中国组织工程研究

中国组织工程研究 ›› 2010, Vol. 14 ›› Issue (9): 1638-1641.doi: 10.3969/j.issn.1673-8225.2010.09.027

• 数字化骨科 • 上一篇    下一篇

基于灰度投影和阈值自动选取的舌像分割方法

张 灵1，秦 鉴2   

  1. 1广东工业大学计算机学院，广东省广州市     510006；
    2中山大学附属第一医院中医科，广东省广州市      510080
  • 出版日期:2010-02-26 发布日期:2010-02-26
  • 通讯作者: 秦 鉴，博士，主任医师，中山大学附属第一医院中医科，广东省广州市 510080 himybox@yeah.net
  • 作者简介:张 灵☆，，1968年生，广西壮族自治区合浦县人，汉族，2004年广东工业大学自动化学院毕业，博士，副教授，主要从事生物医学信息处理、智能控制方面的研究。 june4567@21cn.com
  • 基金资助:

    课题获得国家自然科学基金资助(30371717)。

Tongue-image segmentation based on gray projection and threshold-adaptive method

Zhang Ling1, Qin Jian2   

  1. 1Computer Faculty, Guangdong University of Technology, Guangzhou   510006, Guangdong Province, China;
    2Department of Traditional Chinese Medicine, First Affiliated Hospital, Sun Yat-Sen University, Guangzhou   510080, Guangdong Province, China
  • Online:2010-02-26 Published:2010-02-26
  • Contact: Qin Jian, Doctor, Chief physician, Department of Traditional Chinese Medicine, First Affiliated Hospital, Sun Yat-Sen University, Guangzhou 510080, Guangdong Province, China himybox@yeah.net
  • About author:Zhang Ling, Doctor, Associate professor, Computer Faculty, Guangdong University of Technology, Guangzhou 510006, Guangdong Province, China june4567@21cn.com
  • Supported by:

    the National Natural Science Foundation of China, No. 30371717*

PDF

650

被引次数

29

摘要：

背景：传统的中医舌诊是通过目视观察舌像，凭借医生的临床经验准确诊断疾病，缺乏客观的诊断方法与标准，从而影响了这种诊断方法的有效性。因此，有必要运用计算机视觉等技术，实现舌诊的定量化和客观化。舌体分割是舌象识别诊断系统的前提工作，分割的好坏直接关系着后续工作的成败。目前已经提出的舌体分割方法很多，但是得到的结果很难保证准确性，而且算法的抗干扰能力很差。
目的：旨在设计一种新的舌像分割方法，能够有效地分离出舌体部分。
方法：针对舌图像的灰度和颜色特点，提出了一种基于灰度直方图投影和阈值自动选取相结合的舌图像分割方法，首先对舌像的亮度灰度图像分别进行水平和垂直方向的灰度投影，以确定舌体所在的区域，然后采用自动选取阈值的Otsu法，对该区域进行分割。
结果与结论：舌体图像的准确分割对于舌诊的数字化实现是很重要的。281幅舌像的实验结果证明了该算法的有效性。

关键词: 灰度投影, 舌体分割, 自动阈值, 舌诊, 数字化医学

Abstract:

BACKGROUND: Traditional Chinese medicine glossoscopy observes tongue image by vision, and to diagnose diseases by physicians’ clinical experiences, which lacks of objective diagnostic methods and criteria, finally resulting in affecting the effectiveness of this diagnostic method. Therefore, it is necessary to realize quantitive and objective glossoscopy using techniques such as computer vision. Tongue body segmentation is the premise of the tongue image recognition diagnostic system. The quality of segmentation directly affects the sequent work. At present, there are many methods of tongue body segmentation, but obtained results cannot ensure the accuracy, and the anti-interference ability is poor.
OBJECTIVE: To design a new method of tongue image segmentation, and effectively isolate tongue body.
METHODS: According to tongue-images gray and color’s features, a segmentation method of combining gray projection and threshold-adaptive way is presented in this paper. By this method, the intensity image of a colorful tongue-image is firstly projected at horizontal and vertical direction to locate the tongue-body area, and then threshold-adaptive way Otsu is used to segment the located area.
RESULTS AND CONCLUSION: Tongue-body segmentation is the basis of automatic tongue-images analysis. The following 281 tongue-images segmentation experiments show the efficiency of this method

中图分类号: