• 한국인터넷방송통신학회논문지
• /
• 제15권4호
• /
• pp.55-61
• /
• 2015

오늘날 IT 기술의 발달로 사람들에게 많은 편의성이 제공되고 있다. 이 중 스마트폰 시대가 열리면서 시장 환경이 급격하게 바뀌고 있다. 스마트폰으로 인터넷을 자유자재로 이용하게 되면서 음란물 시장은 활개를 치고 있다. 상당수 이용자들은 미국과 일본의 모바일 음란사이트에 곧바로 접속한다. 애플이 앱스토어에서 음란물 서비스를 철저하게 차단하고 있지만 모바일 웹 페이지 접속차단은 불가능한 상황이다. 유해 이미지를 탐지하기 위해 본 논문에서 제안하는 피부 특징과 비 피부 특징을 이용한 이미지의 유해성 판단 방법을 제안한다. 제안한 방법은 기존의 이미지 유해성 판단 방법보다 좋은 성능을 보이는 것을 확인하였다.

• 한국IT서비스학회지
• /
• 제6권3호
• /
• pp.241-249
• /
• 2007

This paper describes a real-time face tracking system using effective detector and Kalman filter. In the proposed system, an image is separated into a background and an object using a real-time updated face color for effective face detection. The face features are extracted using the five types of simple Haar-like features. The extracted features are reinterpreted using Principal Component Analysis (PCA), and interpreted principal components are used for Support Vector Machine (SVM) that classifies the faces and non-faces. The moving face is traced with Kalman filter, which uses the static information of the detected faces and the dynamic information of changes between previous and current frames. The proposed system sets up an initial skin color and updates a region of a skin color through a moving skin color in a real time. It is possible to remove a background which has a similar color with a skin through updating a skin color in a real time. Also, as reducing a potential-face region using a skin color, the performance is increased up to 50% when comparing to the case of extracting features from a whole region.

• 한국멀티미디어학회논문지
• /
• 제18권5호
• /
• pp.610-619
• /
• 2015

*In this paper, we propose a real-time face tracking system using an adaptive face detector and a tracking algorithm. An image is divided into the regions of background and face candidate by a real-time updated skin color identifying system in order to accurately detect facial features. The facial characteristics are extracted using the five types of simple Haar-like features. The extracted features are reinterpreted by Principal Component Analysis (PCA), and the interpreted principal components are processed by Support Vector Machine (SVM) that classifies into facial and non-facial areas. The movement of the face is traced by Kalman filter and Mean shift, which use the static information of the detected faces and the differences between previous and current frames. The proposed system identifies the initial skin color and updates it through a real-time color detecting system. A similar background color can be removed by updating the skin color. Also, the performance increases up to 20% when the background color is reduced in comparison to extracting features from the entire region. The increased detection rate and speed are acquired by the usage of Kalman filter and Mean shift.

• 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.

• 한국산학기술학회논문지
• /
• 제18권7호
• /
• pp.350-356
• /
• 2017

실시간 인체 검출에 대한 관심이 높아짐에 따라 피부색을 통한 인체 검출에 대한 연구가 활발히 진행되고 있다. 하지만 대다수 기존 피부 탐지 방법은 정적인 피부색 모델을 이용하기 때문에 색 왜곡이 발생한 영상에서 낮은 탐지율을 보인다. 이러한 문제를 해결하기 위해 본 논문에서는 경사도 맵과 채도, YCbCr 공간의 Cb, Cr 요소를 퍼지로 분류하는 방법을 사용하여 피부영역을 탐지하는 기법을 제시한다. 제안하는 방법의 기본적인 절차는 경사도 맵 생성, 채도 맵 생성, CbCr 맵 생성, 퍼지 분류, 피부영역 이진화 순이다. 이 방법은 색상 이외의 특징을 이용하여 조명, 인종, 나이, 개인차 등에 상관없이 강건하게 피부를 탐지하는 것에 중점을 두고 있다. 색상 이외의 피부 특징은 비피부영역과의 경계가 모호하여 구분이 명확하지 않다. 이를 해결하기 위해 경사도, 채도와 색상 특징간의 관계를 소속함수로 정의하고 이를 이용하여 108가지의 퍼지 규칙을 생성하여 피부영역을 탐지한다. 제안한 방법의 검출 정확도는 86.35%로 기존 방법보다 2~5 % 우수함을 확인하였다.

