舌体图像分割技术的实验分析与改进

山东大学学报(工学版) ›› 2010, Vol. 40 ›› Issue (5): 87-95.

舌体图像分割技术的实验分析与改进

李国正1,史淼晶1,李福凤2,王忆勤2

1. 同济大学控制科学与工程系教育部服务计算与嵌入式系统重点实验室, 上海 201804;
2. 上海中医药大学中医四诊信息化综合实验室, 上海 201203

收稿日期:2010-04-02 出版日期:2010-10-16 发布日期:2010-04-02
作者简介:李国正(1977-),男,博士,副研究员,研究方向为机器学习,中医信息学.E-mail: gzli@tongji.edu.cn
基金资助:
国家自然科学基金资助项目(60873129, 30901897);上海市青年科技启明星计划资助项目(08QA1403200)

An empirical study on tongue image detection

LI Guo-zheng1, SHI Miao-jing1, LI Fu-feng2, WANG Yi-qin2

1. Department of Control Science and Engineering, Tongji University, Shanghai 201804, China;
2. Laboratory of Traditional Medical Syndromes, Shanghai University of Traditional Chinese Medicine, Shanghai 201203, China

Received:2010-04-02 Online:2010-10-16 Published:2010-04-02

摘要/Abstract

摘要：

数字舌像图片的正确分割是中医舌诊自动化技术的关键。因为舌体特征的多样性,经典成熟的分割算法并不适用。首先对近5a来该领域已有工作,尤其是Snake算法的研究进展,分类用临床图片测评总结,讨论各类代表性算法的优缺点。最后在已有3个主流算法基础上通过改进提出了3个新算法,不同程度上提高了已有主流算法舌体分割的效果。

关键词: 舌诊, 舌体分割, Snake算法, 实验测评, 算法改进

Abstract:

The extraction of tongue area from digital image is essential to an automatic tongue diagnostic system in Traditional Chinese Medicine. Classic image segmentation methods couldn’t be effective due to its feature diversity. First, it was tried to categorize existing research in this field for recent 5 years, especially for Snake mold,practical test will be given at the same time so as to summarizing advantages and disadvantages of representative methods. Three innovated approaches are proposed afterwards, which improve the performances at certain degree.

Key words: tongue diagnoses, tongue segmentation, Snake, practical test, innovated approach

李国正1,史淼晶1,李福凤2,王忆勤2. 舌体图像分割技术的实验分析与改进[J]. 山东大学学报(工学版), 2010, 40(5): 87-95.

LI Guo-zheng1, SHI Miao-jing1, LI Fu-feng2, WANG Yi-qin2. An empirical study on tongue image detection[J]. JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE), 2010, 40(5): 87-95.

参考文献

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed