• 한국통신학회논문지
• /
• 제36권8B호
• /
• pp.971-978
• /
• 2011

한의학의 진단 이론 중에는 얼굴의 형태 및 색상을 보고 인체 장기의 상태를 판단하는 방법이 있다. 즉, 얼굴을 통해 인체 장기의 이상 유무를 판단함으로써 건강 상태를 진단하는 행위로 이를 활용한 의료 서비스가 발전, 적용되고 있다. 따라서 본 논문에서는 한의학적 진단 이론을 지반으로 간 기능 상태와 관련된 얼굴 영역의 왼뺨, 흰 눈동자를 분류하고 알코올이 누적됨에 따라 변화되는 색상 분석을 수행하였다. 이를 위해 얼굴 영상에서 왼뺨, 흰 눈동자 영역을 추출하고 Lab 디지털 색체계를 적용하여 알코올 누적 단계에 따라 왼뺨 및 흰 눈동자 영역의 색상이 변화되는 패턴을 분석하고 이를 기반으로 간 기능과의 상관성을 의학적으로 분석하는 연구를 수행하였다.

• 대한전자공학회논문지SP
• /
• 제42권1호
• /
• pp.25-31
• /
• 2005

본 논문에서는 컬러 영상에서 Support Vector Domain Description (SVDD)를 이용한 얼굴 검출 방법을 제안한다. 기존의 훈련을 통한 얼굴 검출 방법은 얼굴 영상과 얼굴이 아닌 영상을 모두 사용해야 한다. 그러나, SVDD를 이용한 얼굴 검출은 단지 훈련을 위해 얼굴 영상만이 사용된다. SVDD의 훈련을 통해 나오는 값인 반지름과 중심 좌표를 통해 얼굴을 검출한다. 또한, 엔트로피를 이용한 임계값 추출 방법(Entropic Threshold)을 통해 얼굴 특징을 추출하고, 슬라이딩 윈도우(sliding window)기법을 통해 성능을 개선한다. 주성분 분석(Principle Component Analysis) 과 SVDD를 이용한 얼굴 검출 방법의 비교 실험을 통해 본 논문이 제안한 방법의 효율성을 확인한다.

• 한국지능시스템학회논문지
• /
• 제13권4호
• /
• pp.461-468
• /
• 2003

In a sequence of images obtained by surveillance cameras, facial regions appear very small and their colors change abruptly by lighting condition. This paper proposes a new face detection scheme, robust on complex background, small size, and lighting conditions. The proposed method is consisted of three processes. In the first step, the candidates for the face regions are selected using face color distribution and motion information. In the second stage, the non-face regions are removed using face color ratio, boundary ratio, and average of column-wise intensity variation in the candidates. The face regions containing eyes and mouth are segmented and classified, and then they are scored using their topological relations in the last step. To speed up and improve a performance the above process, a block based image segmentation technique is used. The experiments have shown that the proposed algorithm detects faced regions with more than 91% of accuracy and less than 4.3% of false alarm rate.

• 한국의류산업학회지
• /
• 제14권6호
• /
• pp.918-927
• /
• 2012

This study identified the aesthetic characteristics of the face description in late Joseon Dynasty beauty paintings. A total of 24 beauty paintings were selected as representative of the late Joseon Dynasty genre of painting works. The paintings were analyzed by the shape, color, and physiognomy of beauty trends from the components of women's faces expressed in the works of artists. The results of this study showed that the shape of the face components expressed a round, curved and thin line. Colors were expressed through Obang-sack (a traditional Korean color). Also the physiognomy of the late Joseon Dynasty's women was soft, wise, economical and brilliant. A round-forehead meant that economical and virtuous housekeeper, thin crescent shaped eyebrows denoted women of wisdom and excellent sensitivity. Single long thin eyelids and implied a women of longevity. A round curved nose were eager tobe a wise mother and a good wife. Small concave lips were desired eagerly by gentle and intelligent women. A curve face implied a subjective women of insight and good memory. In conclusion, the late Joseon Dynasty beauty paintings expressed a traditional Korean beauty face and a modern baby face. The data are useful for the aesthetic standards of modern through meaning of Korean traditional beauty.

• 한국패션뷰티학회지
• /
• 제1권1호
• /
• pp.95-104
• /
• 2003

Just as costumes reflect the spirit of the time, hair styles echo the social changes and even facilitate them, being used as a means of communication. In short, hair styles reflect the cultural life of the time dynamically. In our modern times, fashion is moving very fast, and such a phenomenon is more conspicuous in hair styles. While individuals are eager to pursue their own individuality, hair styles play a leading role in fashion, excelling the costumes. In this sense, we need to note that hair styles may be related with individual, social and psychological factors. As people are more interested in hair colors, the scope of hair color selection becomes wider. People visit beauty shops to have their hair colors changes rather than have their hairs cut. Selection of a hair color seems to be deeply related with individuals' psychological states. Since hair colors have much effects on their facial images, hair designers need to have an empathy with their customers. Each person has his or her own unique image, and his/her selection of hair colors is affected much by external environment as well as his/her traits. With such basic assumptions in mind, this study was aimed at analyzing the preferences of hair colors by those in their 20's, 30's and 40's who are more interested in their hair colors. To this end, their preferences of or tendencies for hair colors were surveyed by sex, age group and job.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2008년도 학술대회 논문집 정보 및 제어부문
• /
• pp.153-154
• /
• 2008

