated with less severe autistic symptoms, whereas imitation of meaningless gestures was correlated with higher non-verbal cognitive and fine-motor skills. These findings contribute to a better understanding of the complexity of imitation. We delineated the distinct nature of imitation of meaningful and meaningless gestures in children with ASD. We discuss clinical implications in relation to assessment and intervention programs.

Facial expression recognition based on convolutional network attention mechanism

Aiming at the problems of large number of parameters and weak recognition ability in expression recognition, a method of facial expression recognition based on convolutional network is proposed. An improved residual module is introduced to reduce the number of parameters while enhancing the attention to the expression area; the channel-space attention mechanism is used to realize the weight distribution of different dimensions and positions of the expression area extracted by the network, focusing on the subtle difference feature information in the key points of the expression; the detail module is used to further extract the deep feature information. In order to obtain higher accuracy, a joint loss function is introduced to increase the out-of-class distance and reduce the intra-class distance to improve the accuracy of expression recognition. This paper applies this network to the datasets FER2013 and CK+. The experimental results show that the average recognition rate of this algorithm is respectively and 63.91%，97.98%the number of parameters is 11.34 M. Compared with VGG network, residual network, etc., this model not only improves the recognition rate but also reduces the redundant parameters.

Less can be more: representational vs. stereotypical gender bias in facial expression recognition

AbstractMachine learning models can inherit biases from their training data, leading to discriminatory or inaccurate predictions. This is particularly concerning with the increasing use of large, unsupervised datasets for training foundational models. Traditionally, demographic biases within these datasets have not been well-understood, limiting our ability to understand how they propagate to the models themselves. To address this issue, this paper investigates the propagation of demographic biases from datasets into machine learning models. We focus on the gender demographic component, analyzing two types of bias: representational and stereotypical. For our analysis, we consider the domain of facial expression recognition (FER), a field known to exhibit biases in most popular datasets. We use Affectnet, one of the largest FER datasets, as our baseline for carefully designing and generating subsets that incorporate varying strengths of both representational and stereotypical bias. Subsequently, we train several models on these biased subsets, evaluating their performance on a common test set to assess the propagation of bias into the models’ predictions. Our results show that representational bias has a weaker impact than expected. Models exhibit a good generalization ability even in the absence of one gender in the training dataset. Conversely, stereotypical bias has a significantly stronger impact, primarily concentrated on the biased class, although it can also influence predictions for unbiased classes. These results highlight the need for a bias analysis that differentiates between types of bias, which is crucial for the development of effective bias mitigation strategies.

Reanimation Techniques of Peripheral Facial Paralysis: A Comprehensive Review Focusing on Surgical and Bioengineering Approaches.

Peripheral facial paralysis represents a disabling condition with serious psychological and social impact. Patients with peripheral facial paralysis have a disfigurement of the face with loss of harmony and symmetry and difficulties in everyday facial functions such as speaking, drinking, laughing, and closing their eyes, with impairment of their quality of life. This paralysis leads to impairment of facial expression, which represents one of the first means of communication, an important aspect of human interaction. This review aims to explore the reanimation techniques for managing peripheral facial paralysis. An analysis of static and dynamic techniques for facial reanimation is provided, including muscle flaps, nerve grafting techniques, and bioengineering solutions. Each technique showed its benefits and drawbacks; despite several options for facial reanimation, no technique has been detected as the gold standard. Therefore, each patient must be evaluated on an individual basis, considering their medical history, age, expectations, and treatment goals, to find the best and most fitting treatment.

Different Effects of Attachment Anxiety and Avoidance on Attention to Changing Facial Expressions

AbstractAttachment orientation has been reported to influence visual attention and cognitive decisions regarding facial expressions. However, previous studies have reported mixed results regarding the effects of attachment orientation. This study aims to examine how attachment anxiety and avoidance affect judgment and attention allocation during free viewing of dynamic facial expressions. Although we did not find any association between attachment orientation and the reaction time to judge the timings of changes in facial expressions, the relationship between attachment orientation and attention was found. When viewing the appearance of anger, attachment avoidance had a positive relationship and attachment anxiety had a negative relationship with looking time to the eye area. When the eye‐tracking data were divided into 12 consecutive intervals of 1 s each, the attachment orientation had different relationships with visual attention based on the type of emotion presented. We discuss possible explanations for these results and directions for further research in cross‐cultural contexts.

