Facial Expression Recognition Accuracy Research Articles

Local Directional Ternary Pattern for Facial Expression Recognition.

This paper presents a new face descriptor, local directional ternary pattern (LDTP), for facial expression recognition. LDTP efficiently encodes information of emotion-related features (ı.e., eyes, eyebrows, upper nose, and mouth) by using the directional information and ternary pattern in order to take advantage of the robustness of edge patterns in the edge region while overcoming weaknesses of edge-based methods in smooth regions. Our proposal, unlike existing histogram-based face description methods that divide the face into several regions and sample the codes uniformly, uses a two-level grid to construct the face descriptor while sampling expression-related information at different scales. We use a coarse grid for stable codes (highly related to non-expression), and a finer one for active codes (highly related to expression). This multi-level approach enables us to do a finer grain description of facial motions while still characterizing the coarse features of the expression. Moreover, we learn the active LDTP codes from the emotion-related facial regions. We tested our method by using person-dependent and independent cross-validation schemes to evaluate the performance. We show that our approaches improve the overall accuracy of facial expression recognition on six data sets.

Neural substrates of the ability to recognize facial expressions: a voxel-based morphometry study.

The recognition of facial expressions of emotion is adaptive for human social interaction, but the ability to do this and the manner in which it is achieved differs among individuals. Previous functional neuroimaging studies have demonstrated that some brain regions, such as the inferior frontal gyrus (IFG), are active during the response to emotional facial expressions in healthy participants, and lesion studies have demonstrated that damage to these structures impairs the recognition of facial expressions. However, it remains to be established whether individual differences in the structure of these regions could be associated with differences in the ability to recognize facial expressions. We investigated this issue using acquired structural magnetic resonance imaging, and assessed the performance of healthy adults with respect to recognition of the facial expressions of six basic emotions. The gray matter volume of the right IFG positively correlated with the total accuracy of facial expression recognition. This suggests that individual differences in the ability to recognize facial expressions are associated with differences in the structure of the right IFG. Furthermore, the mirror neuron activity of the IFG may be important for establishing efficient facial mimicry to facilitate emotion recognition.

A differing bidirectional impact on the recognition accuracy of facial expression.

This study explored a bidirectional impact on the recognition accuracy of various facial expressions deriving from both the observer and sender in a sample of Chinese participants. A facial manipulation task was used to examine the ability of an observer's facial feedback to modulate the recognition of various facial expressions. Furthermore, the effect of a sender's facial expression with an open or closed mouth on recognition accuracy was investigated. The results showed that only recognition accuracy of a sad facial expression was influenced simultaneously by bidirectional sources from a sender and observer. Moreover, the impact of the unidirectional cue of a sender's facial feature (i.e., mouth openness) on happy and neutral faces was found to influence the recognition accuracy of these faces, but not the observer's bodily state. These findings indicate that the bidirectional impact derived from an observer and sender on facial expression recognition accuracy differs for emotional and neutral expressions.

Recognition of Facial Expressions of Negative Emotions in Romantic Relationships

Previous research has demonstrated that individuals who were accurate at recognizing facial expressions of emotions reported better relationships with family and friends. The purpose of the present study was to test whether the ability to recognize facial expressions of negative emotions predicted greater relationship satisfaction with their romantic relationships and whether this link was mediated by constructive responses to conflict. Participants currently involved in a romantic relationship completed a validated performance measure of recognition of facial expressions and afterwards reported on the responses they engaged in during conflict with their romantic partner and rated their romantic relationship satisfaction. Results showed that accurate recognition of facial expressions of negative emotions (anger, contempt, disgust, fear, and sadness) predicted less conflict engaging behaviors during conflict with their romantic partners (but not positive problem solving and withdrawal), which in turn predicted greater relationship satisfaction. The present study is the first to show that the ability to recognize facial expressions of negative emotions is related to romantic relationship satisfaction and that constructive responses to conflict such as less conflict engaging behaviors, mediate this process.

