舌苔在西醫與中醫舌診中, 是臨床診斷和治療的一個重要客觀依據. 有鑑於智慧型手機的高普及率與它內建的一些感測器, 以及對於健康狀況持續偵測的需求, 我們在手機上提出了一個自動舌診的框架. 然而, 從手機上取得的一些舌頭圖片, 仍然可能因為是在不同的光源條件下所取得的而使得它呈現不同的顏色, 所以我們必須解決這個問題, 以偵測那些用於舌診的正確舌苔特徵.
先前有很多研究提及, 他們的舌診系統是建置在一個受限制有良好控制的環境下(例如:有個固定的光源條件), 但我們的目的是要讓使用者可以使用他們自己的智慧型手機進行舌診, 無論他們身處何處. 因此, 我們提出一個方法, 在不同的光源條件下去偵測舌頭的舌苔特徵(例如: 在日光燈, 鹵素燈及白熾燈下), 此辦法由一連串的方法所組成: 1. 光源條件的估計 2.舌頭圖片顏色修正 3. 舌苔特徵(白苔)偵測
我們先使用SVM的方法去估計光源條件, 然後根據目前的光源條件所對應的修正矩陣來進行顏色修正. 在我們取得修正後的舌頭照片後, 我們再接著使用一個白苔偵測model來偵測在此舌頭照片上的白苔區域.
在我們這篇論文當中, 我們提出了一個光源條件的估計方法, 它是根據在不同光源條件下, 從手機上取得的有使用閃光和沒有使用閃光燈的照片之間的色差來預估的; 我們也驗證了一件事, 就是必須要針對不同的光源條件, 找出相對應的修正矩陣的參數, 來進行顏色修正; 最後, 我們發現, 經由我們找到的修正矩陣的參數, 使鹵素燈和白熾燈下經修正後的舌頭圖片和標準光源下的舌頭圖片之間的舌頭顏色分布的重疊率有明顯的提升, 且如果此重疊率超過60%則白苔將可以被辨識到.

Tongue fur is an important objective basis for clinical diagnosis and treatment in western medicine and tongue diagnosis for Chinese medicine. Given the high penetration and built-in sensors of smartphones, and the need for continuous monitoring of health conditions, we propose an automatic tongue diagnosis framework on smartphone. However, tongue images taken by smartphone are quite different in color due to various lighting conditions, so we have to solve this problem to detect the correct tongue furs.
In previous work mentioned that their tongue diagnosis systems are set up in a constrained well-controlled environment (e.g. with fixed lighting condition), but we purpose to let users make tongue diagnosis with their own smartphones no matter where they are. Therefore, we provide a way to detect tongue furs under different lighting conditions (e.g. fluorescent, halogen, and incandescent illuminant) by the combination of series methods : 1. Lighting condition estimation, 2. Tongue image color correction 3. Tongue fur (white fur) detection.
We use the SVM to estimate the lighting condition and do the color correction with the corresponding correction matrix for current lighting condition. After getting the corrected tongue images, we use the detection model training by SVM to detect the white fur region in corrected tongue images.
In this thesis, we propose a lighting condition estimation method according to color difference of tongue images taken with and without flash on the smartphone under different lighting condition; we also verify that it need to search corresponding parameter of correction matrix for color correction depend on different lighting condition; finally, we observe that the overlap rate of corrected tongue images for Hal. and Inc. lighting has been clearly upgraded with our correction parameter and the white fur can be identify if the overlap rate of corrected tongue images exceed 60%.

Reference
[1] Zhang, B., Wang, X., You, J., and Zhang, D., Tongue color analysis for medical application. Evid. Based Complement. Alternat. Med. 2013, 2013.
[2] Zhu, B., Basic theories of traditional Chinese medicine. Published by Singing Dragon, 2010.
[3] Zhang, H., Wang, K., Zhang, D., Pang, B., Huang, B. Computer aided tongue diagnosis system. The 27th IEEE International Conference of Engineering in Medicine and Biology Society, 2005.
