中醫診斷精髓在於「辨證論治」，而辨證以望、聞、問、切四診為依據，舌診居四診之首，為中醫望診之重要項目。臨床上中醫師多依個人知識與經驗，透過眼睛觀察舌頭各部位顏色深淺、整體形態及唾液多寡等特徵而推斷病人身體主要病症，其結果易囿於知識、經驗、思維模式、診斷技巧、對顏色感知及詮釋等主觀判定影響，不同醫生對同一舌象可能做出互異判斷，重複性不佳。因此藉由科學方法輔助醫生進行診斷，循標準化判別程序，獲得可靠斷症結果，以提高中醫臨床應用價值，為一重要課題。藉由電腦判讀達到客觀化及定量化之目標，為中醫舌診電腦化研究是必然發展趨勢。
中醫師藉由觀察舌頭以進行辨證，舌面主要觀察重點為舌形、舌質和舌苔所構成之舌象。舌形病理計有中、胖、瘦及歪斜等；舌質病理中，舌色包括淡白、偏淡、淡紅、偏紅、紅、絳、黯及瘀斑、裂紋、齒痕及朱點等特徵；舌苔病理可區分為白、黃、黑、膩、厚、薄、剝或無等。觀察舌象通常由顯見之異常特徵著手，以做為辨證之依據。
自動化舌診系統審視焦點在於舌頭部位，首先須由患者嘴部擷取舌部影像。本論文經由分析舌頭、嘴唇及皮膚部位之RGB色彩分量表現，轉換為易於人眼認知之HSI色彩空間，藉由移除皮膚區域、矩形檢測、控制點偵測、平滑修正曲線及主動性輪廓以擷取舌部影像。由擷取之舌部影像做為後置處理舌面特徵之依據，如裂紋、瘀點、齒痕、朱點、舌苔及舌質等，經由RGB色彩分量變化，色調、飽和度及亮度等特性，藉由拉開對比、臨界值法及連通影像元件檢測，並量化特徵之數目、面積或長度，其結果提供中醫師作為臨床上斷症之參考。

The core of diagnosis in Chinese Medicine is “pattern identification/syndrome differentiation and treatment” with inspection, listening and smelling examination, inquiry, and palpation as the bases. Tongue diagnosis tops the four diagnoses and hence is crucial to the inspection diagnosis in Chinese Medicine. Clinically, doctors mostly rely on their own knowledge and experience when determining major lesions of a patient by observing the coloration, overall modalities, and volume of salivary on different parts of the tongue. As a result, the diagnosis tends to be limited by knowledge, experience, train of thought, and diagnostic techniques.The subjective determination is likely to be affected by the doctor’s color sensitivity and interpretation.Different doctors may come to drastically different judgments on the same tongue presentation with little overlap. Therefore, it is important to develop scientific methods that can help doctors diagnose based on standardized differentiation procedures and render reliable diagnoses in order to enhance the clinical application value of Chinese Medicine.The computerized automatic capture of characteristics shown on the images of the surface and the back of the tongue comprises breakup of the tongue image and capture of the tongue characteristics.The original tongue images first go through HSI color space conversion, detection of the control points inside and outside the surface of the tongue, curve smoothness modification and active contour model to capture images of the tongue. After that, the tongue shape, tongue fur, tongue body, and body fluid are captured from the breakup image of the tongue.

摘要 i
目錄 v
圖目錄 vii
表目錄 x
第一章 簡介 1
1.1中醫舌診 2
1.1.1中醫辨證 2
1.1.2舌與臟腑之關係 7
1.1.3舌診特徵 7
1.2相關研究 9
1.2.1基於HSI色調偵測 9
1.2.2基於極座標轉換 13
1.2.3基於分水嶺轉換 15
1.2.4基於知識背景 17
1.3研究概述 20
第二章 理論基礎 21
2.1 RGB模型 21
2.2中醫舌診 22
2.3 Snake模型 23
2.3.1原始Snake模型 23
2.3.2 Greedy Snake模型 28
第三章 研究方法 33
3.1取像環境 33
3.2擷取流程 33
3.3色彩校正 35
3.4利用HSI移除皮膚區域 37
3.5矩形檢測 38
3.6控制點偵測 40
3.7平滑修正曲線 41
3.8主動性輪廓修正曲線 42
3.9擷取舌面 44
3.10擷取特徵 45
3.10.1移除反光 45
3.10.2舌面裂紋 46
3.10.3舌面瘀斑 48
3.10.4舌面齒痕 49
3.10.5舌面朱點 50
3.10.6舌苔與舌質分離 51
第四章 實驗結果 52
第五章 結論與未來展望 61
5.1結論 61
5.2未來展望 61
參考文獻 62