Ultrasensitive Ultrasoft Buckled Crack‐Based Sensor for Respiration Measurement and Enhanced Human–Machine Interface

Wearable strain sensors have transformed the real‐time monitoring of health conditions and human–machine interactions. However, recently developed wearable strain sensors exhibit several limitations. For example, when a sensor is designed with high sensitivity to detect strain, it struggles to accurately measuring the deformation of low‐stiffness materials like skin. Additionally, finding the optimal balance between sensitivity, durability, hysteresis, and strain range in sensor design is challenging. To address these challenges, a Buckled, Ultrasoft, Crack‐based, Large strain, EpiDermal (BUCKLED) sensor is developed. This sensor integrates the benefits of soft structure engineering with high sensitivity of crack‐based sensing mechanisms to ensure optimal skin deformation measurements. The BUCKLED sensor exhibits significant improvements in compliance (18 500 mm N−1), stretchability (100%), hysteresis (2%), durability (10 000 cycles with 100% strain), and force sensitivity () owing to its buckled shape, confirming its ability to detect subtle movements with enhanced accuracy. The sensor's high compliance allows it to accurately measure low‐stiffness objects, ensuring reliable performance. Furthermore, the sensor's tunability is demonstrating its effectiveness in applications such as respiratory monitoring, facial expression recognition, and silent speech interfaces. Consequently, the proposed sensor is versatile and holds great potential for a wide range of sensing applications.

Exploring the application of synchronous analysis of physiological signals and facial expressions in emotion recognition

In today's increasingly frequent human-computer interaction, the accurate recognition and response of intelligent systems to human emotions has become the key to improving the user experience. This paper aims to explore the application of physiological signals and facial expression synchronization analysis in emotion recognition. This paper adopts the method of literature review, and summarizes the acquisition techniques of physiological signals and facial expressions, synchronous analysis methods, and their application cases in emotion recognition. At the same time, the limitations and challenges of the existing technology are discussed. The review shows that the synchronous analysis of physiological signals and facial expressions has important application value in the field of emotion recognition, especially in mental health monitoring, educational feedback, and customer service automation. However, the practical application of the technology still faces many challenges, including the real-time nature of data collection, the adaptability of individual differences, and other identification problems. Therefore, future research needs to further optimize data acquisition technology and develop more accurate and personalized analysis algorithms.

Influence of facial expression and its congruency with behavior records on young children’s trust judgments

Influence of facial expression and its congruency with behavior records on young children’s trust judgments

Investigating Digital Illiterate Classification Techniques Based on DeepFace Technology

This paper presents an algorithm to identify digital illiterates by analyzing age and emotions from facial recognition. In this paper, digital illiterates refer to people who struggle in using digital devices. The study assumed that older individuals who display surprised or angry facial expressions while using digital devices are more likely to be identified as digitally illiterate. For age detection, the study used MTCNN (Multi-task Cascaded Convolutional Networks), and for emotion detection, it employed the VGG-Face model. MTCNN detects facial features and landmarks to preprocess images and distinguish facial characteristics. The VGG-Face model uses convolution operations to analyze facial images and classify emotional states. The dataset used in the study consisted of 3,000 facial images collected from the internet. The research team categorized the images into faces of individuals aged over 50, angry expressions, and surprised expressions. The dataset included 411 individuals (13.7%) aged over 50, 163 individuals (5.4%) with angry expressions, and 145 individuals (4.8%) with surprised expressions. Accuracy was estimated by comparing the results from the DeepFace algorithm with those from the research team’s classifications. The DeepFace algorithm achieved 95.77% accuracy in detecting individuals aged over 50, 83.45% accuracy for surprise, and 76.07% for anger. The results demonstrate that it is possible to identify digital illiterates based on their age and emotional expressions and could enable the development of personalized services to directly or indirectly support digital illiterates, potentially improving digital accessibility.

When faces don’t lie

Abstract In the last decades, Cognitive Translation Studies (CTIS) have witnessed a growing expansion of Audio Description (AD), with emphasis on experimental studies examining the psychological factors that influence the creation and reception of AD. While most studies have focused on the creation phase of AD, recent reception research has explored emotions, immersion, and presence in the context of AD. A study by Rojo et al. (2021) investigated the impact of AD on the reception of porn, comparing the psychophysiological response of sighted participants watching audiovisual content with blind and sighted participants listening to AD without images. The results indicated no significant differences in physiological and subjective responses. The present study aims at providing further evidence on the participants’ emotional response by analyzing their facial expressions using the FaceReader software (Noldus Information Technology). Unlike cardiac and cortisol responses, the analysis of the participants’ facial expressions reveals some intriguing differences between the groups that point to some emotional differences in the reception of porn.

