• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.6
• /
• pp.772-776
• /
• 2006

A research about facial image recognition is studied in the most of images in a full race. A representative part, effecting a facial image recognition, is eyes and a mouth. So, facial image recognition researchers have studied under the central eyes, eyebrows, and mouths on the facial images. But most people in front of a camera in everyday life are difficult to recognize a fast change of pupils. And people wear glasses. So, in this paper, we try using Principal Component Analysis(PCA) for facial image recognition in blindfold case.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.1
• /
• pp.18-23
• /
• 2005

It is difficult to define and classify human emotion. These vague human emotion appear not in single emotion, but in combination of various emotion. And among them, a remarkable emotion is expressed. This paper proposes a emotional expression algorithm using dynamic emotion space, which give facial expression in similar with vague human emotion. While existing avatar express several predefined emotions from database, our emotion expression system can give unlimited various facial expression by expressing emotion based on dynamically changed emotion space. In order to see whether our system practically give complex and various human expression, we perform real implementation and experiment and verify the efficacy of emotional expression system based on dynamic emotion space.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.6
• /
• pp.1137-1144
• /
• 2022

In this study, an artificial intelligence(AI) was developed to help with facial expression practice in order to express emotions. The developed AI used multimodal inputs consisting of sentences and facial images for deep neural networks (DNNs). The DNNs calculated similarities between the emotions predicted by the sentences and the emotions predicted by facial images. The user practiced facial expressions based on the situation given by sentences, and the AI provided the user with numerical feedback based on the similarity between the emotion predicted by sentence and the emotion predicted by facial expression. ResNet34 structure was trained on FER2013 public data to predict emotions from facial images. To predict emotions in sentences, KoBERT model was trained in transfer learning manner using the conversational speech dataset for emotion classification opened to the public by AIHub. The DNN that predicts emotions from the facial images demonstrated 65% accuracy, which is comparable to human emotional classification ability. The DNN that predicts emotions from the sentences achieved 90% accuracy. The performance of the developed AI was evaluated through experiments with changing facial expressions in which an ordinary person was participated.

• Journal of Korea Multimedia Society
• /
• v.25 no.2
• /
• pp.215-220
• /
• 2022

Emotion recognition is one of the most important and challenging areas of computer vision. Nowadays, many studies on emotion recognition were conducted and the performance of models is also improving. but, more research is needed on emotion recognition and sentiment analysis of video viewers. In this paper, we propose an emotion analysis system the includes a sentiment analysis model and an interest prediction model. We analyzed the emotional patterns of people watching popular and unpopular videos and predicted the level of interest using the emotion analysis system. Experimental results showed that certain emotions were strongly related to the popularity of videos and the interest prediction model had high accuracy in predicting the level of interest.

• Science of Emotion and Sensibility
• /
• v.17 no.1
• /
• pp.53-62
• /
• 2014

Despite the huge potential of the practical application of emotion recognition technologies, the enhancement of the technologies still remains a challenge mainly due to the difficulty of recognizing emotion. Although not perfect, human emotions can be recognized through human images and sounds. Emotion recognition technologies have been researched by extensive studies that include image-based recognition studies, sound-based studies, and both image and sound-based studies. Studies on emotion recognition through facial expression detection are especially effective as emotions are primarily expressed in human face. However, differences in user environment and their familiarity with the technologies may cause significant disparities and errors. In order to enhance the accuracy of real-time emotion recognition, it is crucial to note a mechanism of understanding and analyzing users' personality traits that contribute to the improvement of emotion recognition. This study focuses on analyzing users' personality traits and its application in the emotion recognition system to reduce errors in emotion recognition through facial expression detection and improve the accuracy of the results. In particular, the study offers a practical solution to users with subtle facial expressions or low degree of emotion expression by providing an enhanced emotion recognition function.

• Journal of Korea Multimedia Society
• /
• v.12 no.8
• /
• pp.1128-1141
• /
• 2009

Graphical expressions are continuously improving, spurred by the astonishing growth of the game technology industry. Despite such improvements, users are still demanding a more natural gaming environment and true reflections of human emotions. In real life, people can read a person's moods from facial color and expression. Hence, interactive facial colors in game characters provide a deeper level of reality. In this paper we propose a facial color adaptive technique, which is a combination of an emotional model based on human emotion theory, emotional expression pattern using colors of animation contents, and emotional reaction speed function based on human personality theory, as opposed to past methods that expressed emotion through blood flow, pulse, or skin temperature. Experiments show this of expression of the Facial Color Model based on facial color adoptive technique and expression of the animation contents is effective in conveying character emotions. Moreover, the proposed Facial Color Adaptive Technique can be applied not only to 2D games, but to 3D games as well.

• Science of Emotion and Sensibility
• /
• v.22 no.2
• /
• pp.37-48
• /
• 2019

Current research explores the effect of language on the perception of facial emotion as suggested by the psychological construction theory of emotion by using a psychophysical method. In this study, we hypothesize that the perception of facial expression may be influenced if the observer is shown an affective word before he/she judges an expression. Moreover, we suggest that his/her understanding of a facial emotion will be in line with the conceptual context that the word denotes. During the two experiments conducted for this project, a control stimulus or words representing either angry or happy emotions were briefly presented to participants before they were shown a target face. These target faces were randomly selected from seven faces that were gradually morphed to show neutral to angry (in Experiment 1) and neutral to happy (in Experiment 2) expressions. The participants were asked to perform a two-alternative forced choice (2AFC) task to judge the emotion of the target face (i.e., decide whether it is angry or neutral, or happy or neutral). The results of Experiment 1 (when compared with the control condition) showed that words denoting anger decreased the point of subjective equality (PSE) for judging the emotion of the target as anger, whereas words denoting happiness increased the PSE. Experiment 2, in which participants had to judge expressions on a scale from happy to neutral, produced a contrasting pattern of results. The outcomes of this study support the claim of the psychological construction theory of emotion that the perception of facial emotion is an active construction process that may be influenced by information (such as affective words) that provide conceptual context.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2002.05a
• /
• pp.11-15
• /
• 2002

Activities of venter frontalis, corrugator, levator labii superioris and greater zygomatic muscles were measured for five male subjects while they made pleasant, unpleasant and neutral facial expressions, and while they were presented pleasant, disgusting, and neutral odors. Pleasant expression and odor activated zygomatic muscles while unpleasant expression and odor increased corrugator muscle activity.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2011.05a
• /
• pp.31-32
• /
• 2011

• Smart Media Journal
• /
• v.13 no.3
• /
• pp.9-17
• /
• 2024

Due to the recent pandemic and the development of ICT technology, the use of non-face-to-face and unmanned systems is expanding, and it is very important to understand emotions in communication in non-face-to-face situations. As emotion recognition methods for various facial expressions are required to understand emotions, artificial intelligence-based research is being conducted to improve facial expression emotion recognition in image data. However, existing research on facial expression emotion recognition requires high computing power and a lot of learning time because it utilizes a large amount of data to improve accuracy. To improve these limitations, this paper proposes a method of recognizing facial expressions using age and gender, which are image meta information, as a method of recognizing facial expressions with even a small amount of data. For facial expression emotion recognition, a face was detected using the Yolo Face model from the original image data, and age and gender were classified through the VGG model based on image meta information, and then seven emotions were recognized using the EfficientNet model. The accuracy of the proposed data classification learning model was higher as a result of comparing the meta-information-based data classification model with the model trained with all data.