• 전자공학회논문지SC
• /
• 제45권6호
• /
• pp.123-131
• /
• 2008

한의학에서 혀의 상태는 인체 내부의 생리적 병리적 변화와 같은 건강 상태를 진단하는 중요한 지표로 활용된다. 혀의 상태를 진단하는 방법(설진)은 편리할 뿐 아니라 비침습적이므로, 한의학에서 널리 활용되고 있다. 하지만, 설진은 광원이나 환자의 자세, 의사의 건강 조건과 같은 검사 환경에 따라 많은 영향을 받는다. 객관적이고 표준화된 진단을 위한 자동 설진 시스템을 개발하기 위하여 촬영된 얼굴 영상으로부터 혀를 영역분할하고 설태를 분류하는 것은 필수적이지만 혀와 입술, 입 근처의 피부색이 서로 유사하므로 쉽지 않은 일이다. 제안된 방법은 전처리 과정과 영역분할, 혀의 구조로부터 발생하는 음영 영역의 지역 최소값 위치 검색, 지역 최소값의 교정, 컬러의 차이를 최대로 하는 위치를 찾는 컬러 경계면 탐색, 척의 기하적인 특성에 일치하는 경계면 선택, 경계면 평활화로 구성되어 있으며, 여기서 전처리 과정은 계산량의 감소를 위한 부 표본화, 히스토그램 평활화, 경계면 강화를 수행한다. 이러한 시스템적인 과정을 거치면, 영역분할된 혀를 획득할 수 있게 된다. 제안된 방법으로 분할된 영역은 초과적으로 혀가 아닌 영역을 제외해 낼 뿐 아니라 정확한 진단을 위해 중요한 정보를 제공함을 한의사의 진단 유효도 평가점수를 통해 확인할 수 있었다. 제안된 방법은 진단의 객관화와 표준화에 기여할 뿐만 아니라 u-Healthcare 시스템에도 활용 가능하다.

• 전자공학회논문지
• /
• 제51권6호
• /
• pp.175-182
• /
• 2014

한방에서 설진은 초기 병증을 진단할 수 있는 방법으로 객관적인 진단 지표의 개발은 중요한 연구 분야 가운데 하나이다. 그러나 이전의 대부분의 설진 시스템은 한의사의 간섭을 배제한 자동 진단을 위한 전문가 시스템으로서 진료를 위한 객관화된 진단 지표의 생성에 있어서 어려움이 있었다. 따라서 본 논문에서는 한방 설진에 있어서 한의사의 진료 행위에 의해서 최적화된 설진을 위한 진단 지표를 계산하는 컴퓨터 지원 진단 소프트웨어를 제안한다. 개발한 소프트웨어는 반자동 방식으로 설질 추출을 위해서는 한의사의 매뉴얼 방식을 이용하고, 설태 영역을 자동 분할하여 비설태와 설태의 색상, WTCI 등에 대한 수치적 진단 지표를 한의사에게 실시간으로 제공한다. 또한, 설태 비율을 이용하여 소태, 박태, 후태의 분류 확률 추정 값과 진료 편의를 위한 전자의무기록 차트 기능도 제공한다. 구현된 컴퓨터 지원 진단 소프트웨어의 유효성 평가를 위해서는 60명의 피실험자를 대상으로 혀 영상을 구축하고, 설진 소프트웨어를 실험한 결과 피실험자의 95%가 소프트웨어 사용-유효성을 나타냈다.