[1] 李乃民等：中國舌診大全，學苑出版社，北京，1995:1-525。
[2] 王季藜等：舌診源鑑，立得出版社，台北 1993:2-15。
[3] 洪禎徽：舌診，立得出版社，台北，1996。
[4] 黃帝內經章句索引。啟業書局，台北，1987 :7~459。
[5] 三原陳素中：最新實用溫病學。國際書局，台中，1987:17-24。
[6] 尚瑞梅：舌體大小的臨床意義與客觀化計量化研究。浙江中醫雜誌 1993；(11):518。
[7] 狄群英等：600例纖維胃鏡與舌象的對照觀察。雲南中醫雜誌 1986；1:1-2。
[8] 趙榮菜等：舌質舌苔的計算機定量描述和分類。中醫雜誌 1989；2:47。
[9] 張永賢、邱創乾：以色彩學探討中醫舌象之研究。第六十六屆國醫節中醫學術研討會 1996；三月:2。
[10] 宋汝濬APSC著：攝影學，藝術圖書公司，台北 1993:10-11，65-69。
[11] 林傑人編著：實用攝影，渤海堂文化事業有限公司，台北 1993:106-123，265-272。
[12] Rafael C. Gonzalez and Richard E. Woods, Digital Image Processing, Addison-Wesley Publishing Company, USA, 1992.
[13] William K. Pratt, Digital Image Processing, Second Edition, A Wiley-Interscience Publication, USA, 1991.
[14] Anil K. Jain, Fundamentals of Digital Image Processing, Prentice-Hall International, Inc., USA, 1989.
[15] Kenneth R. Castleman, Digital Image Processing, Prentice-Hall International, Inc., USA, 1996.
[16] George J. Klir and Tina A. Folger, Fuzzy Sets, Uncertainty, and Information, New Jersey, 1988.
[17] Shinichi Tamura, Seihaku Higuchi, and Kokichi Tanaka, “Pattern Classification Based on Fuzzy Relations,” IEEE Transactions on Systems, Man, and Cybernetics, vol. SMC-1, No. 1, pp. 61-66, Jan. 1971.
[18] L. A. Zadeh, “Fuzzy algorithms,” Inform. Contr., vol. 12, pp. 99-102, Feb. 1968.
[19] L. A. Zadeh, “Fuzzy sets and systems,” Proc. 1965 Symp. On Syst. Theory, pp. 29-39, 1965.
[20] 菅野道夫原著，楊英魁編譯：Fuzzy控制，全華科技圖書出版，台北 1993:1-66。
[21] Bart Kosko原著，林基興編譯：模糊思考，全華科技圖書出版，台北 1995:121-154。
[22] L. A. Zadeh, “Fuzzy sets,” Inform. Contr., vol. 8, pp. 338-353, June 1965.
[23] R. Bellman, R. Kalaba, and L. Zadeh, “Abstraction and pattern classification,” J. Math. Anal. Appl., vol. 13, pp. 1-7, Jan. 1966.
[24] Krzysztof J. Cios, Inho Shin and Lucy S. Goodenday, “Using Fuzzy Sets to Diagnose Coronary Artery Stenosis,” IEEE Computer, pp. 57-63, Mar. 1991.
[25] Zhao Zhong-xu, Wang Ai-min, Shen Lan-sun. “Color Tongue Image Segmentation Based on Mathematical Morphology and HSI Model,” Journal of Beijing Industry University, 25(2), pp. 67-71, 1999.
[26] Du Jian-qiang, Lu Yan-sheng, Zhu Ming-feng, Zhang Kang and Ding Cheng-hua, “A Novel Algorithm of Color Tongue Image Segmentation Based on HSI,” BMEI 2008. International Conf. on BioMedical Engineering and Informatics, pp.733-737, vol. 1, 27-30, May 2008.
[27] Soo-Chang Pei. Image sampling structure conversion by morphological filters, Signal Processing: Image Communication, pp. 13-24, 1994.
[28] Wangmeng Zuo, Kuanquan Wang, Zhang D. and Hongshi Zhang, “Combination of polar edge detection and active contour model for automated tongue segmentation,” The 3rd International Conf. on Image and Graphics, pp.270-273, 18-20 Dec. 2004.
[29] A.A. Amini, T.E. Weymouth, R.C. Jain, “Using Dynamic Programming for solving variational problems in vision,” IEEE Trans. PAMI, vol. 12, no. 9, pp. 855-867, 1990.
[30] Jia Wu, Yonghong Zhang and Jing Bai “Tongue Area Extraction in Tongue Diagnosis of Traditional Chinese Medicine,” The 27th Annual International Conf. of the Engineering in Medicine and Biology Society, pp.4955-4957, 17-18 Jan. 2006.
[31] Vincent, Luc, and Pierre Soille, “Watersheds in Digital Spaces: An Efficient Algorithm Based on Immersion Simulations,” IEEE Trans. PAMI, vol. 13, No. 6, pp. 583-598, June 1991.
[32] Shengyang Yu, Jie Yang, Yonggang Wang and Yan Zhang, “Color Active Contour Models Based Tongue Segmentation in Traditional Chinese Medicine,” The 1st International Conf. on Bioinformatics and Biomedical Engineering, pp.1065-1068, 6-8 July 2007.
[33] G. Sapiro, Dario L. Ringach. “Anisotropic diffusion on multivalued images with application to color filtering,” IEEE Trans. on Image Process. vol. 11, pp. 1582-1586, 1996.
[34] Chenyang Xu and Jerry L. Prince, “Snakes, shapes, and gradient vector flow,” IEEE Trans. on Image Processing, vol. 7, pp.359-369, March 1998.
[35] M. Kass, A. Witkin, and D. Terzopoulos, “Snakes: Active contour models,” IEEE Trans. IJCV, vol. 1, pp. 321-331, 1987.
[36] Williams, D. J. and Shah, M. “A fast algorithm for active contours,” Proc. 3rd Inter. Conf. on Computer Vision, pp. 592-595, 4-7 Dec. 1990.