• International Journal of Contents
• /
• 제9권3호
• /
• pp.9-14
• /
• 2013

In this paper, we will examine single face tracking algorithms with scaling function in a mobile device. Face detection and tracking either in PC or mobile device with scaling function is an unsolved problem. Standard single face tracking method with particle filter has a problem in tracking the objects where the object can move closer or farther from the camera. Therefore, we create an algorithm which can work in a mobile device and perform a scaling function. The key idea of our proposed method is to extract the average of skin color in face detection, then we compare the skin color distribution between the detected face and the tracking face. This method works well if the face position is located in front of the camera. However, this method will not work if the camera moves closer from the initial point of detection. Apart from our weakness of algorithm, we can improve the accuracy of tracking.

• 한국의류학회지
• /
• 제29권7호
• /
• pp.959-967
• /
• 2005

The color of apparels has the interaction of the face skin colors of the wearers. This study was carried out to classify the face skin colors of Korean males into several similar face skin colors in order to extract favorable colors which flatter to their face skin colors. The criterion that select the new subjects who have the classified face skin colors have to be decided. With color spectrometer, JX-777, face skin colors of subjects were measured quantitatively and classified into three clusters that had similar hue, value and chroma with Munsell Color System. Sample size was 418 Korean males and other 15 of new males subjects. Data were analyzed by K-means cluster analysis, ANOVA, Duncan multiple range test, Stepwise discriminant analysis using SPSS Win. 12. Findings were as follows: 1. 418 subjects who have YR colors were clustered into 3 kinds of face skin color groups. 2. Discriminant variables of face skin colors was 4 variables : L value of forehead, v value of cheek, c value of forehead, and b value of cheek from standardized canonical discriminant function coefficient 1 and c value of forehead, L value of forehead, b value of cheek. and L value of cheek from standardized canonical discriminant function coefficient 2. 3. Hit ratio of type 1 was $92.3\%$, of type 2 was $96.5\%$ and of type 3 was $92.6\%$ by the canonical discriminant function of 4 variables. 4. The canonical discriminant function equation 1 and 2 were calculated with the unstandardized canonical discriminant function coefficient and constant, the cutting score, and range of the score were computed. 5. The criterion that select the new subjects who have the classified face skin colors was decided.

• Asian Pacific Journal of Cancer Prevention
• /
• 제17권12호
• /
• pp.5257-5264
• /
• 2016

Background: Though people of color (POC) are less likely to become afflicted with skin cancer, they are much more likely to die from it due to delay in detection or presentation. Very often, skin cancer is diagnosed at a more advanced stage in POC, making treatment difficult.The purpose of this research was to improve awareness regarding skin cancers in people of color by providing recommendations to clinicians and the general public for early detection and photo protection preventive measures. Methods: Data on different types of skin cancers were presented to POC. Due to limited research, there are few resources providing insights for evaluating darkly pigmented lesions in POC. Diagnostic features for different types of skin cancers were recorded and various possible risk factors were considered. Results: This study provided directions for the prevention and early detection of skin cancer in POC based on a comprehensive review of available data. Conclusions: The increased morbidity and mortality rate associated with skin cancer in POC is due to lack of awareness, diagnosis at a more advanced stage and socioeconomic barriers hindering access to care. Raising public health concerns for skin cancer prevention strategies for all people, regardless of ethnic background and socioeconomic status, is the key to timely diagnosis and treatment.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.105-107
• /
• 2004

In this work, we suggested the method which improves the efficiency of the face detection algorithm using Pulse-Coupled Neural Network. Face detection algorithm which uses the color information is independent on size, angle, and obstruction of a face. But the use of color information encounters some problems arising from skin-tone color in the background, intensity variation within faces, and presence of random noise, and so on. Depending on these conditions, we obtained the mean and variance of skin-tone colors by experiments. Then we introduce a preprocess that the pixel with a mean value of skin-tone colors has highest level value(255) and the other pixels in the skin-tone region have values between 0 and 255 according to a normal distribution with a variance. This preprocess leads to an easy decision of the linking parameters.

• 한국의류학회지
• /
• 제30권4호
• /
• pp.567-581
• /
• 2006

The purpose of this research is to provide the basic data for the development of make-up color application system, based of Korean's skin tone and the preference in make-up color to enhance the effectiveness of the education of beauty in universities. The research was conducted by the previous studies, the analyses of sale's rate of hue-cosmetics, the analytic experiment of color of cosmetics by using Spectrum Color Analyzer and other experimental researches. This research, based on the results of three preliminary researches, shows the result of evaluation from perceivers which has been come out from the experiment of having one model in her twenties being changed with twenty-two different conditions of make-up. Here follows the result of the research. Firstly, there was difference on perceiving images in terms of the gender of perceivers and especially male-group tend to have clearly perceived the gap between elegance-greyish purple, orange-natural, red-classic on monochrome make-up and contrast make-up. Secondly, in terms of lip-colors, salmon pink and pink was regarded positively to both female and male subjects and to male subjects, greyish purple was thought to be better on darker skin-tone and to female subjects, better on lighter skin-tone. Thirdly, on image make-up, romantic gives intelligent image regardless of skin-tone and gender, especially gives more positive looks to male subjects. Natural and classic elements were perceived more positively on darker skin-tone and had bigger perceiving gap in female subjects. Fourthly, in preference rate, male subjects normally preferred the look with make-up than female subjects did and salmon pink and pink lip color was preferred on the darker skin-tone.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2011년도 춘계학술대회
• /
• pp.617-618
• /
• 2011

