首页 | 本学科首页   官方微博 | 高级检索  
     

基于颜色和纹理特征提取彩色图像的有意义区域
引用本文:于铂,郑丽敏,田立军.基于颜色和纹理特征提取彩色图像的有意义区域[J].计算机工程,2006,32(3):206-208,211.
作者姓名:于铂  郑丽敏  田立军
作者单位:中国农业大学信息与电气工程学院,北京,100094
摘    要:针对猪肉眼肌彩色图像中眼肌区域的提取,提出一种基于颜色和纹理特征的彩色图像分割方法,实现了眼肌区域的自动分割。该研究在RGB彩色空间下进行,改进以往区域生长算法中种子点的选取方法,实现了基于彩色图像的区域生长算法,并比较以灰度为特征,以颜色为特征和以颜色与纹理相结合为特征进行区域生长的分割效果。研究结果表明,基于R、G、B和纹理特征的改进区域生长算法具.有较好的分割效果。

关 键 词:图像分割  区域生长  灰度共生矩阵
文章编号:1000-3428(2006)03-0206-03
收稿时间:2005-02-01
修稿时间:2005-02-01

Image Segmentation for Meaningful Region Based on Color and Texture
YU Bo,ZHENG Limin,TIAN Lijun.Image Segmentation for Meaningful Region Based on Color and Texture[J].Computer Engineering,2006,32(3):206-208,211.
Authors:YU Bo  ZHENG Limin  TIAN Lijun
Affiliation:College of Information and Electrical Engineering, China Agricultural University, Beijing 100094
Abstract:This paper presents an improved segmentation method for color pictures based upon color and texture, to segment the lion-eye area from lion-eye colorful pictures of pigs automatically. The research is based on RGB model. The selection of the initial point in region-growing arithmetic is improved. It is applied in color pictures. And a comparison of the improved algorithms is performed, which takes gray, color and both color and texture as eigenvectors. The results show that the improved region-growing arithmetic which grounds on R, Ca B and texture has a perfect effect.
Keywords:Image segmentation  Region-growing  Gray level concurrence matrix
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号