• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.3
• /
• pp.924-942
• /
• 2020

The facial expression is diverse and various among persons due to the impact of the psychology factor. Whilst the facial action is comparatively steady because of the fixedness of the anatomic structure. Therefore, to improve performance of the action unit recognition will facilitate the facial expression recognition and provide profound basis for the mental state analysis, etc. However, it still a challenge job and recognition accuracy rate is limited, because the muscle movements around the face are tiny and the facial actions are not obvious accordingly. Taking account of the moving of muscles impact each other when person express their emotion, we propose to make full use of co-occurrence relationship among action units (AUs) in this paper. Considering the dynamic characteristic of AUs as well, we adopt the 3D Convolutional Neural Network(3DCNN) as base framework and proposed to recognize multiple action units around brows, nose and mouth specially contributing in the emotion expression with putting their co-occurrence relationships as constrain. The experiments have been conducted on a typical public dataset CASME and its variant CASME2 dataset. The experiment results show that our proposed AU co-occurrence constraint 3DCNN based AU recognition approach outperforms current approaches and demonstrate the effectiveness of taking use of AUs relationship in AU recognition.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.3 s.35
• /
• pp.55-64
• /
• 2005

The avatar can be used as an auxiliary methodology of text and image communications in cyber space. An intelligent communication method can also be utilized to achieve real-time communication, where intelligently coded data (joint angles for arm gestures and action units for facial emotions) are transmitted instead of real or compressed pictures. In this paper. for supporting the action of arm and leg gestures, a method of generating the facial expressions that can represent sender's emotions is provided. The facial expression can be represented by Action Unit(AU), in this paper we suggest the methodology of finding appropriate AUs in avatar models that have various shape and structure. And, to maximize the efficiency of emotional expressions, a comic-style facial model having only eyebrows, eyes, nose, and mouth is employed. Then generation of facial emotion animation with the parameters is also investigated.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.11
• /
• pp.5546-5559
• /
• 2019

Facial action units (AUs) have recently drawn increased attention because they can be used to recognize facial expressions. A variety of methods have been designed for frontal-view AU detection, but few have been able to handle multi-view face images. In this paper we propose a method for multi-view facial AU detection using a fused multilayer, multi-task, and multi-label deep learning network. The network can complete two tasks: AU detection and facial view detection. AU detection is a multi-label problem and facial view detection is a single-label problem. A residual network and multilayer fusion are applied to obtain more representative features. Our method is effective and performs well. The F1 score on FERA 2017 is 13.1% higher than the baseline. The facial view recognition accuracy is 0.991. This shows that our multi-task, multi-label model could achieve good performance on the two tasks.

• ETRI Journal
• /
• v.37 no.6
• /
• pp.1199-1210
• /
• 2015

Automatic emotion recognition based on facial cues, such as facial action units (AUs), has received huge attention in the last decade due to its wide variety of applications. Current computer-based automated two-phase facial emotion recognition procedures first detect AUs from input images and then infer target emotions from the detected AUs. However, more robust AU detection and AU-to-emotion mapping methods are required to deal with the error accumulation problem inherent in the multiphase scheme. Motivated by our key observation that a single AU detector does not perform equally well for all AUs, we propose a novel two-phase facial emotion recognition framework, where the presence of AUs is detected by group decisions of multiple AU detectors and a target emotion is inferred from the combined AU detection decisions. Our emotion recognition framework consists of three major components - multiple AU detection, AU detection fusion, and AU-to-emotion mapping. The experimental results on two real-world face databases demonstrate an improved performance over the previous two-phase method using a single AU detector in terms of both AU detection accuracy and correct emotion recognition rate.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.04a
• /
• pp.881-883
• /
• 2015

실제적인 표정인식 응용에서는 테스트 시 등장하는 인물이 트레이닝 데이터에 존재하지 않는 경우가 빈번하여 성능 저하가 발생한다. 본 논문에서는 인물에 독립적인(subject-independent) 표정인식을 위한 얼굴특징을 제안한다. 제안방법은 인물에 공통적인 얼굴 근육 움직임(Action Unit(AU))에 기반한 기하학 정보를 표정 특징으로 사용한다. 따라서 인물의 고유 아이덴티티(identity)의 영향은 감소되고 표정과 관련된 정보는 강조된다. 인물에 독립적인 표정인식 실험결과, 86%의 높은 표정인식률과 테스트 비디오 시퀀스 당 3.5ms(Matlab 기준)의 매우 빠른 분류속도를 달성하였다.