Digital photographic analysis is currently considered as a routine procedure in clinic because periodic follow-up examinations can provide meaningful information for diagnosis. However, it is impractical to separately evaluate all suspicious lesions with conventional digital photographic systems, which have inconsistent characteristics of the environmental conditions. To address the issue, it is necessary for total diagnostic evaluation in clinic to integrate conventional systems. Previously, a multimodal digital photographic imaging system, which provides a conventional color image, parallel and cross polarization color images and a fluorescent color image, was developed for objective evaluation of facial skin lesions. Based on our previous study, we introduce a commercial product, "DermaVision-PRO," for routine use in clinical application in dermatology. We characterize the system and describe the image analysis methods for objective evaluation of skin lesions. In order to demonstrate the validity of the system in dermatology, sample images were obtained from subjects with various skin disorders, and image analysis methods were applied for objective evaluation of those lesions.

• Journal of Information Processing Systems
• /
• 제9권1호
• /
• pp.141-156
• /
• 2013

In this paper we propose a method to detect human faces in color images. Many existing systems use a window-based classifier that scans the entire image for the presence of the human face and such systems suffers from scale variation, pose variation, illumination changes, etc. Here, we propose a lighting insensitive face detection method based upon the edge and skin tone information of the input color image. First, image enhancement is performed, especially if the image is acquired from an unconstrained illumination condition. Next, skin segmentation in YCbCr and RGB space is conducted. The result of skin segmentation is refined using the skin tone percentage index method. The edges of the input image are combined with the skin tone image to separate all non-face regions from candidate faces. Candidate verification using primitive shape features of the face is applied to decide which of the candidate regions corresponds to a face. The advantage of the proposed method is that it can detect faces that are of different sizes, in different poses, and that are making different expressions under unconstrained illumination conditions.

• 한국지능시스템학회논문지
• /
• 제13권2호
• /
• pp.216-221
• /
• 2003

본 논문에서는 다양한 환경하에서 인간의 식별과 감정을 인식할 수 있는 감정 인식 알고리즘을 제안한다. 제안된 알고리즘을 구현하기 위해, 먼저, CCD 칼라 카메라에 의해 획득한 원 영상으로부터 피부색을 이용해 얼굴영상을 얻는 과정을 거친다. 그 다음, 주요 요소분석을 기본으로 하는 얼굴인식기술인 Eigenface를 사용하여 이미지들을 고차원의 픽셀공간으로부터 저차원공간으로의 변환하는 과정을 거친다. 제안된 개인에 대한 식별과 감성인식은 사용한 특징벡터들의 추출로 인한 Eigenface의 가중치와 상관관계를 통해 이루어진다. 즉, 영상의 가중치로부터 개인에 대한 식별과 감성정보를 찾는 방법을 제안한다. 마지막으로, 실험을 통해 제안된 방법의 응용가능성을 보인다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 하계종합학술대회 논문집
• /
• pp.583-586
• /
• 1999

In this paper, the wavelet transform is performed in the input 256$\times$256 color image and decomposes a image into low-pass and high-pass components. Since the high-pass band contains the components of three directions, edges are detected by combining three parts. After finding the position of face using the histogram of the edge component, a face region in low-pass band is cut off. Since RGB color image is sensitively affected by luminances, the image of low pass component is normalized, and a facial region is detected using face color informations. As the wavelet transform decomposes the detected face region into three layer, the dimension of input image is reduced. In this paper, we use the 3000 images of 10 persons, and KL transform is applied in order to classify face vectors effectively. FCM(Fuzzy C-Means) algorithm classifies face vectors with similar features into the same cluster. In this case, the number of cluster is equal to that of person, and the mean vector of each cluster is used as a codebook. We verify the system performance of the proposed algorithm by the experiments. The recognition rates of learning images and testing image is computed using correlation coefficient and Euclidean distance.

• 한국정보통신학회논문지
• /
• 제10권3호
• /
• pp.542-548
• /
• 2006

본 논문에서는 컬러 정지 영상을 대상으로 상반신 인물 영상이 입력되었을 때, 얼굴 영역을 추출하고 검증하는 방법을 제안한다. 본 논문의 얼굴 추출과정은 1단계로 영상 내 피부색 영역을 추출한 다음, 후보 영역들에 대한 공간적 제한조건을 이용하여 1차 얼굴 후보 영역을 결정한다. 2단계에서는 얼굴 구성 요소 중 가장 두드러진 특징으로서 눈 영역을 탐색하고, 눈 영역을 기준으로 한국인의 얼굴에 대한 구조적 통계값을 적용한다. 이로서 얼굴 포함 최소 사각형 후보 영역을 결정한다. 마지막 3단계에서는 영상 내 색상 정보와 공간 정보 그리고 구조적 통계치로부터 결정된 얼굴 후보 영역에 대하여 얼굴 영역의 텍스춰(texture)를 Wavelet Packet Analysis를 이 용해 조사함으로써 얼굴 영역을 확정하게 된다.