인간은 누구나 좋아하는 색이 자연적으로 혹은 인위적으로 존재한다. 본 논문에서는 인간에게 어울리는 색을 찾는 방법에 대하여 제시하고자 한다. 우선, 피부의 색, 머리카락의 색, 눈동자의 색과 같이 색의 기본을 이루는 톤에 대하여 알아본다. 다음으로 색을 봄, 여름, 가을, 겨울의 사계절로 나누어 피부의 색, 머리카락의 색, 눈동자의 색과 본인이 좋아하는 것이나 성격에 따라서 나누어지는 사계절 색채이론을 설명한다. 그리고 각 계절별 컬러의 특성을 살펴 보도록 한다.

• 대한전자공학회논문지SP
• /
• 제39권2호
• /
• pp.69-78
• /
• 2002

본 논문에서는 복잡한 배경에서의 얼굴 추출 방법을 제안한다. 제안된 알고리즘은 적응 퍼지 색 분할기법을 사용하여 얼굴색과 머리색을 분할시킨다. 얼굴색 분포는 Y,Cb,Cr 색 공간내에서 유도되어지고, 조명값에 적응적인 퍼지 시스템을 사용하여 얼굴색을 구분해낸다. 머리색은 RGB 색 공간내에서 구분되어진다. 전처리 과정을 거쳐 추출되어진 얼굴색과 머리색 영역에 컨벡스 헐을 적용하여 그들의 관계를 통해 최종적인 얼굴 영역이 추출되어진다. 제안된 방법은 기존의 패턴 매칭 방법에 비해 효율적인 성능을 나타낸다. 제안된 알고리즘의 유효성을 실험을 통해 증명하며, 색 영역에서의 제한 조건 없이 성공적으로 얼굴 영역을 추출해 냄을 알 수 있다.

• 한국정보과학회논문지:컴퓨팅의 실제 및 레터
• /
• 제16권1호
• /
• pp.35-44
• /
• 2010

본 논문에서는 입력영상에서 적응적으로 피부색상 모델을 생성하여 얼굴을 탐지하는 방법을 제안한다. 제안하는 방법의 기본적인 절차는 먼저 눈의 특징을 인공신경망에 적용하여 눈 후보를 찾은 후, 그 주변의 색상을 이용하여 피부영역의 색상값 분포를 찾는다. 그 다음은 피부영역으로 검출된 색상값 분포를 이용하여 얼굴영역을 산출하고, 해당 얼굴영역 내에서 입 후보를 찾아 눈 후보와 입 후보의 구조적인 관계가 얼굴 구조와의 일치여부를 판단하여 얼굴영역을 검증하는 과정을 거친다. 이 방법은 눈을 찾아서 피부영역을 적응적으로 검출하기 때문에 기존의 얼굴탐지 방법들의 문제인 피부색상의 왜곡으로 인한 오검출을 해결하였다. 실험은 눈 탐지와, 피부 탐지, 입 탐지, 얼굴탐지에 대해 각각 수행하였다. 실험을 통하여 기존의 주요 방법들 보다 우수한 결과를 보였다.

• 한국산학기술학회논문지
• /
• 제16권2호
• /
• pp.1414-1419
• /
• 2015

영상에서 피부영역을 탐지하는 방법은 색상 정보를 이용하여 탐지하는 방법이 일반적이다. 하지만 영상의 채도가 낮아지는 경우 색상정보가 손실되어 올바른 피부영역 탐지가 어렵다는 단점이 있다. 따라서 본 논문은 촬영 시 밝은 조명에 의해 채도 정보가 낮아진 피부 영상의 색상 보정 방법을 제안한다. 제안한 방법의 색상 보정 절차는 채도 영상 획득 및 저채도 영역 분류, 영역 분할, 분할한 저채도 영역에서의 채도 및 색상값 추출, 색상 보정 순이다. 이 방법은 영상에서 채도가 낮은 부분을 추출한 후 해당 영역 및 주변영역의 색상과 채도를 추출하는 방법을 통해 원 색상과 유사한 색상을 예측하여 적용한다. 따라서 저채도 영역을 올바르게 산출하는 방법이 선행되어야 한다. 저채도 영역을 구하는 과정에서 보다 정확한 영역 분할을 위하여 HSV 색상공간의 Hue 값에 오츠가 제안한 다중문턱치를 이용하여 이진 영상을 만든 후 사용하였다. 170장의 인물 사진들을 사용하여 실험을 수행한 결과, 제안한 방법을 사용하지 않은 피부 결과에 비해 약 5.8% 이상 검출율이 높게 나타났으며, 제안하는 방법이 피부색 탐지를 위한 전처리에 적합함을 확인하였다.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2003년도 가을 학술발표논문집 Vol.30 No.2 (2)
• /
• pp.559-561
• /
• 2003

Human face detection plays an important role in variable applications. A face detection method based on skin-color information and facial feature in color images is proposed in this paper. First, the RGB color space is transformed to YCbCr space and only the skin region is extracted with the skin color information. And then, the candidate where face is likely to exist is selected after labeling processing. Finally, we detect facial features in face candidate. The experimental results show that the method proposed here is effective.