• 대한화장품학회지
• /
• 제31권3호
• /
• pp.253-257
• /
• 2005

피부노화의 정도를 판정하기 위해 사용되는 주름측정법들은 객관성과 재현성의 확보가 중요한 요소이다. 최근의 경향은 주름의 형태나 깊이에 주는 영향을 최소화하기 위해 주름 측정시 피부에 직접 기계나 도구를 접촉하지 않고 측정하는 비접촉식 측정방법으로 빠르게 전환되고 있는 상황이다. 저자들은 주름측정 기술의 변천 과정을 간단히 살펴보고, 비접촉식 fringe projection 방식의 미세주름 측정기기인 PRIMOS를 중심으로 측정원리, 특징들을 접촉식 측정방법인 모사판을 이용한 방법과 비교하였다.

• Journal of Yeungnam Medical Science
• /
• 제34권1호
• /
• pp.137-139
• /
• 2017

Dermatomyositis (DM) is characterized by progressive proximal limb weakness and typical skin manifestations. The histological findings that show perifascicular atrophy and deposition of membrane attack complex are pathognomic features of DM. Dermatomyositis is categorized into classical DM and non-classical DM, which includes amyopathic DM and DM sine dermatitis. DM sine dermatitis is seldom described because of its rarity, making the diagnosis more challenging. We report a case of DM sine dermatitis, a rare phenotype of DM.

• 한국실내디자인학회논문집
• /
• 제23권4호
• /
• pp.83-93
• /
• 2014

Because the 'image' is the 'reality' in this era, there are the characteristics dematerialized between reality and non-reality in the contemporary architecture. These are promoting individualization, differentiation and multi-layered time with the development of electronic technology. This trend emphasizes the importance of imagines that are not only homogenized, simultaneous but also overlapped, multi-layered, discriminatory. Perspectives and essential characteristics of the architectural skin are changing in terms of the technical and social awareness and that means the skin has features as a complex body. Recently as an imagine creator, the architectural skin make form of media boundaries reflecting the various relationships between the observer and the external environment and also, the interior space become another sensory skin by removing the boundaries of the internal and external. It is important that making an identity of the architecture defined by the media or the imagine as well as the importance of space in architecture. These changes of skin make the third space based on the viewer's imagination and show the potential of new architectural skin with the expansion space by blurring the boundary between reality and illusion. It occurs to the diversity of the architectural skin with the identity. It will more diversified and be recognized immediately and sensibly through the interface attributes in contact with the city directly. In addition, it is more important that the skin become a unified body related with urban, social and cultural context.

• Asian Pacific Journal of Cancer Prevention
• /
• 제16권7호
• /
• pp.3051-3056
• /
• 2015

Background: Skin self-examination (SSE) may facilitate early diagnosis of melanoma at a potentially curable stage. Little data are available concerning the SSE frequency and knowledge about the symptoms of melanoma in non-patient populations. The aim of our study was to assess the performance of skin self-examination, recognition of potential melanoma symptoms as well as behavior related to sun exposure among web users in Poland. Materials and Methods: A cross-sectional study was conducted among readers of a scientific portal. Invited respondents were asked to complete an online questionnaire. Finally, statistical analysis was conducted on 4,919 surveys towards potential clinical signs of melanoma and SSE performance. Results: Approximately 60% of respondents had ever performed SSE in their life. Only 18.4 % declared performance on a regular, monthly, basis. Factors promoting this activity were established to be bigger place of residence, higher education and sensitive skin phototype, higher level of knowledge concerning melanoma, safe tanning rules and, especially, past surgical excision of naevi. Declared longer use of tanning beds was linked to understanding better the importance of clinical features of melanoma. Awareness of hazardous behavior during sunbathing is associated with the attempts to change them. Conclusions: Regular SSE is not a common practice, whilst the knowledge about the clinical features of melanoma is varied. Therefore, constant pressure should be put on promotion of regular skin self-examination and teaching its proper techniques, including familiarity with the ABCD (asymmetry; border; color; diameter) rule and its extension of "EFG" (elevated, firm, progressive growth) criteria.

• 한국콘텐츠학회논문지
• /
• 제17권1호
• /
• pp.137-144
• /
• 2017

얼굴 검출은 복잡한 배경 내에서 다양한 얼굴의 자세로 인해 여전히 어려운 문제에 직면하고 있다. 본 논문은 피부색과 깊이 정보를 기반으로 한 한명 또는 여러 명의 얼굴을 검출하는 효과적인 알고리즘을 제안한다. 먼저 우리는 컬러 영상에서 가우시안 혼합 모델을 이용한 피부색 검출 방법에 대해 소개한다. 그리고 Kinect V2의 깊이 센서를 이용하여 획득한 3차원의 깊이 정보는 배경으로부터 사람의 몸을 분할할 때 유용하다. 그리고 레이블링 과정에서 여러 개의 특징을 이용하여 얼굴이 아닌 영역은 성공적으로 제거된다. 실험 결과를 통해 제안한 얼굴 검출 알고리즘은 다양한 조건과 복잡한 배경에서 얼굴이 효과적으로 검출되는 것을 확인할 수 있다.