Precisión y tiempo de reacción en el reconocimiento de emociones faciales en personas con esclerosis múltiple

Facial emotional expression constitutes a basic guide in the social interaction and, thus, the alterations in its expression or recognition imply an important limitation for the communication. On the other hand, cognitive impairment and the presence of depressive symptoms, which are commonly found in patients with multiple sclerosis, it is unknown how they influence cognitive function and depression on emotional recognition. To consider the evaluation of time reaction and response accuracy of facial expression recognition in people affected by multiple sclerosis, and to assess the possible variables that may be modulating the emotion recognition, such as depression and cognitive functions. The study has a cross-sectional non-experimental design with a single measurement. The sample is compound by 85 participants, 45 diagnosed as multiple sclerosis and 40 control subjects. Multiple sclerosis subjects reveal significant differences in both reaction time and response accuracy in neuropsychological tests in comparison to the control group. Explanatory models were identified in the emotional recognition. Multiple sclerosis subjects face difficulties at recognising facial emotions; and differences at attention memory, processing speed and depressive symptomatology were observed in regard to the control group.

5-HTTLPR modulates the recognition accuracy and exploration of emotional facial expressions.

Individual genetic differences in the serotonin transporter-linked polymorphic region (5-HTTLPR) have been associated with variations in the sensitivity to social and emotional cues as well as altered amygdala reactivity to facial expressions of emotion. Amygdala activation has further been shown to trigger gaze changes toward diagnostically relevant facial features. The current study examined whether altered socio-emotional reactivity in variants of the 5-HTTLPR promoter polymorphism reflects individual differences in attending to diagnostic features of facial expressions. For this purpose, visual exploration of emotional facial expressions was compared between a low (n = 39) and a high (n = 40) 5-HTT expressing group of healthy human volunteers in an eye tracking paradigm. Emotional faces were presented while manipulating the initial fixation such that saccadic changes toward the eyes and toward the mouth could be identified. We found that the low vs. the high 5-HTT group demonstrated greater accuracy with regard to emotion classifications, particularly when faces were presented for a longer duration. No group differences in gaze orientation toward diagnostic facial features could be observed. However, participants in the low 5-HTT group exhibited more and faster fixation changes for certain emotions when faces were presented for a longer duration and overall face fixation times were reduced for this genotype group. These results suggest that the 5-HTT gene influences social perception by modulating the general vigilance to social cues rather than selectively affecting the pre-attentive detection of diagnostic facial features.

얼굴 표정인식을 위한 2D-DCT 특징추출 방법

본 논문에서는 2D-DCT와 EHMM 알고리즘을 이용하여 과적합에 강인한 얼굴 표정인식 방법을 고안하였다. 특히, 본 논문에서는 2D-DCT 특징추출을 위한 윈도우 크기를 크게 설정하여 EHMM의 관측벡터를 추출함으로써, 표정인식 성능 향상을 도모하였다. 제안 방법의 성능평가는 공인 CK 데이터베이스와 JAFFE 데이터베이스를 이용하여 수행되었고, 실험 결과로부터 특징추출 윈도우의 크기가 커질수록 표정 인식률이 향상됨을 확인하였다. 또한, CK 데이터베이스를 이용하여 표정 모델을 생성하고 JAFFE 데이터베이스 전체 샘플을 테스트한 결과, 제안 방법은 87.79%의 높은 인식률을 보였으며, 기존의 히스토그램 특징 기반의 표정인식 접근법보다 46.01~50.05%의 향상된 인식률을 보였다. This paper devices a facial expression recognition method robust to overfitting using 2D-DCT and EHMM algorithm. In particular, this paper achieves enhanced recognition performance by setting up a large window size for 2D-DCT feature extraction and extracting the observation vectors of EHMM. The experimental results on the CK facial expression database and the JAFFE facial expression database showed that the facial expression recognition accuracy was improved according as window size is large. Also, the proposed method revealed the recognition accuracy of 87.79% and showed enhanced recognition performance ranging from 46.01% to 50.05% in comparison to previous approaches based on histogram feature, when CK database is employed for training and JAFFE database is used to test the recognition accuracy.

