• Journal of Internet Computing and Services
• /
• v.13 no.5
• /
• pp.9-19
• /
• 2012

Virtual human used as HCI in digital contents expresses his various emotions across modalities like facial expression and body posture. However, few studies considered combinations of such nonverbal multimodal in emotion perception. Computational engine models have to consider how a combination of nonverbal modal like facial expression and body posture will be perceived by users to implement emotional virtual human, This paper proposes the impacts of nonverbal multimodal in design of emotion expressed virtual human. First, the relative impacts are analysed between different modals by exploring emotion recognition of modalities for virtual human. Then, experiment evaluates the contribution of the facial and postural congruent expressions to recognize basic emotion categories, as well as the valence and activation dimensions. Measurements are carried out to the impact of incongruent expressions of multimodal on the recognition of superposed emotions which are known to be frequent in everyday life. Experimental results show that the congruence of facial and postural expression of virtual human facilitates perception of emotion categories and categorical recognition is influenced by the facial expression modality, furthermore, postural modality are preferred to establish a judgement about level of activation dimension. These results will be used to implementation of animation engine system and behavior syncronization for emotion expressed virtual human.

• 한국HCI학회:학술대회논문집
• /
• 2007.02a
• /
• pp.667-674
• /
• 2007

Facial expressions provide significant clues about one's emotional state; however, it always has been a great challenge for machine to recognize facial expressions effectively and reliably. In this paper, we report a method of feature-based adaptive motion energy analysis for recognizing facial expression. Our method optimizes the information gain heuristics of ID3 tree and introduces new approaches on (1) facial feature representation, (2) facial feature extraction, and (3) facial feature classification. We use minimal reasonable facial features, suggested by the information gain heuristics of ID3 tree, to represent the geometric face model. For the feature extraction, our method proceeds as follows. Features are first detected and then carefully "selected." Feature "selection" is finding the features with high variability for differentiating features with high variability from the ones with low variability, to effectively estimate the feature's motion pattern. For each facial feature, motion analysis is performed adaptively. That is, each facial feature's motion pattern (from the neutral face to the expressed face) is estimated based on its variability. After the feature extraction is done, the facial expression is classified using the ID3 tree (which is built from the 1728 possible facial expressions) and the test images from the JAFFE database. The proposed method excels and overcomes the problems aroused by previous methods. First of all, it is simple but effective. Our method effectively and reliably estimates the expressive facial features by differentiating features with high variability from the ones with low variability. Second, it is fast by avoiding complicated or time-consuming computations. Rather, it exploits few selected expressive features' motion energy values (acquired from intensity-based threshold). Lastly, our method gives reliable recognition rates with overall recognition rate of 77%. The effectiveness of the proposed method will be demonstrated from the experimental results.

• Science of Emotion and Sensibility
• /
• v.14 no.4
• /
• pp.605-616
• /
• 2011

The present study examined memory accuracy for faces with positive, negative and neutral emotional expressions to test whether their emotional content can affect visual working memory (VWM) performance. Participants remembered a set of face pictures in which facial expressions of the faces were randomly assigned from pleasant, unpleasant and neutral emotional categories. Participants' task was to report presence or absence of an emotion change in the faces by comparing the remembered set against another set of test faces displayed after a short delay. The change detection accuracies of the pleasant, unpleasant and neutral face conditions were compared under two memory exposure duration of 500ms vs. 1000ms. Under the duration of 500ms, the accuracy in the pleasant condition was higher than both unpleasant and neutral conditions. However the difference disappeared when the duration was extended to 1000ms. The results indicate that a positive facial expression can improve VWM accuracy relative to the negative or positive expressions especially when there is not enough time for forming durable VWM representations.

• Proceedings of the IEEK Conference
• /
• 2001.06c
• /
• pp.121-124
• /
• 2001

In this paper, a method of generating the facial gesture CG animation on different avatar models is provided. At first, to edit emotional expressions efficiently, regeneration of the comic expression on different polygonal mesh models is carried out, where the movements of the cheeks and numerical methods. Experimental results show a possibility that the method could be used for intelligent avatar communications between Korea and Japan.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.19 no.3
• /
• pp.245-251
• /
• 2023

Facial expression recognition plays a significant role in understanding human emotional states. With the advancement of AI and computer vision technologies, extensive research has been conducted in various fields, including improving customer service, medical diagnosis, and assessing learners' understanding in education. In this study, we develop a model that can infer emotions in real-time from a webcam using transfer learning with TensorFlow.js and MobileNet. While existing studies focus on achieving high accuracy using deep learning models, these models often require substantial resources due to their complex structure and computational demands. Consequently, there is a growing interest in developing lightweight deep learning models and transfer learning methods for restricted environments such as web browsers and edge devices. By employing MobileNet as the base model and performing transfer learning, our study develops a deep learning transfer model utilizing JavaScript-based TensorFlow.js, which can predict emotions in real-time using facial input from a webcam. This transfer model provides a foundation for implementing facial expression recognition in resource-constrained environments such as web and mobile applications, enabling its application in various industries.