[4] Kanawong, R., Xu, W., Xu, D., Li, S., Ma, T., and Duan, Y., An automatic tongue detection and segmentation framework for computer-aided tongue image analysis. Int. J. of Functional Informatics and Personalised Medicine. 4(1):56–68, 2012.
[5] Wang, X., and Zhang, D., A high quality color imaging system for computerized tongue image analysis. Expert Systems with Applications. 40(15):5854–5866, 2013.
[6] Kanawong, R., Computer-aided tongue image diagnosis and analysis. University of Missouri at Columbia Columbia, MO, Doctoral Dissertation, 2012.
[7] Lo, L.-C., Cheng, T.-L., Chen, W.-J., Chen, Y.-F., and Chiang, J. Y. The Study on the Agreement between Automatic Tongue Diagnosis System and Traditional Chinese Medicine Practitioners. European Congress for Integrative Medicine (ECIM 2012), 2012.
[8] Qi WJ, Zhang MM, Wang H, Wen Y, Wang BE, Zhang SW. Research on the relationship between thick greasy tongue fur formation and vascular endothelial cell permeability with the protein expression of zonula occludens-1. Chin J Integr Med 2011;17:510–516.
[9] Cao MQ, Wu ZZ, Wu WK. Identification of salivary biomarkers in breast cancer patients with thick white or thick yellow tongue fur using isobaric tags for relative and absolute quantitative proteomics. J Chin Integr Med / Zhong Xi Yi Jie He Xue Bao. 2011; 9(3): 275-280.
[10] Wu Z, Li M, Zhang Y, Chen M. Study on relationship between the thickness of tongue fur and the expressions of apoptosis-related genes of the tongue epithelial cells in patients with diseases of the digestive system. J Tradit Chin Med. 2007 Jun;27(2):148-52.
[11] Li FF, Li GG, Wu YZ, Li J, Zhang XY, Wang HF, Wang YQ. Immunological mechanism of exfoliative tongue fur in children with asthma. Zhong Xi Yi Jie He Xue Bao. 2005 Nov;3(6):446-9. Chinese.
[12] X. Wang, B. Zhang, Z. Yang, H. Wang and D. Zhang, "Statistical Analysis of Tongue Images for Feature Extraction and Diagnostics," in IEEE Transactions on Image Processing, vol. 22, no. 12, pp. 5336-5347, Dec. 2013.
[13] Junwen Zhang, Guangqin Hu and Xinfeng Zhang, "Extraction of tongue feature related to TCM physique based on image processing," 2015 12th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP), Chengdu, China, 2015, pp. 251-255.
[14] Y. C. Hsu, Y. C. Chen, L. c. Lo and J. Y. Chiang, "Automatic tongue feature extraction," Computer Symposium (ICS), 2010 International, Tainan, 2010, pp. 936-941.
[15] L. Y. Bai et al., "Automatic extraction of tongue coatings from digital images: A traditional Chinese medicine diagnostic tool," in Tsinghua Science and Technology, vol. 14, no. 2, pp. 170-175, April 2009.
[16] C. W. Huang, Y. J. Chen, T. T. Yen, K. Y. Lin and D. Y. Chen, "Region-based hierarchical tongue feature extraction," 2014 International Conference on Machine Learning and Cybernetics, Lanzhou, 2014, pp. 867-870.
[17] Jiatuo Xu, Liping Tu, Zhifeng Zhang, Li Zhang and Changle Zhou, "The region partition of quality and coating for tongue image based on color image segmentation method," IT in Medicine and Education, 2008. ITME 2008. IEEE International Symposium on, Xiamen, 2008, pp. 817-821.
[18] C. C. Wei, C. H. Wang and S. W. Huang, "Using threshold method to separate the edge, coating and body of tongue in automatic tongue diagnosis," Networked Computing and Advanced Information Management (NCM), 2010 Sixth International Conference on, Seoul, 2010, pp. 653-656.