• 대한한의진단학회지
• /
• 제20권2호
• /
• pp.51-65
• /
• 2016

Objectives This study was conducted to suggest a standard operating procedure (SOP) in order to improve the reliability of tongue-image analysis system. Methods An affecting-factors list was made, which may affect the diagnostic parameters of the tongue-image analysis system. They were sub-classified into two groups: controllable and uncontrollable. Only the controllable factors, which could affect the results and easily set-up, were included into the SOP draft. Affecting factors control experiment was performed to investigate the effects of controllable factors, whose influence on diagnostic parameters of the tongue-image analysis system is ambiguous: rehearsal for tongue extrusion; alignment of camera axis; and presentation of a guideline. Three subjects volunteered for this experiment. Each of three variables was implemented twice in a random order by two operators on the subjects. Finally, 96 tongue images obtained in the aggregate. The diagnostic parameter set as a primary outcome in this experiment was the percentage of tongue coating. Results All of the control variables were not significant in both operators; however, the presentation of a guideline was relatively more affect than two other variables. Interaction effects among the variables were also insignificant. Therefore, the presentation of a guideline was included in the final SOP and the other variables were not included. Conclusions We suggested the SOP which could be used for both experimenter and subject. Moreover, Each of the SOPs applied to various types of tongue-image analysis system should be developed in order to improve the reliability.

• 한방안이비인후피부과학회지
• /
• 제20권3호
• /
• pp.118-126
• /
• 2007

Tongue diagnosis is a profound and special part of the whole Oriental Medicine. We examined the method, the principle and the meaning of tongue diagnosis according to a literature cited, considered a meaning of tongue diagnosis. As a result, we come to a conclusion like that. 1. Tongue is related with internal organs by meridian system, especially has a direct connection with heart and spleen. 2. The heart, a master of internal organs, has its specific opening in the tongue. The spleen, source of nutrients for growth and development, has its specific body opening in the mouth. So tongue reflects states of internal organs, Qi, blood, the constructive energy and the defensive energy. 3. When doing tongue diagnosis, we must pay attention to the position and the order of inspection of the tongue. We must diagnose by referring to a ray of light, diet, season, age, physical constitution, habit and taste, can make a accurate diagnosis. 4. We can classify constitutions, distinguish syndromes, suppose prognosis, make a prescription by using tongue diagnosis. 5. Reddened tip of the tongue represents flaring-up of the heart fire, and it means psychologic stress. Dental identations on the tongue edges represents deficiency of Qi of the spleen, and it means physiologic fatigue. 6. Through observing humidity of fur of the tongue, we can guess psychologic stress and physiologic fatigue. Through observing thickness of fur of the tongue, we can guess function of spleen and stomach.

• 대한한의학회지
• /
• 제27권2호
• /
• pp.134-144
• /
• 2006

Tongue diagnosis is an important diagnostic method in traditional Oriental medicine. It has been especially accepted that quantitative analysis of tongue images allows the accurate diagnosis of the exterior-interior and cold-heat patterns of a patient. However, to ensure stable and reliable results, the color reproduction of such images must first be error-tree. Moreover, tongue diagnosis is much influenced by the surrounding illumination and subjective color recognition, so it has to be performed objectively and quantitatively using a digital diagnostic machine. In this study, 457 tongue images of outpatients were collected using the Digital Tongue Inspection System. Through statistical analysis, the result shows that the heat and cold patterns can be distinguished clearly based on the hue value of the tongue images. The average hue value (1.00) of the tongue's image in the cold pattern is higher than that in the heat pattern (0.99).

• 대한한의진단학회지
• /
• 제19권1호
• /
• pp.1-10
• /
• 2015

Objectives The purpose of this study was to survey the status of clinical use of a computerized tongue diagnosis system (CTDS) Methods We searched domestic/international articles using the CTDS from online medical databases including OASIS, NDSL and pubmed. We selected articles on clinical application or reliability of CTDS but excluded articles on mechanical design or software programming for developing a new CTDS. Finally we found 15 articles and classified the articles according to the study purpose. Results Out of the 15 articles, 8 were focused on the clinical application including halitosis, cold/heat syndrome, lung cancer, xerostomia etc. Other 5 articles were aimed at evaluating and improving reliability of CTDS. The other 2 articles were studied for development of differential diagnostic criteria on tongue coating thickness. Conclusion We found out that until now the researches on clinical application of CTDS mainly had been performed for producing a variety of CTDSs. Considering the importance of the tongue color in the traditional Korean medicine, we suggest that at first standard operating procedure for CTDS be developed and researches to develop differential diagnostic criteria on tongue body/coating color be performed and then explore its applications.