• The Journal of the Korea Contents Association
• /
• v.16 no.12
• /
• pp.327-345
• /
• 2016

The purpose of this study was to carry out cognitive movement therapy program for children with affective and behavioral disorder based on neuro science, psychology, motor learning, muscle physiology, biomechanics, human motion analysis, movement control and to quantify characteristic of expression and gestures according to change of facial expression by emotional change. We could observe problematic expression of children with affective disorder, and could estimate the efficiency of application of movement therapy program by the face expression change of children with affective disorder. And it could be expected to accumulate data for early detection and therapy process of development disorder applying converged measurement and analytic method for human development by quantification of emotion and behavior therapy analysis, kinematic analysis. Therefore, the result of this study could be extendedly applied to the disabled, the elderly and the sick as well as children.

• Journal of the Korean Academy of Child and Adolescent Psychiatry
• /
• v.24 no.2
• /
• pp.83-89
• /
• 2013

Objectives : It is known that children with attention-deficit hyperactivity disorder (ADHD) experience significant difficulty in recognizing facial emotion, which involves processing of emotional facial expressions rather than speech, compared to children without ADHD. This objective of this study is to investigate the differences in facial emotion recognition between children with ADHD and normal children used as control. Methods : The children for our study were recruited from the Suwon Project, a cohort comprising a non-random convenience sample of 117 nine-year-old ethnic Koreans. The parents of the study participants completed study questionnaires such as the Korean version of Child Behavior Checklist, ADHD Rating Scale, Kiddie-Schedule for Affective Disorders and Schizophrenia-Present and Lifetime Version. Facial Expression Recognition Test of the Emotion Recognition Test was used for the evaluation of facial emotion recognition and ADHD Rating Scale was used for the assessment of ADHD. Results : ADHD children (N=10) were found to have impaired recognition when it comes to Emotional Differentiation and Contextual Understanding compared with normal controls (N=24). We found no statistically significant difference in the recognition of positive facial emotions (happy and surprise) and negative facial emotions (anger, sadness, disgust and fear) between the children with ADHD and normal children. Conclusion : The results of our study suggested that facial emotion recognition may be closely associated with ADHD, after controlling for covariates, although more research is needed.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.3
• /
• pp.438-444
• /
• 2008

In this study, we propose a automatic facial expression generation tool which can generate various facial expressions efficiently for animation characters expressing various emotion. For this purpose, 9 types of facial expressions were defined by adopting Russell's pleasure-displeasure and arousal-sleep coordinate values of infernal states. And by rendering specific coordinate values consisted of the two basic dimensions of emotion(i.e., dimensions of pleasure-displeasure and arousal-sleep) and their combination, the proposed automatic facial expression generation tool could yield various facial expressions which reflected subtle changes in characters' emotion. It is expected that the tool could provide useful method of generating character face with various emotion.

• The Journal of the Korea Contents Association
• /
• v.9 no.9
• /
• pp.125-133
• /
• 2009

As interactivity is becoming one of the key success factors in today's digital communication environment, increasing emphasis is being placed on technologies for user-oriented emotion expression. We aim for development of enabling technologies for creation of emotional characters who can express personalized emotions in real-time. In this paper, we conduct a survey on domestic and international researches and case studies for emotional characters with a focus on facial expression. The survey result is believed to have its meaning as a guideline for future research direction.

• Journal of Fashion Business
• /
• v.25 no.6
• /
• pp.119-130
• /
• 2021

This study investigated the effects of the chatbot's level of anthropomorphism - closeness to the human form - and its self-disclosure - delivery of emotional exchange with the chatbot through its facial expressions and chatting message on the user's intention to accept the service. A 2 (anthropomorphism: High vs. Low) × 2 (self-disclosure through facial expressions: High vs. Low) × 2 (self-disclosure through conversation: High vs. Low) between-subject factorial design was employed for this study. An online survey was conducted and a total of 234 questionnaires were used in the analysis. The results showed that consumers used chatbot service more when emotions were disclosed through facial expressions, than when it disclosed fewer facial expressions. There was statistically significant interaction effect, indicating the relationship between chatbot's self-disclosure through facial expression and the consumers' intention to use chatbot service differs depending on the extent of anthropomorphism. In the case of "robot chatbots" with low anthropomorphism levels, there was no difference in intention to use chatbot service depending on the level of self-disclosure through facial expression. When the "human-like chatbot" with high anthropomorphism levels discloses itself more through facial expressions, consumer's intention to use the chatbot service increased much more than when the human-like chatbot disclosed fewer facial expressions. The findings suggest that chatbots' self-disclosure plays an important role in the formation of consumer perception.