[19] Y. Wei, J. Li, Q. Chen and M. Liu, "A new pattern recognition algorithm and its application about tongue fur image classification of Traditional Chinese Medicine," 2010 3rd International Conference on Biomedical Engineering and Informatics, Yantai, 2010, pp. 37-40.
[20] W. Li, S. Hu, J. Yao and H. Song, "The separation framework of tongue coating and proper in Traditional Chinese Medicine," Information, Communications and Signal Processing, 2009. ICICS 2009. 7th International Conference on, Macau, 2009, pp. 1-4.
[21] Weitong Huang, Zhaoqian Yan, Jiatuo Xu and Li Zhang, "Analysis of the tongue fur and tongue features by naive Bayesian classifier," 2010 International Conference on Computer Application and System Modeling (ICCASM 2010), Taiyuan, 2010, pp. V4-304-V4-308.
[22] K. H. Kim, J. H. Do, H. Ryu and J. Y. Kim, "Tongue diagnosis method for extraction of effective region and classification of tongue coating," 2008 First Workshops on Image Processing Theory, Tools and Applications, Sousse, 2008, pp. 1-7.
[23] X. Li, Q. Shao and J. Wang, "Classification of tongue coating using Gabor and Tamura features on unbalanced data set," Bioinformatics and Biomedicine (BIBM), 2013 IEEE International Conference on, Shanghai, 2013, pp. 108-109.
[24] R. Kanawong, T. Obafemi-Ajayi, J. Yu, D. Xu, S. Li and Y. Duan, "ZHENG classification in Traditional Chinese Medicine based on modified specular-free tongue images," Bioinformatics and Biomedicine Workshops (BIBMW), 2012 IEEE International Conference on, Philadelphia, PA, 2012, pp. 288-294.
[25] Bo Huang, D. Zhang, Yanlai Li, Hongzhi Zhang and Naimin Li, "Tongue coating image retrieval," Advanced Computer Control (ICACC), 2011 3rd International Conference on, Harbin, 2011, pp. 292-296.
[26] J. Q. Du, Y. S. Lu, K. Zhang, M. F. Zhu and C. H. Ding, "A Novel Approach of Tongue Body and Tongue Coating Separation Based on FCM," 2008 2nd International Conference on Bioinformatics and Biomedical Engineering, Shanghai, 2008, pp. 2499-2503.
[27] B. Huang, K. Wang, X. Wu, D. Zhang and N. Li, "Quantified Vector Oriented Tongue Color Classification," 2009 2nd International Conference on Biomedical Engineering and Informatics, Tianjin, 2009, pp. 1-4.
[28] SHEN Lan-sun,WANG Ai-min,WEI Bao-guo etc. Image Analysis for Tongue Characterization[J]. Chinese Journal of Electronics, 2001, 29(S1): 1762-1765.
[29] ZHANG Xin-feng, SHEN Lan-sun, WEI Bao-guo, CAI Yi-heng. Application of the Multi-class SVM to the Classification and the Recognition of Tongue Substance and Tongue Coat. Journal of Circuits and Systems《电路与系统学报》2004年第5期 110-113
[30] 王爱民, 赵忠旭, 沈兰荪. 中医舌象自动分析中舌色、苔色分类方法的研究. 北京生物医学工程, 2000, 19(03): 136-142
[31] 李晓宇, 张新峰, 沈兰荪. 基于支撑向量机的中医舌色苔色识别算法研究. 北京生物医学工程, 2006, 25(01): 43-46
[32] 陈海燕, 卜佳俊, 龚一萍, 连奕劭. 一种基于多色彩通道动态阈值的舌苔舌质分离算法. 北京生物医学工程, 2006, 25(5): 466-469
[33] 张静, 张新峰, 王亚真, 蔡轶珩, 胡广芹. 多标记学习在中医舌象分类中的研究. 北京生物医学工程, 2016, 35(2)
[34] 赵荣莱, 许胜, 等. 舌质舌苔的计算机定量描述和分类. 中醫雜誌, 1989； 2:47-48
[35] X. Wang and D. Zhang, "An Optimized Tongue Image Color Correction Scheme," in IEEE Transactions on Information Technology in Biomedicine, vol. 14, no. 6, pp. 1355-1364, Nov. 2010.