• The Journal of the Korea Contents Association
• /
• v.14 no.9
• /
• pp.476-483
• /
• 2014

The purpose of this study was to make a suitable images for korean emotional expressions. KSFI(Korean Standard Facial Image)-AUs was produced from korean standard apperance and FACS(Facial Action coding system)-AUs. For the objectivity of KSFI, the survey was examined about emotion recognition rate and contribution of emotion recognition in facial elements from six-basic emotional expression images(sadness, happiness, disgust, fear, anger and surprise). As a result of the experiment, the images of happiness, surprise, sadness and anger which had shown higher accuracy. Also, emotional recognition rate was mainly decided by the facial element of eyes and a mouth. Through the result of this study, KSFI contents which could be combined AU images was proposed. In this future, KSFI would be helpful contents to improve emotion recognition rate.

• Proceedings of the IEEK Conference
• /
• 1999.06a
• /
• pp.651-654
• /
• 1999

In this paper we propose an emotional expression method using a comic model and special marks for effective sign-language communications. Until now we have investigated to produce more realistic facial and emotional expression. When representing only emotional expression, however, a comic expression could be better than the real picture of a face. The comic face is a comic-style expression model in which almost components except the necessary parts like eyebrows, eyes, nose and mouth are discarded. In the comic model, we can use some special marks for the purpose of emphasizing various emotions. We represent emotional expression using Action Units(AU) of Facial Action Coding System(FACS) and define Special Unit(SU) for emphasizing the emotions. Experimental results show a possibility that the proposed method could be used efficiently for sign-language image communications.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.40 no.1
• /
• pp.59-73
• /
• 2003

As a means of overcoming the linguistic barrier between different languages in the Internet, a new sign-language communication system with CG animation techniques has been developed and proposed. In the system, the joint angles of the arms and the hands corresponding to the gesture as a non-verbal communication tool have been considered. The emotional expression, however, could as play also an important role in communicating each other. Especially, a comic expression is more efficient than real facial expression, and the movements of the cheeks and the jaws are more important AU's than those of the eyebrow, eye, mouth etc. Therefore, in this paper, we designed a 3D emotion editor using 2D model, and we extract AU's (called as PAU, here) which play a principal function in expressing emotions. We also proposed a method of generating the universal emotional expression with Avatar models which have different vertex structures. Here, we employed a method of dynamically adjusting the AU movements according to emotional intensities. The proposed system is implemented with Visual C＋＋ and Open Inventor on windows platforms. Experimental results show a possibility that the system could be used as a non-verbal communication means to overcome the linguistic barrier.

• Journal of Broadcast Engineering
• /
• v.25 no.4
• /
• pp.537-544
• /
• 2020

This paper proposes the creation of an android robot head based on the facial action coding system(FACS), and the generation of emotional expressions by FACS. The term android robot refers to robots with human-like appearance. These robots have artificial skin and muscles. To make the expression of emotions, the location and number of artificial muscles had to be determined. Therefore, it was necessary to anatomically analyze the motions of the human face by FACS. In FACS, expressions are composed of action units(AUs), which work as the basis of determining the location and number of artificial muscles in the robots. The android head developed in this study had servo motors and wires, which corresponded to 30 artificial muscles. Moreover, the android head was equipped with artificial skin in order to make the facial expressions. Spherical joints and springs were used to develop micro-eyeball structures, and the arrangement of the 30 servo motors was based on the efficient design of wire routing. The developed android head had 30-DOFs and could express 13 basic emotions. The recognition rate of these basic emotional expressions was evaluated at an exhibition by spectators.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.11
• /
• pp.193-201
• /
• 2014

This paper suggests a facial expression recognition system using face detection, face alignment, facial unit extraction, and training and testing algorithms based on AdaBoost classifiers. First, we find face region by a face detector. From the results, face alignment algorithm extracts feature points. The facial units are from a subset of action units generated by combining the obtained feature points. The facial units are generally more effective for smaller-sized databases, and are able to represent the facial expressions more efficiently and reduce the computation time, and hence can be applied to real-time scenarios. Experimental results in real scenarios showed that the proposed system has an excellent performance over 90% recognition rates.