PCA-based dictionary building for accurate facial expression recognition via sparse representation

Sparse representation is a new approach that has received significant attention for image classification and recognition. This paper presents a PCA-based dictionary building for sparse representation and classification of universal facial expressions. In our method, expressive facials images of each subject are subtracted from a neutral facial image of the same subject. Then the PCA is applied to these difference images to model the variations within each class of facial expressions. The learned principal components are used as the atoms of the dictionary. In the classification step, a given test image is sparsely represented as a linear combination of the principal components of six basic facial expressions. Our extensive experiments on several publicly available face datasets (CK+, MMI, and Bosphorus datasets) show that our framework outperforms the recognition rate of the state-of-the-art techniques by about 6%. This approach is promising and can further be applied to visual object recognition.

Impaired recognition of emotional facial expressions in patients with multiple sclerosis

BackgroundDisturbances that occur in patients with multiple sclerosis (MS) are not restricted to motor, sensory, or urinary functions; they also include cognitive dysfunction, fatigue, and depression. Moreover, people with MS are known to have fewer social activities and a reduced quality of life. One aspect of social interaction is accurate recognition of facial expressions. Several studies have suggested impairment in the processing of facial expressions in patients with multiple sclerosis, but it is not clear if these deficits are based on cognitive, depressive, or other attendant symptoms. ObjectiveTo investigate emotion recognition and facial identity recognition abilities and their relation with cognitive functions, depression, and fatigue in a cohort of MS patients. MethodsEmotion recognition and facial identity recognition abilities were investigated in a cohort of 61 MS patients with unimpaired visual acuity and 53 healthy controls using the Florida Affect Battery. Additionally, we investigated possible relationships between impaired facial expression recognition and other clinical features. ResultsMS patients were not impaired in facial identity discrimination, but showed a poor performance in all subtests that required emotion recognition. ConclusionImpaired recognition of facial emotions by patients with MS seems to be associated with both cognitive and affective (depression) aspects of the disease.

Facial emotion recognition in adolescents with personality pathology

It has been argued that a heightened emotional sensitivity interferes with the cognitive processing of facial emotion recognition and may explain the intensified emotional reactions to external emotional stimuli of adults with personality pathology, such as borderline personality disorder (BPD). This study examines if and how deviations in facial emotion recognition also occur in adolescents with personality pathology. Forty-two adolescents with personality pathology, 111 healthy adolescents and 28 psychiatric adolescents without personality pathology completed the Emotion Recognition Task, measuring their accuracy and sensitivity in recognizing positive and negative emotion expressions presented in several, morphed, expression intensities. Adolescents with personality pathology showed an enhanced recognition accuracy of facial emotion expressions compared to healthy adolescents and clients with various Axis-I psychiatric diagnoses. They were also more sensitive to less intensive expressions of emotions than clients with various Axis-I psychiatric diagnoses, but not more than healthy adolescents. As has been shown in research on adults with BPD, adolescents with personality pathology show enhanced facial emotion recognition.

Research on Facial Expression Recognition Based on Variable Precision Fuzzy Rough Set

In this paper, facial expression recognition as the starting point, it is extracted the mixing characteristics of the facial expression, including geometric and texture features. It can solve the problem of the collection contains the degree based on Variable Precision Fuzzy Rough Set, It could improved the accuracy of facial expression recognition using the method, thus making the facial expression recognition process more accurate and efficient.

Discriminant Analysis of Two-Dimensional Gabor Features for Facial Expression Recognition

A facial expression recognition algorithm using discriminant analysis of the two-dimensional Gabor features is described. Six basic emotions are used in the classification. The training and testing sets are based on images from the JAFFE Database. Facial expression recognition accuracy was 72.38 % for the testing set.

