DOI QR코드

DOI QR Code

영역 특징 학습을 이용한 혀의 자동 영역 분리 및 한의학적 설진 시스템

Automatic segmentation of a tongue area and oriental medicine tongue diagnosis system using the learning of the area features

  • Lee, Min-taek (Department of Information and Communications Engineering School, Daejeon University) ;
  • Lee, Kyu-won (Department of Information and Communications Engineering School, Daejeon University)
  • 투고 : 2016.02.22
  • 심사 : 2016.03.25
  • 발행 : 2016.04.30

초록

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.

In this paper, we propose a tongue diagnosis system for determining the presence of specific taste crack area as a first step in the digital tongue diagnosis system that anyone can use easily without special equipment and expensive digital tongue diagnosis equipment. Training DB was developed by the Haar-like feature, Adaboost learning on the basis of 261 pictures which was collected in Oriental medicine. Tongue candidate regions were detected from the input image by the learning results and calculated the average value of the HUE component to separate only the tongue area in the detected candidate regions. A tongue area is separated through the Connected Component Labeling from the contour of tongue detected. The palate regions were divided by the relative width and height of the tongue regions separated. Image on the taste area is converted to gray image and binarized with each of the average brightness values. A crack in the presence or absence was determined via Connected Component Labeling with binary images.

키워드

참고문헌

  1. C. C. Chiu, "A novel approach based on computerized image analysis for traditional Chinese medical diagnosis of the tongue," Computer Methods and Programs in Biomedicine, vol. 61, pp. 77-89, Feb. 2000. https://doi.org/10.1016/S0169-2607(99)00031-0
  2. W. Li, C. Zhou, and Z. Zhang, "On automated tongue image segmentation in Chinese medicine," in Proc. the 5th world congress on intelligent control and automation, pp. 15-19, 2004.
  3. Y. Boykov and V. Kolmogorov, "Computing geodesics and minimal surfaces via graph cuts," in Proc. the 9th ICCV' 03, pp. 26-33, 2003.
  4. C. Rother, V. Kolmogorov, and A. Blake, "GrabCut: interactive foreground extraction using iterated graph cuts," ACM Trans. Graphics, vol. 23, no. 3, pp. 309-314, Aug. 2004. https://doi.org/10.1145/1015706.1015720
  5. V. Vezhnevets and V. Konouchine, "Grow-Cut-interactive multi-label N-D image segmentation," in Proc. GraphiCon, pp. 150-156, 2005.