• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -3
• /
• pp.1515-1518
• /
• 2002

This paper proposes an active contour model to detect facial regions in a given image. Accordingly we use the color information human faces which is represented by a skin color model. We evolve the active contour using the level set method which allows for cusps, corners, and automatic topological changes. Experimental results show the effectiveness of the proposed method.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제15권3호
• /
• pp.180-185
• /
• 2015

Digital infrared thermal imaging is a non-invasive adjunctive diagnostic technique that allows an examiner to visualize and quantify changes in skin surface temperature. The asymmetry of temperature differences between the diseased and the contralateral healthy body parts can be automatically analyzed and has been studied in many areas of medical science. In this paper, we propose a method for intelligent automatic asymmetry detection based on a K-means analysis and a YCbCr color model. The implemented software successfully visualizes an asymmetric distribution of colors with respect to the patients’ health status.

• 한국산학기술학회:학술대회논문집
• /
• 한국산학기술학회 2012년도 춘계학술논문집 1부
• /
• pp.182-186
• /
• 2012

human tyrosinase (hTyr) catalyzes first and the rate limiting step in the synthesis of polymerized pigment, melanin which determines skin, hair and eye colors. Mutation of hTyr often brings about decrease of melanin production and further albinism. Meanwhile, a number of cosmetic companies providing skincare products for woman in Asia-Pacific region have tried to develop inhibitors to bright skin color for several decades. In this study, we built a 3D structure by comparative modeling technique based on the crystal structure of tyrosinase from bacillus megaterium as a template to serve structural information of hTyr. According to our model and sequence analysis of type 3 copper protein family proteins, two copper atoms of active site located deep inside are coordinated with six strictly conserved histidine residues coming from four-helix-bundle. Cavity which accommodates substrates was like funnel shape of which entrance was wide and expose to solvent. In addition, protein-substrate and protein-inhibitor complex were modeled with the guide of van der waals surface generated by in house software. Our model suggested that only phenol group or its analogs can fill the binding site near nuclear copper center because inside of binding site has narrow shape relatively. In conclusion, the results of this study may provide helpful information for designing and screening new anti-melanogensis agents.

• 방송공학회논문지
• /
• 제13권6호
• /
• pp.875-882
• /
• 2008

영상으로부터 사람의 귀를 검출하는 것은 생체 인식 분야에 있어서 매우 중요한 분야이다. 따라서 본 논문에서는 측면 얼굴 영상으로부터 귀를 검출하는 알고리즘을 제안한다. 제안하는 알고리즘은 먼저 피부색을 이용하여 얼굴 영역을 검출하고 검출된 얼굴 영역으로부터 Haar-like 특징을 이용하여 귀를 검출한다. 그리고 검출된 귀를 검증하기 위해 표준 템플릿을 이용하여 검출된 귀를 검증한다. 실험 결과 본 논문에서 제안된 방법은 기존의 연구에 비해 60%의 처리 속도 향상과 92%의 검출 성공률을 보였다.

• 한국지능시스템학회논문지
• /
• 제15권7호
• /
• pp.813-816
• /
• 2005

귀 영역 검출은 무구속 귀 인식 시스템에서 중요한 요소 중에 하나이다. 본 논문에서는 얼굴 측면 영상에서의 귀 영역 검출방법을 제안한다. 제안하는 방법은 모양정보와 색상정보를 활용하는 인간의 인식과정을 모방하여 만들었다. 먼저 획득된 영상에서 피부색을 이용하여 얼굴영역을 검출하고, 검출된 얼굴영역에서 에지정보를 이용하여 귀후보 영역을 검출한다. 그리고 실제 귀영역인지를 검증하기 위해서는 통계적 학습 이론에 근거한 SVM(Support Vector Machine)을 이용한다 제안된 방법은 조명이 안정적인 실내 환경에서 높은 검출율을 보였다.

• 한국멀티미디어학회논문지
• /
• 제16권9호
• /
• pp.1044-1056
• /
• 2013

본 논문에서는 피부 색소 침착 영역을 검출하고 침착 정도를 측정하는 알고리즘을 제안한다. 제안한 알고리즘에서는 먼저 훈련 영상(training image)의 통계적 분석을 통해 피부 영역에 대한 GMM-EM 클러스터링 기반 컬러 모델을 구축하고 이를 통해 피부 영역을 추출한 후, 형태학적 처리(morphological processing)를 통해 피부 영역에 존재하는 잡음을 제거한다. 이후 ICA (independent component analysis) 알고리즘을 통해 피부 영역을 헤모글로빈 및 멜라닌 성분으로 분리하고, 각 성분에 대한 투영 변환 블록 계수에 의하여 색소 침착 영역 및 크기를 결정한다. 성능 평가를 위한 모의실험으로부터 제안한 색소 침착 검출 알고리즘은 피부 색소 침착 영역의 크기 및 침착 정도를 정확하게 검출할 수 있음을 확인하였다.