Face Emotion Processing in Depressed Children and Adolescents with and without Comorbid Conduct Disorder

Studies of adults with depression point to characteristic neurocognitive deficits, including differences in processing facial expressions. Few studies have examined face processing in juvenile depression, or taken account of other comorbid disorders. Three groups were compared: depressed children and adolescents with conduct disorder (n = 23), depressed children and adolescents without conduct disorder (n = 29) and children and adolescents without disorder (n = 37). A novel face emotion processing experiment presented faces with 'happy', 'sad', 'angry', or 'fearful' expressions of varying emotional intensity using morphed stimuli. Those with depression showed no overall or specific deficits in facial expression recognition accuracy. Instead, they showed biases affecting processing of low-intensity expressions, more often perceiving these as sad. In contrast, non-depressed controls more often misperceived low intensity negative emotions as happy. There were no differences between depressed children and adolescents with and without conduct disorder, or between children with comorbid depression/conduct disorder and controls. Face emotion processing biases rather than deficits appear to distinguish depressed from non-depressed children and adolescents.

Facial expression recognition accuracy of valence emotion among high and low indicated PTSD

Introduction: Emotional experience of stressful event reflects itself in form of inability to start and maintain social contact, to cope with stress and sometimes distorted cognitive outages. Aim: To test hypothesis that facially expressed emotions were useful monitor in practice as mediator for understanding nature of emotionally difficulties of traumatized forty-two individuals are facing with. Primary task was assessed whether psychologically traumatized individuals differ in facial recognition accuracy, and secondary, accuracy positive versus negative emotions among two studied groups. Subject and methods: The total sample of participants were divided in two groups based on score results of DSM- IV Harvard Trauma Questionnaire, Bosnia and Herzegovina version which was expressed perception of their PTSD symptoms self- assessed used of the score results of DSM- IV Harvard Trauma Questionnaire– Bosnia and Herzegovina version (the experimental group with high indicative PTSD and control group without moderate PTSD). Accuracy of recognition of seven facially expressed emotions was investigated. The authors presented results of significantly lower (p<.05) recognition accuracy in experimental group for all studied emotions with exception of emotion of sadness. Also, recognition of negative emotions are more accurate (p<.05). These findings suggest that emotional stress leads to a less accurate recognition of facially expressed emotions especially positive valence emotions.

Speed and accuracy of facial expression classification in avoidant personality disorder: A preliminary study.

The aim of this preliminary study was to examine whether individuals with avoidant personality disorder (APD) could be characterized by deficits in the classification of dynamically presented facial emotional expressions. Using a community sample of adults with APD (n = 17) and non-APD controls (n = 16), speed and accuracy of facial emotional expression recognition was investigated in a task that morphs facial expressions from neutral to prototypical expressions (Multi-Morph Facial Affect Recognition Task; Blair, Colledge, Murray, & Mitchell, 2001). Results indicated that individuals with APD were significantly more likely than controls to make errors when classifying fully expressed fear. However, no differences were found between groups in the speed to correctly classify facial emotional expressions. The findings are some of the first to investigate facial emotional processing in a sample of individuals with APD and point to an underlying deficit in processing social cues that may be involved in the maintenance of APD.

The misclassification of facial expressions in generalised social phobia

The aim of this study was to investigate facial expression recognition (FER) accuracy in social phobia and in particular to explore how facial expressions of emotion were misclassified. We hypothesised that compared with healthy controls, subjects with social phobia would be no less accurate in their identification of facial emotions (as reported in previous studies) but that they would misclassify facial expressions as expressing threatening emotions (anger, fear or disgust). Thirty individuals with social phobia and twenty-seven healthy controls completed a FER task which featured six basic emotions morphed using computer techniques between 0 percent (neutral) and 100 percent intensity (full emotion). Supporting our hypotheses we found no differences between the groups on measures of the accuracy of emotion recognition but that compared with healthy controls the social phobia group were more likely both to misclassify facial expressions as angry and to interpret neutral facial expressions as angry. The healthy control group were more likely to misclassify neutral expressions as sad. The importance of the role of these biases in social phobia needs further replication but may help in understanding the disorder and provide an interesting area for future research and therapy.

Sex differences in scanning faces: Does attention to the eyes explain female superiority in facial expression recognition?

