基于双光源的舌质舌苔分离方法研究  

Research on Separation Method of Tongue Body and Coating Based on Double Light Sources

作　　者：王学民[1,2] 吕元婷 王瑞云[1] 陆小佐[3] 周鹏[1,2] Wang Xuemin Lti Yuanting Wang Ruiyun Lu Xiaozuo Zhou Peng(School of Precision Instruments and Opto-Electronics Engineering, Tianjin University, Tianjin 300072, China Tianjin Key Laboratory of Biomedical Detecting Techniques and Instruments, Tianjin 300072, China College of Traditional Chinese Medicine, Tianjin University of Traditional Chinese Medicine, Tianjin 300193, China)

机构地区：[1]天津大学精密仪器与光电子工程学院,天津300072 [2]天津市生物医学检测技术与仪器重点实验室,天津300072 [3]天津中医药大学中医工程学院,天津300193

出　　处：《纳米技术与精密工程》2016年第6期434-439,共6页Nanotechnology and Precision Engineering

基　　金：国家"十二五"支撑计划资助项目(2012BAI25B05)

摘　　要：中医舌诊客观化研究中,舌质舌苔分离是后续实现舌象自动诊断的关键,然而舌质舌苔复杂多样,现有的分离方法多基于颜色差异,适应性不高,尤其是在苔薄厚交错、黄白苔交错等情况下分离效果不理想.针对上述问题,本文设计开发了一种基于双光源的舌质舌苔分离系统,研究了白、绿光源对舌质舌苔分离效果的影响,针对纯绿色光源和标准白色光源下舌图像的色彩特点,分别采用自动和人机交互的初始轮廓提取方法进行Snakes算法分割、互信息理论配准以及聚类法分类,从而实现最终的舌质舌苔分离,结果表明纯绿光图像分离效果明显更好,为中医舌诊处理方法提供了新思路.Separation of tongue body and coating is the key to realizing automatic diagnosis in tongue in- spection. However, tongue body and coating are complex, and most existing separation methods, which are based on difference in color, cannot applicable in various situations. For example, staggered thick and thin coating or yellow and white coating cannot be well separated with these methods. Regarding this problem, this paper designs and deveXops a system to separate tongue body and coating based on double light sources. The influence of white light and pure green light on the separation of tongue body and coat- ing is investigated. Considering the color features of tongue images under white light or pure green light, the tongue images are segmented by Snakes algorithm with different initial contour extraction methods, in- cluding automatic algorithm and artificial interaction algorithm. Mutual information theory for image regis- tration and clustering method for classification are adopted to separate tongue body and coating. Results show that the separation result of pure green light image is preferable to that of the white light image, pro- viding new reference for tongue inspection method in traditional Chinese medicine.

关 键 词：纯绿光LED 舌质舌苔分离 图像分割 图像配准 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] R241.2[自动化与计算机技术—计算机科学与技术]