• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.42 no.3 s.303
• /
• pp.63-72
• /
• 2005

In this paper, we propose a deformation technique based on Radial Basis Function (RBF) and a blending technique combining the deformed facial component with the original face for a Virtual Aesthetic Surgery (VAS) system. The deformation technique needs the smoothness and the accuracy to deform the fluid facial components and also needs the locality not to affect or distort the rest of the facial components besides the deformation region. To satisfy these deformation characteristics, The VAS System computes the degree of deformation of lattice cells using RBF based on a Free-Form Deformation (FFD) model. The deformation error is compensated by the coefficients of mapping function, which is recursively solved by the Singular Value Decomposition (SVD) technique using SSE (Sum of Squared Error) between the deformed control points and target control points on base curves. The deformed facial component is blended with an original face using a blending ratio that is computed by the Euclidean distance transform. An experimental result shows that the proposed deformation and blending techniques are very efficient in terms of accuracy and distortion.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.4 s.304
• /
• pp.59-68
• /
• 2005

This paper proposes a face recognition under varying poses using local area obtained by side-view pose normalization. General normalization methods for face recognition under varying pose have a problem with the information about invisible area of face. Generally this problem is solved by compensation, but there are many cases where the image is distorted or features lost due to compensation .To solve this problem we normalize the face pose in side-view to reduce distortion that happens mainly in areas that have large depth variation. We only use undistorted area, removing the area that has been distorted by normalization. We consider two cases of yaw pose variation and pitch pose variation, and by experiments, we confirm the improvement of recognition performance.

• Proceedings of the Korea Contents Association Conference
• /
• 2010.05a
• /
• pp.475-477
• /
• 2010

경극은 중국의 전통극 중 하나이다. 경극의 영어 명칭은 'peking Opera'다. 경극의 "분장"은 희극에서 배우들이 얼굴에 하는 채색 화장을 가리킨다. 경극 배우들의 얼굴 분장을 '검보'라고 한다. 형태, 색채와 유형 면에서 특별한 양식을 갖춘다. 본 논문은 중국에 전하는 가면극의 외면적 표현 형태를 시각디자인 조형영역 분석을 통해 학문적 가치를 창출하는데 목적이 있다. 본 논문의 연구 영역은 경극의 유래, 색채, 형식적 측면에 대한 조형분석과 가면의 표현형식, 즉 표형기법, 색상구성, 형태구성, 역할특성 등의 구성형식을 조형적 분석 틀에 의해 분석하고자 한다. 가면 얼굴의 대표문양 분석을 통해 단순화 표현형식으로 작품을 만들어 연구하고자 한다. 분 논문의 의의는 중국 전통경극의 집중적 연구의 결과 추출을 통해 한국의 유사 전통탈춤과 비교하는 연구의 귀중한 자료로 예측되기에 본 연구를 진행하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2006.11a
• /
• pp.97-100
• /
• 2006

사상의학은 한의학의 독특하고 뛰어난 의료 체계이나 체질 감별에 객관성이 확보되지 않아 원래의 가치를 인정 받지 못하고 있다. 이를 위해 본 연구에서는 용모사기론을 기반으로 안면 형태학적 특징 분석을 통한 진단시스템을 만드는 것을 목표로 하고 있다. 이를 통해 정확하고 편리하게 체질을 분류 할수 있는 방법을 제시하고 정확한 사상체질 분류 진단기기의 개발을 위한 정면 얼굴과 측면 얼굴에서의 주요 영역을 추출하는 방법을 제안하고자 한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2004.05a
• /
• pp.745-748
• /
• 2004

얼굴 이미지의 대부분은 표본의 수보다 특징 변수의 수가 많기 때문에 이러한 점을 고려한 특징 추출 방법이 필요하다. 본 논문에서는 부분 최소제곱법을 이용하여 특징 벡터의 차원을 축소하는 방법을 제안한다. 전통적인 차원 축소 방법인 주성분 분석은 클래스의 정보를 고려하지 않고 최대 변이를 가지는 성분을 추출하기 때문에, 클래스의 구분에 필요한 특징을 필수적으로 추출하지 못한다. 이에 비해, 부분 최소제곱법은 클래스 변수에 대한 정보를 포함하여 성분을 추출한다. 그러므로, 분류를 하는데 있어서는 주성분 분석에 의해 추출된 성분보다는 부분 최소제곱법에 의해 추출된 성분이 보다 더 예측적이다. 맨체스터와 ORL 얼굴 데이터베이스를 이용하여 실험한 결과, 분류와 차원 축소 측면에서 주성분 분석 방법보다는 부분 최소제곱법을 이용한 방법이 그 성능이 우수함을 알 수 있었다.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.45 no.3
• /
• pp.123-134
• /
• 2008

