• Korean Journal of Cognitive Science
• /
• v.13 no.3
• /
• pp.11-21
• /
• 2002

Parke and Waters' model［1］ of muscle-based face deformation was used to develop a system that can synthesize facial expressions when the pleasure-displeasure and arousal-sleep coordinate values of internal states are specified. Facial expressions sampled from a database developed by Chung, Oh, Lee and Byun ［2］ and its underlying model of internal states were used to find rules for face deformation. The internal - state model included dimensional and categorical values of the sampled facial expressions. To find out deformation rules for each of the expressions, changes in the lengths of 21 facial muscles were measured. Then, a set of multiple regression analyses was performed to find out the relationship between the muscle lengths and internal states. The deformation rules obtained from the process turned out to produce natural-looking expressions when the internal states were specified by the pleasure-displeasure and arousal-sleep coordinate values. Such a result implies that the rules derived from a large scale database and regression analyses capturing the variations of individual muscles can be served as a useful and powerful tool for synthesizing facial expressions.

• Proceedings of the IEEK Conference
• /
• 2005.11a
• /
• pp.537-540
• /
• 2005

본 논문에서는 사람의 감정, 건강상태, 정신상태등 다양한 정보를 포함하고 있는 웃음, 슬픔, 졸림, 놀람, 윙크, 무표정 등의 표정을 인식하기 위한 표정의 특징이 되는 얼굴의 국부적 요소인 눈과 입을 검출하여 표정의 특징을 추출한다. 표정 특징의 추출을 위한 전체적인 알고리즘 과정으로는 입력영상으로부터 칼라 정보를 이용하여 얼굴 영역을 검출하여 얼굴에서 특징점의 위치 정보를 이용하여 국부적 요소인 특징점 눈과 입을 추출한다. 이러한 특징점 추출 과정에서는 에지, 이진화, 모폴로지, 레이블링 등의 전처리 알고리즘을 적용한다. 레이블 영역의 크기를 이용하여 얼굴에서 눈, 눈썹, 코, 입 등의 1차 특징점을 추출하고 누적 히스토그램 값과 구조적인 위치 관계를 이용하여 2차 특징점 추출 과정을 거쳐 정확한 눈과 입을 추출한다. 표정 변화에 대한 표정의 특징을 정량적으로 측정하기 위해 추출된 특징점 눈과 입의 눈과 입의 크기와 면적, 미간 사이의 거리 그리고 눈에서 입까지의 거리 등 기하학적 정보를 이용하여 6가지 표정에 대한 표정의 특징을 추출한다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.9
• /
• pp.1547-1553
• /
• 2008

This paper presents a method that generates various facial expressions of vector graphic character by using the simplified principle component vector. First, we analyze principle components to the nine facial expression(astonished, delighted, etc.) redefined based on Russell's internal emotion state. From this, we find principle component vector having the biggest effect on the character's facial feature and expression and generate the facial expression by using that. Also we create natural intermediate characters and expressions by interpolating weighting values to character's feature and expression. We can save memory space considerably, and create intermediate expressions with a small computation. Hence the performance of character generation system can be considerably improved in web, mobile service and game that real time control is required.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.04a
• /
• pp.742-744
• /
• 2002

얼굴 애니메이션은 개인을 쉽게 구분하고 의사소통을 효율적으로 할 수 있는 보조도구로써 최근 연구가 활발하다. 본 논문에서는 얼굴 표정생성을 위해서 실제얼굴의 피부조직 얼굴 근육 등 해부학적 구조에 기반한 근육 기반 모델 방법을 사용하여 현실감 있고 자연스러운 얼굴 애니메이션이 이루어지도록 한다. 또한 부드러운 얼굴모델을 구현하기 위하여 폴리곤 메쉬를 분할하고 얼굴 표정에 중요한 영향을 미치는 얼굴근육을 추가하여 다양하고 자연스러운 표정을 연출하는 방법을 제시하고자 한다. 제안된 방법을 water〔3〕의 모델에 적용해 봄으로서 더 실감 있는 얼굴 애니메이션에 접근할 수 있는 결과를 얻을 수 있었다. 이 결과는 화상회의나 가상현실, 원격교육, 영화 등 많은 분야에서 활용될 수 있다.

• The Journal of the Korea Contents Association
• /
• v.14 no.11
• /
• pp.7-15
• /
• 2014

This paper proposed a recognition algorithm of human facial expressions using the PCA and the template matching. Firstly, face image is acquired using the Haar-like feature mask from an input image. The face image is divided into two images. One is the upper image including eye and eyebrow. The other is the lower image including mouth and jaw. The extraction of facial components, such as eye and mouth, begins getting eye image and mouth image. Then an eigenface is produced by the PCA training process with learning images. An eigeneye and an eigenmouth are produced from the eigenface. The eye image is obtained by the template matching the upper image with the eigeneye, and the mouth image is obtained by the template matching the lower image with the eigenmouth. The face recognition uses geometrical properties of the eye and mouth. The simulation results show that the proposed method has superior extraction ratio rather than previous results; the extraction ratio of mouth image is particularly reached to 99%. The face recognition system using the proposed method shows that recognition ratio is greater than 80% about three facial expressions, which are fright, being angered, happiness.