The Effect of the Parent's Presence during the Dressing Process on the Severity of the Child's Pain

Objective: This research was carried out to determine the effect of the parent's presence near the child during the dressing process on the severity of pain caused by the dressing. Method: The sample of the descriptive comparative study consisted of 60 children. Ethics committee and study permission were obtained from the relevant institutions. Data were collected by observation and face-to-face interviews using the “Individual Characteristics Form” and the YBATT (facial expression, legs, activity, crying, and being able to be consoled) pain assessment scale Results: It was determined that the effect of the parent's presence with the child during the dressing on the severity of pain and behavioral pain symptoms was not statistically significant. In addition, it was determined that the gender (X2=0.071; p=0.500>0.05) and age (X2=6.133; p=0.105>0.05) of the children did not affect the perceived pain intensity in the presence or absence of parents. In the examination of the way parents support their children during the painful procedure, it was observed that 13 (43.4%) of them had a remote monitoring approach. Conclusion: In this study, it was seen that the presence of the parent with the child during the dressing did not affect the severity of the pain, the presence of the parent extended the dressing time, and the parents were in the approach of remote monitoring as a way of supporting the child during the procedure.

The impact of a customized aesthetic prosthetic leg cover on social interaction cues and attitudes in the general UK population: Two experimental studies.

To explore the impact of an aesthetic prosthetic leg cover on attitudes toward individuals with lower-limb amputation and associated social interaction cues among the general UK population. Two novel experimental methodologies. In study 1, participants (n = 188) viewed 1 of 3 images of an individual: (1) wearing a traditional stem prosthetic, (2) wearing an aesthetic leg cover, or (3) as a nonamputee. They then completed an attitude scale and rated the personality of the individual using the 10-item Big Five Inventory. Study 2 (n = 31) used eye tracking and facial expression software to explore gaze and facial arousal when viewing 1 of 9 manipulated videos of the same individual talking about 3 different scenarios. In study 1, the aesthetic leg cover led to significantly higher ratings of agreeableness than stem and nonamputee images and significantly higher ratings of extraversion than the nonamputee image. Attitudes toward an individual with a prosthesis did not significantly differ depending on which image they viewed and were generally positive. In study 2, all participants focused mainly on the individual's face regardless of scenario topic or leg condition, although participants focused more around the leg cover in more active contexts. Customized aesthetic leg covers may help individuals living with amputation to be perceived more positively in social situations. These experimental methodologies could be extended to explore the differential impact of context, functionality, and activity of specific types of customized aesthetic prosthetics and could help inform shared decision-making processes in clinical settings.

Lagged multidimensional recurrence quantification analysis for determining leader-follower relationships within multidimensional time series.

The current article introduces lagged multidimensional recurrence quantification analysis. The method is an extension of multidimensional recurrence quantification analysis and allows to quantify the joint dynamics of multivariate time series and to investigate leader-follower relationships in behavioral and physiological data. Moreover, the method enables the quantification of the joint dynamics of a group, when such leader-follower relationships are taken into account. We first provide a formal presentation of the method, and then apply it to synthetic data, as well as data sets from joint action research, investigating the shared dynamics of facial expression and beats-per-minute recordings within different groups. A wrapper function is included, for applying the method together with the "crqa" package in R. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Anger and Art Ambivalent emotion in art