Previous meta-analyses support a female advantage in decoding non-verbal emotion (Hall, 1978, 1984), yet the mechanisms underlying this advantage are not understood. The present study examined whether the female advantage is related to greater female attention to the eyes. Eye-tracking techniques were used to measure attention to the eyes in 19 males and 20 females during a facial expression recognition task. Women were faster and more accurate in their expression recognition compared with men, and women looked more at the eyes than men. Positive relationships were observed between dwell time and number of fixations to the eyes and both accuracy of facial expression recognition and speed of facial expression recognition. These results support the hypothesis that the female advantage in facial expression recognition is related to greater female attention to the eyes.

Image Ratio Features for Facial Expression Recognition Application

Video-based facial expression recognition is a challenging problem in computer vision and human-computer interaction. To target this problem, texture features have been extracted and widely used, because they can capture image intensity changes raised by skin deformation. However, existing texture features encounter problems with albedo and lighting variations. To solve both problems, we propose a new texture feature called image ratio features. Compared with previously proposed texture features, e.g., high gradient component features, image ratio features are more robust to albedo and lighting variations. In addition, to further improve facial expression recognition accuracy based on image ratio features, we combine image ratio features with facial animation parameters (FAPs), which describe the geometric motions of facial feature points. The performance evaluation is based on the Carnegie Mellon University Cohn-Kanade database, our own database, and the Japanese Female Facial Expression database. Experimental results show that the proposed image ratio feature is more robust to albedo and lighting variations, and the combination of image ratio features and FAPs outperforms each feature alone. In addition, we study asymmetric facial expressions based on our own facial expression database and demonstrate the superior performance of our combined expression recognition system.

Avatar culture: cross-cultural evaluations of avatar facial expressions

Avatars are increasingly used to express our emotions in our online communications. Such avatars are used based on the assumption that avatar expressions are interpreted universally among all cultures. This paper investigated cross-cultural evaluations of avatar expressions designed by Japanese and Western designers. The goals of the study were: (1) to investigate cultural differences in avatar expression evaluation and apply findings from psychological studies of human facial expression recognition, (2) to identify expressions and design features that cause cultural differences in avatar facial expression interpretation. The results of our study confirmed that (1) there are cultural differences in interpreting avatars’ facial expressions, and the psychological theory that suggests physical proximity affects facial expression recognition accuracy is also applicable to avatar facial expressions, (2) positive expressions have wider cultural variance in interpretation than negative ones, (3) use of gestures and gesture marks may sometimes cause counter-effects in recognizing avatar facial expressions.

Comparison of ICA approaches for facial expression recognition

Independent component analysis (ICA) and Gabor wavelets extract the most discriminating features for facial action unit classification by employing either a cosine similarity measure (CSM) classifier or support vector machines (SVMs). So far, only the ICA approach, which is based on the InfoMax principle, has been tested for facial expression recognition. In this paper, in addition to the InfoMax approach, another five ICA approaches extract features from two facial expression databases. In particular, the Extended InfoMax ICA, the undercomplete ICA, and the nonlinear kernel-ICA approaches are exploited for facial expression representation for the first time. When applied to images, ICA treats the images as being mixtures of independent sources and decomposes them into an independent basis and the corresponding mixture coefficients. Two architectures for representing the images can be employed yielding either independent and sparse basis images or independent and sparse distributions of image representation coefficients. After feature extraction, facial expression classification is performed with the help of either a CSM classifier or an SVM classifier. A detailed comparative study is made with respect to the accuracy offered by each classifier. The correlation between the accuracy and the mutual information of independent components or the kurtosis is evaluated. Statistically significant correlations between the aforementioned quantities are identified. Several issues are addressed in the paper: (i) whether features having super- and sub-Gaussian distribution facilitate facial expression classification; (ii) whether a nonlinear mixture of independent sources improves the classification accuracy; and (iii) whether an increased “amount” of sparseness yields more accurate facial expression recognition. In addition, performance enhancements by employing leave-one-set of expressions-out and subspace selection are studied. Statistically significant differences in accuracy between classifiers using several feature extraction methods are also indicated.