• ETRI Journal
• /
• 제32권5호
• /
• pp.784-794
• /
• 2010

Automatic facial expression recognition has many potential applications in different areas of human computer interaction. However, they are not yet fully realized due to the lack of an effective facial feature descriptor. In this paper, we present a new appearance-based feature descriptor, the local directional pattern (LDP), to represent facial geometry and analyze its performance in expression recognition. An LDP feature is obtained by computing the edge response values in 8 directions at each pixel and encoding them into an 8 bit binary number using the relative strength of these edge responses. The LDP descriptor, a distribution of LDP codes within an image or image patch, is used to describe each expression image. The effectiveness of dimensionality reduction techniques, such as principal component analysis and AdaBoost, is also analyzed in terms of computational cost saving and classification accuracy. Two well-known machine learning methods, template matching and support vector machine, are used for classification using the Cohn-Kanade and Japanese female facial expression databases. Better classification accuracy shows the superiority of LDP descriptor against other appearance-based feature descriptors.

• 한국지능시스템학회논문지
• /
• 제19권4호
• /
• pp.562-567
• /
• 2009

얼굴 표정은 사람의 감정을 전달하는 핵심 메커니즘으로 이를 적절하게 활용할 경우 Robotics의 HRI(Human Robot Interface)와 같은 Human Computer Interaction에서 큰 역할을 수행할 수 있다. 이는 HCI(Human Computing Interface)에서 사용자의 감정 상태에 대응되는 다양한 반응을 유도할 수 있으며, 이를 통해 사람의 감정을 통해 로봇과 같은 서비스 에이전트가 사용자에게 제공할 적절한 서비스를 추론할 수 있도록 하는 핵심요소가 된다. 본 논문에서는 얼굴표정에서의 감정표현을 인식하기 위한 방법으로 FACS(Facial Action Coding System)와 AAM(Active Appearance Model)을 이용한 특징 추출과 Bayesian Network 기반 표정 추론 기법이 융합된 얼굴표정 인식 시스템의 개발에 대한 내용을 제시한다.

• 한국의류산업학회지
• /
• 제14권5호
• /
• pp.803-810
• /
• 2012

This study investigates the effect of nonverbal communication on trust, switching barrier, and repurchase intention. Sample subjects used in this study were customers of a fashion shop in Sunchon. The questionnaires were conveniently sampled from July 2010 to August 2010. Questionnaire data from 335 customers of a national brand were analyzed through a reliability analysis, factor analysis, and multiple regression analysis. The results of this study are as follows. First, nonverbal communication by the service provider was divided into 3 types, physical appearance and paralanguage, postures and proxemics, and facial expressions. Second, it was found that physical appearance and paralanguage, postures and proxemics, facial expression of nonverbal communication had a significant impact on customer trust. Third, given the relationship between nonverbal communication and switching barrier, it was represented that the postures and proxemics and facial expressions (except physical appearance and paralanguage) had a significantly positive influence on the switching barrier. Forth, physical appearance/paralanguage, postures/proxemics, and facial expressions (nonverbal communication) had a positive influence on repurchase intention. Fifth, given the relationship between trust and repurchase intention as well as switching barrier and repurchase intention, it was represented that trust and switching barrier have a significantly positive influence upon repurchase intention. According to the results of this study, the more positive nonverbal communication by the service provider then the higher the customer repurchase intention as well as trust and switching barrier. Fifth, given the relationship between trust and repurchase intention as well as switching barrier and repurchase intention, it was represented that trust and switching barrier have a significantly positive influence upon repurchase intentions.

• Journal of International Society for Simulation Surgery
• /
• 제2권1호
• /
• pp.7-9
• /
• 2015

Purpose In the many face-related application such as head pose estimation, 3D face modeling, facial appearance manipulation, the robust and fast facial feature extraction is necessary. We present the facial feature extraction method based on shape regression and feature selection for real-time facial feature extraction. Materials and Methods The facial features are initialized by statistical shape model and then the shape of facial features are deformed iteratively according to the texture pattern which is selected on the feature pool. Results We obtain fast and robust facial feature extraction result with error less than 4% and processing time less than 12 ms. The alignment error is measured by average of ratio of pixel difference to inter-ocular distance. Conclusion The accuracy and processing time of the method is enough to apply facial feature based application and can be used on the face beautification or 3D face modeling.

• 대한치과교정학회지
• /
• 제33권5호
• /
• pp.319-322
• /
• 2003

Recent scientific findings on the perception of facial attractiveness coupled with technological advances in computer imaging make it possible to measure the facial characteristics that nay be associated with specific judgments of facial appearance. These new methods can be used to produce psychometric norms of facial attractiveness which potentially could supplement the conventional population norms or averages used currently in orthodontic treatment planning. It is hypothesized that consideration of psychometric norms will enhance doctor-patient communication and lead to greater patient satisfaction at the completion of orthodontic treatment.