• 한국정보통신학회논문지
• /
• 제20권4호
• /
• pp.826-832
• /
• 2016

본 논문에서는 고가의 디지털 설진 장비와 특별한 장치 없이 누구나 손쉽게 사용할 수 있는 디지털 설진 시스템의 첫 단계로 미각 영역별 균열 유무를 판별하는 시스템을 제안한다. 훈련 DB는 한방 병원에서 수집한 사진 261장을 바탕으로 Haar-like feature, Adaboost 학습을 하였다. 학습된 결과를 통하여 입력영상으로부터 혀 후보영역을 검출하고, 검출된 혀 후보영역으로부터 혀 영역만을 분리하기 위하여 261장의 훈련 DB의 HSV 컬러모델의 Hue 성분 평균 값을 산출하였다. 검출된 혀 윤곽으로부터 Connected Component Labeling을 통하여 혀 영역을 분리 하였다. 분리된 혀 영역의 상대적 너비와 높이를 이용하여 미각 영역별 로 분할하였다. 분할된 미각 영역별 영상은 Gray영상으로 변환하고, 각각의 영역별 평균 밝기를 산출하여 이진화하였다. 이진화 영상에 Connected Component Labeling을 통하여 균열 유무를 판별하였다.

• 대한한의진단학회지
• /
• 제15권2호
• /
• pp.149-158
• /
• 2011

Objectives: The objective of this study is to compare the colour intensity of tongue body and that of tongue coat under the visible light and the ultraviolet light. Methods: We selected 7 subjects with completely or partially peeled tongue coat among the recruited 94 adults for the experiment. We took each tongue picture under the visible light and the ultraviolet light (315-400 nm) and then extracted sample images from the tongue body and tongue coat regions. Mean, median and mode of colour intensity from the sample images were calculated in 256 RGB system. Results: The green and the blue colour intensities of the tongue coats were significantly higher than those of the tongue bodies under the visible light. In all channels, the red, green and blue, the colour intensities of the tongue coats were significantly higher than those of the tongue bodies under the ultraviolet light. The colour differences between tongue coats and tongue bodies under the ultraviolet light were significantly higher than the colour differences under the visible light. Especially the colour difference under the ultraviolet light was highest in the green channel. Conclusions: We suggested that green colour image of the RGB system taken under the ultraviolet light could be used for more easy separating tongue coat region from tongue body.

• 대한한의진단학회지
• /
• 제17권3호
• /
• pp.225-232
• /
• 2013

Objectives The aim of this study is to design a part in contact with the face of computerized tongue diagnosis system (CTDS), so that external light is effectively shielded even if the facial appearance and degree of protrusion differ when a patient opens or closes his/her jaws. Methods Each of the 4 researchers manually produced clay models of the part in contact with the face of CTDS. Shielding and contact feeling of the clay models were evaluated by 20 assessors. Based on the evaluation, we selected the appropriate model and produced the final silicon model. Then we evaluated the performance of the shielding of the completed silicon model. We took tongue pictures of 60 participants with a CTDS applying the silicon model in condition with external light and without it. The color values in RGB color model and gray scale of the tongue pictures in condition with external light were compared with those without external light. Results There was no significant difference between the color values of the picture taken in condition with external light and those without external light. Conclusions We concluded that the produced part in contact with the face of CTDS can effectively block out the external light.

• 대한한의진단학회지
• /
• 제17권3호
• /
• pp.215-223
• /
• 2013

Objectives Although tongue diagnosis is one of major diagnostic methods in east Asian traditional medicine, the standard of normal tongue color have not established. So we tried to suggest the method to establish the standard of normal tongue color range and the pilot data about the normal range. Materials and methods: 22 precedent study papers that presented the numerical data of normal (light red) tongue color were analyzed. At the same time, 46 adult people tongue color data were also collected and analyzed. Results Precedent studies showed remarkable fluctuations of the range of normal tongue color. Collected tongue color data of the 46 people showed mean Hue value 2 and standard deviation 14 in HSB system. Additionally, 3 ways of standard establishment for normal tongue color were suggested. Conclusion We suggest statistical method as a reasonable method for tongue color standard establishment and $2{\pm}14$ as a reference Hue value for normal tongue color.