• Journal of the Korea Computer Industry Society
• /
• v.4 no.4
• /
• pp.569-578
• /
• 2003

This paper presents a method in which the user produces a real-time facial animation by navigating in the space of facial expressions created from a great number of captured facial expressions. The core of the method is define the distance between each facial expressions and how to distribute into suitable intuitive space using it and user interface to generate realtime facial expression animation in this space. We created the search space from about 2,400 raptured facial expression frames. And, when the user free travels through the space, facial expressions located on the path are displayed in sequence. To visually distribute about 2,400 captured racial expressions in the space, we need to calculate distance between each frames. And we use Floyd's algorithm to get all-pairs shortest path between each frames, then get the manifold distance using it. The distribution of frames in intuitive space apply a multi-dimensional scaling using manifold distance of facial expression frames, and distributed in 2D space. We distributed into intuitive space with keep distance between facial expression frames in the original form. So, The method presented at this paper has large advantage that free navigate and not limited into intuitive space to generate facial expression animation because of always existing the facial expression frames to navigate by user. Also, It is very efficient that confirm and regenerate nth realtime generation using user interface easy to use for facial expression animation user want.

• The KIPS Transactions:PartA
• /
• v.11A no.2
• /
• pp.189-194
• /
• 2004

This paper describes method to distribute much high-dimensional facial expression motion data to 2 dimensional space, and method to create facial expression animation by select expressions that want by realtime as animator navigates this space. In this paper composed expression space using about 2400 facial expression frames. The creation of facial space is ended by decision of shortest distance between any two expressions. The expression space as manifold space expresses approximately distance between two points as following. After define expression state vector that express state of each expression using distance matrix which represent distance between any markers, if two expression adjoin, regard this as approximate about shortest distance between two expressions. So, if adjacency distance is decided between adjacency expressions, connect these adjacency distances and yield shortest distance between any two expression states, use Floyd algorithm for this. To materialize expression space that is high-dimensional space, project on 2 dimensions using Sammon's Mapping. Facial animation create by realtime with animators navigating 2 dimensional space using user interface.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.449-454
• /
• 2009

The human face has "expression" as an important visual factor in contrast with general objects. For this reason, cartoonists draw shadow that emphasizes facial shape and facial expression in order to convey atmosphere of scene and trait of character. This shadow should be considered when doing cartoon rendering for facial expression although it is not an physical shading. This paper proposes a cartoon rendering system for facial expression based on shading techniques of real cartoonist. First of all, we searched such techniques of cartoonist through variety of collected cartoon images and defined shadow templates according to character's facial expression to do cartoon rendering diffently. After that, we demonstrated cartoon rendering system of facial expression on the basis of survey result that effectively emphasizes facial shape and facial expression. Finally, we showed the usefulness through the user questionnaire.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.04b
• /
• pp.526-528
• /
• 2001

기존의 얼굴표정 인식연구의 대부분은 얼굴영상에서 사전정보 획득과, 인식이 각각 별개로 수행되어, 전자의 결과가 후자를 보장하지 못하거나, 데이터와 계산 양의 과다, 그리고 인지과정이 사람과 다르다는 등의 문제가 있다. 이에 대해 하우스도르프 거리 매칭을 적용, 표정인식을 시도한다. 이는 전체적인 유사도를 측정하는 방법으로서 전체이론(Holistic theory)에 기반하여, '사람의 인지과정'을 따른다. 그러나 축소된 데이터를 사용하므로, 이 방법의 인식결과가 부족할 경우, 영상워핑을 적용하여 Brennan과 Carton이 제안한 캐리커쳐 효과를 이용한다. 이는 영상을 적절히 변형, 표정의 특징을 과장하고 잡영을 제거하여, 인식하기 쉬운, 분명한 표정을 생성하는 방법이다. 위 과정을 통해, 사람의 인지과정을 모사하고, 최소한의 데이터로써 사전정보 획득과정이 생략된, 입력영상으로부터 직접 표정을 인식하는 방법을 제안한다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2006.11a
• /
• pp.167-170
• /
• 2006

본 논문은 선형분류기인 LDA 융합모델과 최소거리패턴분류법을 이용한 얼굴표정인식 알고리즘 연구에 관한 것이다. 제안된 알고리즘은 얼굴 표정을 인식하기 위해 두 단계의 특징 추출과정과 인식단계를 거치게 된다. 먼저 특징추출 단계에서는 얼굴 표정이 담긴 영상을 PCA를 이용해 고차원에서 저차원의 공간으로 변환한 후, LDA 이용해 특징벡터를 클래스 별로 나누어 분류한다. 다음 단계로 LDA융합모델을 통해 계산된 특징벡터에 최소거리패턴분류법을 적용함으로서 얼굴 표정을 인식한다. 제안된 알고리즘은 6가지 기본 감정(기쁨, 화남, 놀람, 공포, 슬픔, 혐오)으로 구성된 데이터베이스를 이용해 실험한 결과, 기존알고리즘에 비해 향상된 인식률과 특정 표정에 관계없이 고른 인식률을 보임을 확인하였다.