[36] X. Wang and D. Zhang, "A New Tongue Colorchecker Design by Space Representation for Precise Correction," in IEEE Journal of Biomedical and Health Informatics, vol. 17, no. 2, pp. 381-391, March 2013.
[37] Hong-Zhi Zhang, Kuan-Quan Wang, Xue-Song Jin and David Zhang, "SVR based color calibration for tongue image," Machine Learning and Cybernetics, 2005. Proceedings of 2005 International Conference on, Guangzhou, China, 2005, pp. 5065-5070 Vol. 8.
[38] Cao Meiling, Cai Yiheng, Liu Changjiang and Shen Lansun, "Recent progress in new portable device for tongue image analysis," Neural Networks and Signal Processing, 2008 International Conference on, Nanjing, 2008, pp. 488-492.
[39] Jiatuo Xu, Liping Tu, Zhifeng Zhang and X. Qiu, "A medical image color correction method base on supervised color constancy," IT in Medicine and Education, 2008. ITME 2008. IEEE International Symposium on, Xiamen, 2008, pp. 673-678.
[40] Yang Cai, "A novel imaging system for tongue inspection," Instrumentation and Measurement Technology Conference, 2002. IMTC/2002. Proceedings of the 19th IEEE, 2002, pp. 159-163 vol.1.
[41] L. c. Lo, M. C. c. Hou, Y. l. Chen, J. Y. Chiang and C. c. Hsu, "Automatic Tongue Diagnosis System," Biomedical Engineering and Informatics, 2009. BMEI '09. 2nd International Conference on, Tianjin, 2009, pp. 1-5.
[42] Li Zhuo, Jing Zhang, Pei Dong, Yingdi Zhao, Bo Peng, An SA–GA–BP neural network-based color correction algorithm for TCM tongue images, Neurocomputing, Volume 134, 25 June 2014, Pages 111-116
[43] Ini Ryu and Itiro Siio. 2014. TongueDx: a tongue diagnosis for health care on smartphones. InProceedings of the 5th Augmented Human International Conference (AH '14). ACM, New York, NY, USA, , Article 25 , 2 pages
[44] Xu, X., Zhuo, L., Zhang, J., Shen, L. Research on color constancy under open illumination conditions. Journal of Electronics (China). 26(5):681–686, 2009.
[45] Q.H. Su, H. Cheng, W.B. Sun, F.J. Zhang, A novel correction algorithm based on polynomial and TPS models, in: Proceedings of International Conference on Information Technology, Computer Engineering and Management Sciences, 1, 2011. pp. 52–55.
[46] Kim, J., and Scott, C., Variable kernel density estimation. Ann. Stat. 20:1236–1265, 1992.
[47] C.-C. Chang and C.-J. Lin, "LIBSVM: A library for support vector machines," ACM Transactions on Intelligent Systems and Technology (TIST), vol. 2, p. 27, 2011.
[48] Min-Chun Hu, Ming-Hsun Cheng, Kun-Chan Lan, "Color Correction Parameter Estimation on the Smartphone and Its Application for Automatic Tongue Diagnosis" Journal of Medical Systems, 2015.
[49] 中医四诊仪_上海道生中医四诊仪_中医四诊http://www.gdzjkf.com/show/b6/78/1_e4_b8_ad_e5_8c_bb_e5_9b_9b_e8_af_8a_e4_bb_aa.htm
[50] Smith, Thomas; Guild, John (1931–32). "The C.I.E. colorimetric standards and their use". Transactions of the Optical Society. 33 (3): 73–134.
[51] https://en.wikipedia.org/wiki/List_of_color_spaces_and_their_uses
[52] https://commons.wikimedia.org/wiki/File:CIE1931xy_CIERGB.svg