• 전자공학회논문지
• /
• 제53권1호
• /
• pp.118-125
• /
• 2016

본 논문에서는 얼굴 영역 수술용 네비게이션을 위한 스테레오 비전과 CT 영상을 이용하여 환자-영상 간 정합(Image to patient registration) 알고리즘의 성능을 평가한다. 환자 영상 간 정합은 스테레오 비전 영상의 특징점 추출과 이를 통한 3차원 좌표 계산, 3차원 좌표와 3차원 CT 영상과의 정합 과정을 거친다. 스테레오 비전 영상에서 3가지 얼굴 특징점 추출 방법과 3가지 정합 방법을 사용하여 생성될 수 있는 5가지 조합 중 정합 정확도가 가장 높은 방법을 평가한다. 또한 머리의 회전에 따라 환자 영상 간 정합의 정확도를 비교한다. 실험을 통해 머리의 회전 각도가 약 20도의 범위 내에서 Active Appearance Model과 Pseudo Inverse Matching을 사용한 정합의 정확도가 가장 높았으며, 각도가 20도 이상일 경우 Speeded Up Robust Features와 Iterative Closest Point를 사용하였을 때 정합 정확도가 높았다. 이 결과를 통해 회전각도가 20도 범위 내에서는 Active Appearance Model과 Pseudo Inverse Matching 방법을 사용하고, 20도 이상의 경우 Speeded Up Robust Features와 Iterative Closest Point를 이용하는 것이 정합의 오차를 줄일 수 있다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2002년도 ICCAS
• /
• pp.100.4-100
• /
• 2002

For visual navigation, mobile robot can use a stereo camera which has large field of view. In this paper, we propose an algorithm to detect and recognize human face on the basis of such camera system. In this paper, a new coarse to fine detection algorithm is proposed. For coarse detection, nearly face-like areas are found in entire image using dual ellipse templates. And, detailed alignment of facial outline and features is performed on the basis of view- based multiple appearance model. Because it hard to finely align with facial features in this case, we try to find most resembled face image area is selected from multiple face appearances using most distinguished facial features- two eye...

• Maxillofacial Plastic and Reconstructive Surgery
• /
• 제41권
• /
• pp.22.1-22.2
• /
• 2019

• 대한두개안면성형외과학회지
• /
• 제17권4호
• /
• pp.240-243
• /
• 2016

Perfect facial and body symmetry is an important aesthetic concept which is very difficult, if not impossible, to achieve. Yet, facial asymmetries are commonly encountered by plastic and reconstructive surgeons. Here, we present a case of posttraumatic facial asymmetry successfully treated with a unique concept of facial flap repositioning. A 25-year-old male patient visited our department with severe posttraumatic facial asymmetry. There was deviated nasal bone and implant to the right, and the actual facial appearance asymmetry was much more severe compared to the computed tomography, generally shifted to the right. After corrective rhinoplasty, we approached through intraoral incision, and much adhesion from previous surgeries was noted. We meticulously elevated the facial flap of both sides, mainly involving the cheeks. The elevated facial flap was shifted to the left, and after finding the appropriate location, we sutured the middle portion of the flap to the periosteum of anterior nasal spine for fixation. We successfully freed the deviated facial tissues and repositioned it to improve symmetry in a single stage operation. We conclude that facial flap repositioning is an effective technique for patients with multiple operation history, and such method can successfully apply to other body parts with decreased tissue laxity.

• 인지과학
• /
• 제14권4호
• /
• pp.53-63
• /
• 2003

얼굴 인상과 얼굴의 물리적 특징 사이의 관계를 분석하고 인상이 얼굴의 유사성 판단에 미치는 영향을 조사하였다. 얼굴 데이터베이스로부터 선정한 79개의 얼굴에 대해 '순하다-사납다', '영리하다-우둔하다', '여성스럽다-남자답다', '앳되다-성숙하다'의 네 개 차원에 대한 인상 평정값과 41개의 물리적 특징의 측정값을 수집하였다. 두 가지 값을 대상으로 한 중다 회귀 분석 결과, 얼굴의 물리적 구조가 인상과 밀접한 관계가 있는 것으로 나타났다. 얼굴의 유사성 판단 실험을 통해서 인상이 얼굴 정보 처리 과정에서의 사용 가능성을 확인하였다. 실험 결과, 사람들은 물리적 특징 조건이 비슷할 때 중성 인상의 얼굴보다 동일한 인상의 얼굴들을 더 유사하게 지각하는 것으로 나타났다. 이러한 결과들은 인상이 얼굴 생김새를 표상하는 심리적인 구조로 사용되며 인상 정보가 얼굴 처리 과정에 포함될 가능성이 있음을 시사한다.