In this paper, we propose a real-tin e face recognition system that is robust under various lighting conditions. Th Modified Census Transform algorithm that is insensitive to illumination variations is employed to extract local structure features. In a practical face recognition system, acquired images through a camera are likely to be blurred and some of them could be side face images, resulting that unacceptable performance could be obtained. To improve stability of a practical face recognition system, we propose a real-time algorithm that rejects unnecessary facial picture and makes use of recognition consistency between successive frames. Experimental results on the Yale database with large illumination variations show that the proposed approach is approximately 20% better than conventional appearance-based approaches. We also found that the proposed real-time method is more stable than existing methods that produces recognition result for each frame.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.33 no.6
• /
• pp.938-948
• /
• 2009

The purpose of this study was to offer typical facial shapes Korean women in their 20's to 50's. We used facial photographs of 600 Korean women obtained from $2003\sim2004$ Size Korea Project and we measured these photographs indirectly in this study by utilizing the Venus face2D program. Total 62 measurements on the face were measured and analyzed by statistical methods. The results were as follows. First of all, the mean of face length was 196mm, top face length was 62.3mm, middle face length was 68.9mm, bottom face length was 66.5mm, mean of forehead width was 125.1mm. As based on those average sizes, we proposed a average facial size and shape of Korean women and a average facial size and shape of 20's, 30's, 40's and 50's in this study. When examined characteristic of 20's facial shape, it was recognized that the width of forehead was wider and the width of gnathion was smaller than other age groups. In the characteristic of 30's facial shape, the ratios of facial length, top of face, middle of face and bottom of face were balanced well, as comparing with other age groups. Overall, the values of facial measurement of 30's were similar to the averages of total women. In the facial shape of 40's, mean length and width of face each were the smallest among each age group. The eye shape of 40's was more drooped than the average eye shape and the protrusion of the zygomatic bone was significantly different. In case of the facial shape of 50's, it was similar to the facial shape of 40's, but mean lengths and widths of 50's face were slightly larger than the values of 40's. The eye shape of 50's was more drooped than average group and the eye length was the smallest among all age groups.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.6C
• /
• pp.585-592
• /
• 2005

One of the most important things in the researches on diseases is to attach more importance to prevention of a disease and preservation of health than to treatment of a disease, also to foods rather than to medicines. In this context, the most significant concern in examining a patient is to find the presence of disease, and, if any, to diaguose the type of disease, after which a pharmacotherapy is followed. In this paper, various diagnosis methods of Oriental medicines are discussed. And ocular inspection, the most important method among the 4 disease diagnoses of Oriental medicines, is studied. Observing a person's shape and color has been the major method for ocular inspection, which usually has been dependent upon doctor's intuition as of these days. We are developing an automatic system which provides objective basic data for ocular inspection. As the first stage, we applied the signal processing techniques to automatic feature extraction of faces for ocular inspection. Firstly, facial regions are extracted from the point of frontal view, which was followed by extraction of their features. The experiment applied to 20 persons showed that frontal face regions are perfectly extracted, as well as their features, such as eyes, eyebrows, noses and mouths. Future work will seek to address the issues of morphological operation for a few unfinished extraction results, such as combined hair and eyebrows.

• The KIPS Transactions:PartB
• /
• v.13B no.4 s.107
• /
• pp.393-400
• /
• 2006

There are many feature extraction methods for face recognition. We need a new method to overcome the small sample problem that the number of feature variables is larger than the sample size for face image data. The paper considers partial least squares(PLS) as a new dimension reduction technique for feature vector. Principal Component Analysis(PCA), a conventional dimension reduction method, selects the components with maximum variability, irrespective of the class information. So, PCA does not necessarily extract features that are important for the discrimination of classes. PLS, on the other hand, constructs the components so that the correlation between the class variable and themselves is maximized. Therefore PLS components are more predictive than PCA components in classification. The experimental results on Manchester and ORL databases shows that PLS is to be preferred over PCA when classification is the goal and dimension reduction is needed.

• Science of Emotion and Sensibility
• /
• v.13 no.3
• /
• pp.533-540
• /
• 2010

This study was designed to examine the difference in visual attention between the evaluations of facial attractiveness and facial trustworthiness, both of which may be the two most fundamental social evaluation for forming first impressions under various types of social interactions. In study 1, participants were asked to evaluate the attractiveness and trustworthiness of 40 new faces while their gaze directions being recorded using an eye-tracker. The analysis revealed that participants spent significantly longer gaze fixation time while examining certain facial features such as eyes and nose during the evaluation of facial trustworthiness, as compared to facial attractiveness. In study 2, participants performed the same face evaluation tasks, except that a word was briefly displayed on a certain facial feature in each face trial, which were then followed by unexpected recall tests of the previously viewed words. The analysis demonstrated that the recognition rate of the words that had been presented on the nose was significantly higher for the task of facial trustworthiness vs. facial attractiveness evaluation. These findings suggest that the evaluation of facial trustworthiness may be distinguished by that of facial attractiveness in terms of the allocation of attentional resources.