北京生物医学工程

基于颜色与纹理的痤疮痧象证型自动分类初探

Preliminary study of automatic classification for Sha image based on color and texture

作者：武文强张新峰孙艳玲蔡轶珩

单位：                      北京工业大学电子信息与控制工程学院(北京100124)        

关键词：痧象；颜色直方图；Tamura；纹理；走罐

分类号：

出版年·卷·期（页码）：2014·33·6（565-569）

摘要：

目的走罐是中医治疗系统中一种非药物治疗手段。痧象是走罐后在背部显现的图像，含有很多疾病的信息，患者的证型就是其中一种。本文主要完成3种痤疮痧象证型的自动分类。方法首先分析中医走罐后，背部痤疮痧象图像的特点，然后对7个穴位模块提取Tamura 纹理特征，同时针对背部整体痧象图像提取Tamura纹理特征和颜色特征，再通过支持向量机分类方法进行分类。结果提取的痧象特征可以较好地完成湿热、心火炽盛、脾气虚三种痧象证型的自动分类。结论痤疮痧象自动分类具有可行性，为中医客观诊断和验证打下初步基础。

Objective Cupping is a non-drug treatment in traditional Chinese medicine (TCM) treatment system. Sha image appears on the back after cupping and contains information of many diseases, such as the syndrome of the patient. This paper mainly completes the automatic classification of three Sha images of acne syndrome. Methods The Sha image feature of acne syndrome on the human body back after cupping treatment is analyzed，and Tamura texture feature is extracted from the module of seven acupoints, meanwhile Tamura texture features and color features are extracted from the whole picture of Sha image, and then support vector machine (SVM) is used for classification. Results We can perform the automatic classification of three kinds of blood stasis—damp-heat, exuberance of heat fire and qi deficiency through the extracted feature of Sha image. Conclusions The feasibility of automatic classification for Sha images of acne syndrome is demonstrated, which paves the way for the objective diagnosis and verification of TCM.

参考文献：

［1］刘永,娄政驰,陶海燕.浅谈中医药学发展趋向［J］.山西中医,2008,24(12):51-53. Liu Yong, Lou Zhengchi, Tao Haiyan. Talking about the development trend of traditional Chinese medicine［J］. Shanxi Journal of Traditional Chinese Medicine,2008,24(12):51-53. ［2］朱显武.唐乾利，何清湖. 中医发展现状与现代化的若干问题思考［J］.中华中医药杂志，2011,26（11）:2728-2730. Tang Qianli, He Qinghu. Some problems about the developing situation and modernization of TCM［J］. CJTCMP, 2011,26（11）:2728-2730. ［3］陈波，陈泽林，郭义,等. 罐疗之走罐研究——天人地三部走罐法［J］. 中国针灸，2010，30（9）:777-780. Chen Bo, Chen Zelin , Guo Yi , et al. Study on moving cup method［J］. Chinese Acupuncture & Moxibustion，2010，30（9）:777-780. ［4］孙艳玲. 中医痧象自动分析及其应用初步研究［D］.北京：北京工业大学，2013. Sun Yanling. Preliminary research on the automatic analysis and application of the measles of traditional Chinese medicine［D］. Beijing：Beijing University of Technology, 2013. ［5］辛民宣，史正星，崔光彬,等. 基于内容的医学图像检索中对Tamura 纹理特征的算法改进［J］.医疗卫生装备，2010，31(2):32-35. Xin Minxuan, Shi Zhengxing, Cui Guangbin, et al. Algorithm improvement of tamura texture features in content-based medical image retrieval［J］. Chinese Medical Equipment Journal，2010，31(2):32-35. ［6］赵美丽. 古代痧症的病因病机和症候表现研究［J］.中国中医基础医学杂志,2008,14（11）：859-861. Zhao Meili. Ancient measles symptoms and pathogenesis research performance［J］. Chinese Journal of Basic Medicine in Traditional Chinese Medicine ,2008,14（11）：859-861. ［7］曹玉祥. 采用刮痧预测疾病［N］. 医药养生保健报，2010-5-3（14）. ［8］吕晓琪，郭金鸽，赵宇红，等. 基于图像分割的 Tamura 纹理特征算法的研究与实现［J］.中国组织工程研究，2012,16（17）:3160-3163. Lv Xiaoqi, Guo Jinge, Zhao Yuhong, et al. Research and realization of Tamura texture feature extraction method based on image segmentation［J］. Chinese Journal of Tissue Engineering Research, 2012, 16(17): 3160-3163. ［9］丁世飞，齐丙娟，谭红艳. 支持向量机理论与算法研究综述［J］. 电子科技大学学报，2011,40（1）:2-10. Ding Shifei, Qi Bingjuan, Tan Hongyan. An overview on theory and algorithm of support vector machines［J］. Journal of University of Electronic Science and Technology of China，2011,40（1）:2-10.

服务与反馈：

【文章下载】【加入收藏】

提示：您还未登录，请登录！点此登录