The present study investigates the depiction of anger in Western visual art, highlighting the paradox of this emotion: its inherent unpleasantness and repulsiveness versus its artistic representation. The authors examine historical transformations in the expression of anger and the mechanisms that render its depiction effective in art. Despite being a fundamental human emotion encountered from birth, anger is surprisingly scarce in Western visual art. Historical artworks often depict actions resulting from anger rather than capturing its raw emotional expression. Kelly Grovier's essay "Art of Feeling: Why We Should Celebrate Anger" posits that the rarity of anger’s depiction may stem from its classification as a deadly sin by early Christian teachings, which stigmatized the emotion. However, significant works such as Delacroix's "Medea" and Gentileschi's "Judith" juxtapose violent acts with serene facial expressions, underscoring a disconnect between action and emotional display. The repulsiveness and transformative impact of anger on human appearance make it a challenging subject for art. Yet, works like Cabanel's "Fallen Angel" and Gérôme's "Truth Coming Out of Her Well" explore this transformation, employing beauty to attract and distortion to repulse, thereby creating a Medusa-like effect. This duality engages viewers and evokes mixed emotions, which enhances an artwork's impact. Furthermore, anger can drive creative innovation, as demonstrated in works by Munch, Picasso, and Kahlo, where personal and societal grievances fuel artistic expression. However, prolonged anger may lead to destructive creativity, emphasizing the complex role of anger in art and its potential for both innovation and hostility. This multifaceted exploration underscores anger’s unique, albeit limited, place in visual arts and its dual capacity to repel and inspire.

Advances in VNS efficiency and mechanisms of action on cognitive functions.

This systematic review aims to comprehensively analyze the efficacy and underlying mechanisms of vagus nerve stimulation (VNS) in enhancing cognitive functions and its therapeutic potential for various cognitive impairments. The review focuses on the impact of VNS on emotional processing, executive functions, learning, memory, and its clinical applications in conditions such as epilepsy, depression, Alzheimer's disease, and other neurological disorders. A systematic search of electronic databases (PubMed, Scopus, Web of Science) was conducted using the keywords "vagus nerve stimulation," "cognitive enhancement," "emotional processing," "executive function," "learning and memory," "epilepsy," "depression," "Alzheimer's disease," "neurological disorders," "attention-deficit/hyperactivity disorder," "sleep disorders," and "long COVID." The inclusion criteria encompassed controlled trials, longitudinal studies, and meta-analyses published in English between 2000 and July 2024. A comprehensive review of 100 articles highlighted the cognitive effects of Vagus Nerve Stimulation (VNS). Studies show that VNS, especially through transcutaneous auricular VNS (taVNS), enhances emotional recognition, particularly for facial expressions, and improves selective attention under high cognitive demands. Additionally, VNS enhances learning and memory, including associative memory and spatial working memory tasks. In clinical applications, VNS exhibits promising benefits for improving cognitive functions in treatment-resistant epilepsy, depression, and Alzheimer's disease. VNS represents a promising therapeutic approach for enhancing cognitive function across diverse patient populations. The reviewed evidence highlights its efficacy in modulating cognitive domains in healthy individuals and improving cognition in neurological conditions. However, the comparative effectiveness of different VNS modalities and the differential effects of online versus offline VNS on cognitive psychology require further investigation. Future research should focus on optimizing VNS protocols and elucidating specific cognitive domains that benefit most from VNS interventions. This ongoing exploration is essential for maximizing the therapeutic potential of VNS in clinical practice.

Multi-head Network based Students Behaviour Prediction with Feedback Generation for Enhancing Classroom Engagement and Teaching Effectiveness

Emotions are pivotal in the learning process, highlighting the importance of identifying students' emotional states within educational settings. While neural network models, particularly those rooted in deep learning, have demonstrated remarkable accuracy in detecting primary emotions like happiness, sadness, fear, disgust, and anger from facial expressions in videos, these emotions occur infrequently in learning environments. Conversely, cognitive emotions such as engagement, confusion, frustration, and boredom are significantly more prevalent, transpiring five times more frequently than basic emotions. However, unlike basic emotions which are relatively distinct, cognitive emotions present a subtler distinction, necessitating the utilization of more sophisticated models for accurate recognition. The proposed work presents an efficient Facial Expression Recognition (FER) model for monitoring the student engagement in a learning environment by considering their facial expressions like boredom, frustration, confusion and engagement. The proposed methodology includes certain pre-processing steps followed by facial expression recognition founded on Efficient-Net B3 CNN in which the learning parameters are optimized using Circle-Inspired Optimization Algorithm (CIOA). Finally, the post processing stage estimates the frame-wise group engagement level (GEL) of students based on certain expression labels. Based on the acquired results, it is noted that the suggested Efficient-Net B3 CNN-CIOA based FER model provides promising results in terms of accuracy by 99.5%, precision by 99.2%, recall by 99.5% and f1-score by 99.6%, when compared with some state-of-art facial expression recognition approaches. Also, the suggested approach computational complexity is very much less than the compared existing approaches.