监督FCM聚类算法及其在中医舌像自动分类中的应用  

SUPERVISED FCM CLUSTERING ALGORITHM AND ITS APPLICATION TO AUTOMATIC CLASSIFICATION FOR CHINESE MEDICAL TONGUE IMAGES

作　　者：王爱民[1] 沈兰荪[1] 赵忠旭[1] 

机构地区：[1]北京工业大学信号与信息处理研究室,北京100022

出　　处：《模式识别与人工智能》1999年第4期480-485,共6页Pattern Recognition and Artificial Intelligence

基　　金：国家自然科学基金

摘　　要：本文提出一种监督FCM聚类算法,并设计了多层去模糊处理,用于对彩色中医舌图像进行自动分类。文中给出了算法的具体实现过程,比较了不同色度空间中的分类结果。实验表明,这种方法进行舌像自动分类与中医专家的分类是较为一致的。In this paper, a supervised FCM clustering algorithm is proposed. A combination of this algorithm and multistage defuzzification processing is used for automatic classification for traditional Chinese medical tongue images. The principle and implementation of this method are described. Color space is chosen in order to generate best, classification results. Experimental results show that this automatic classification is in accordance with that of traditional Chinese clinicians.

关 键 词：FCM 模糊分类 舌诊 舌像 自动分类 中医 

分 类 号：R241.25[医药卫生—中医诊断学] TP391.4[医药卫生—中医临床基础]