• 한국정보통신학회논문지
• /
• 제14권8호
• /
• pp.1827-1835
• /
• 2010

본 논문은 사용자 사진에서 ASM(Active Shape Model)을 이용하여 얼굴의 각 특징 점을 추출하고, 추출 된 특징점을 이용하여 화장할 부분의 영역을 생성 한다. 기존의 가상 메이크업 프로그램에서는 사용자가 수동적으로 몇 개의 특징 점을 정확히 선택해야 하는데서 불편함을 초래했다. 본 논문에서 제안하는 가상 메이크업 프로그램에서는 ASM을 이용하여 사용자의 입력을 필요로 하지 않는다. 자연스러운 화장 효과를 표현하기 위해서 기본적인 알파 블렌딩을 각각 화장품의 특징에 맞게 변형하여 사용자 피부색과 화장품의 색을 혼합한다. 얼굴 윤곽, 눈, 눈썹, 입술, 볼의 영역을 생성하고, Foundation, Blush, Lip Stick, Lip Liner, Eye Pencil, Eye Liner, Eye Shadow 종류의 화장을 할 수 있게 구현하였다.

• 한국지능시스템학회논문지
• /
• 제8권4호
• /
• pp.43-52
• /
• 1998

인간의 시각의 물체를 구분할 수 있는 가장 큰 특징 중의 하나가 색상 정보이므로 본 논문에서는 칼라 정보를 이용하여 손영역을 획득한다. 카메라를 통하여 입력된 영상의 칼라 값은 동일한 물체에 대해서도 조명의 강도와 방향에 따라 변하기 때문에 사전 지식이 없이는 정확한 손영역을 획득하기가 어렵다. 따라서 본 논문에서는 손영역을 획득하기 전에 학습단계를 통하여 손색상 모델을 생성한다. 뿐만 아니라 사용자의 움직임에 따른 칼라 값의 변화를 손색상 모델에 반형하기 위하여 칼만필터를 이용한다. 이때, 칼라필터는 다음 시점의 손영역을 예측하여 탐색 공간의 최적화 하므로 시스템의 처리 속도를 향상시킨다. 실험에서는 손영역 획득 모듈을 구현함으로써 제안된 방법의 타당성을 검증하였다.

• Asian Pacific Journal of Cancer Prevention
• /
• 제13권10호
• /
• pp.5011-5017
• /
• 2012

Background: Overexposure to sunlight in childhood and the adolescent period and associsated sunburns significantly increase the risk of skin cancer in adulthood. In Turkey, the incidence of skin cancer in the general population is 0.8%. The incidence is 0.6% and the mortality rate is 0.4% for men, while these rates are 1.0% and 0.7%, respectively, for women. If skin cancer is found early, its treatment is facilitated. Therefore, personal skin examination is important for early diagnosis. Objectives: Our aim was to determine the effects of training for raising consciousness among adolescents to protect against skin cancer by influencing skin self examination behavior. Method: This quasi experimental intervention study was conducted between February and April 2012 in Izmir. The study population consisted of students attending $6^{th}$, $7^{th}$ and $8^{th}$ classes of a primary school (n:302). No sampling was performed. Data were collected with a form developed by the researchers based on the literature. The first part of form is aimed to determine demographic characteristics of adolescents (3 questions) and their risk status of skin cancer (6 questions). The second part was prepared for skin cancer risks of adolescents (8 questions) and indications of skin cancer (12 questions). The last part was intended to determine their knowledge about skin self examination (4 questions) and behavioral stages of skin self examination (1 question). Data collection was achieved with a questionnaire form in three phases. In the 1st phase, data about demographic characteristics of students, risk status of skin cancer, knowledge level of skin cancer and behavior stages were collected. In the $2^{nd}$ phase, skin self examination training based on the transtheoretical model was performed within the same day just after obtaining preliminary data. In the $3^{rd}$ phase, adolescents were followed up three times to establish the efficacy of the training (on the $15^{th}$ day after training program and at end of the $1^{st}$ and $2^{nd}$ months). Follow-up data were evaluated by questioning skin self examination performing behavior stages through electronic mail. Results: Half of the adolescents (50.5%) are male, and 58.4% of them are 13 years old with a mean age of $12{\pm}1.15$ years. About 29.4% of adolescents had brown hair color, 37.9% had brown/hazel eye color, 29.4% had white skin, and 47.2% had fewer than 10 moles in their body. The pretest mean score on knowledge level about risks of skin cancer was found to be $4.19{\pm}1.96$, while the post-test mean score was $6.79{\pm}1.67$ (min:0, max:8).The pretest mean score about indications of skin cancer was $7.45{\pm}3.76$, while the post-test mean score was $10.7{\pm}2.60$ (min:0, max:12). The increases were statistically significant (p<0.05). The behavior "I do not perform skin self examination regularly in every month and I do not think to perform it in the next 6 months" was reduced from 52.8 to 35.5% after training. Conclusion: The training program organized to raise consciousness among adolescents for protection against skin cancer increased the knowledge level about risks and indications of skin cancer and it also improved the behavior of performing skin self examination.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 1998년도 가을 학술발표논문집 Vol.25 No.2 (3)
• /
• pp.765-767
• /
• 1998

Many application in human computer interaction(HCI) require tacking a human face and facial features. In this paper we propose efficient parallel processing system for face tracking under heterogeneous networked. To track a face in the video image we use the skin color information and connected components. In terms of parallelism we choose the master-slave model which has thread for each processes, master and slaves, The threads are responsible for real computation in each process. By placing queues between the threads we give flexibility of data flowing