东北大学学报（自然科学版）

东北大学学报(自然科学版) ›› 2006, Vol. 27 ›› Issue (6): 610-613.DOI: -

• 论著 • 上一篇    下一篇

多类特征显微图像的识别

王亚杰;李殿起;付萍;徐心和;   

  1. 东北大学教育部暨辽宁省流程工业综合自动化重点实验室;东北大学教育部暨辽宁省流程工业综合自动化重点实验室;东北大学教育部暨辽宁省流程工业综合自动化重点实验室;东北大学教育部暨辽宁省流程工业综合自动化重点实验室 辽宁沈阳110004;辽宁沈阳110004;沈阳工业大学机械学院;辽宁沈阳110023;辽宁沈阳110004;辽宁沈阳110004
  • 收稿日期:2013-06-23 修回日期:2013-06-23 出版日期:2006-06-15 发布日期:2013-06-23
  • 通讯作者: Wang, Y.-J.
  • 作者简介:-
  • 基金资助:
    国家自然科学基金资助项目(60475036)

Multiple-feature recognition of microimages

Wang, Ya-Jie (1); Li, Dian-Qi (1); Fu, Ping (1); Xu, Xin-He (1)   

  1. (1) Key Laboratory of Process Industry Automation of Liaoning Province, Northeastern University, Shenyang 110004, China; (2) School of Mechanical Engineering, Shenyang University of Technology, Shenyang 110023, China
  • Received:2013-06-23 Revised:2013-06-23 Online:2006-06-15 Published:2013-06-23
  • Contact: Wang, Y.-J.
  • About author:-
  • Supported by:
    -

RichHTML

0

PDF (PC)

749

摘要： 针对粉末状态下的中药材显微图像明显具有纹理的特性,提出了一种基于多类型特征组合的中药材显微图像的识别方法.分别使用了三种分析方法,即分形分析方法、小波分析方法、灰度/梯度共生矩阵法,在各种方法中提取对图像分类贡献较大的特征量,并组合成特征向量,作为识别的依据.实验中采用了k-近邻分类方法,实验结果表明了该方法的可行性和有效性,为中药材的定量识别提供了理论依据.

关键词: 中药材显微图像, 小波分析, 分形分析, 多类特征, k-近邻法

Abstract: A new way to recognize the microimage of powdered Chinese medical herbs is put forward on multiple-feature basis according to their textural characteristics. It includes three analytic methods, i.e., fractal analysis, wavelet analysis and gray level-gradient joint occurrence matrix. As the foundation on which the images are efficiently recognized, the characteristic vector is formed by combining together the characteristic quantities that are picked out according to different methods as above and how important the rates they play in the classification of images. Using the k-nearest neighbour classification, the experimental results show that the way proposed is feasible and effective and provides a theoretical reference for the quantitative recognition of Chinese medical herbs.

中图分类号: