《计算机应用研究》|Application Research of Computers

多模式共生的彩色纹理图像分类方法

Texture classification method based on co-occurrence of multi-pattern

免费全文下载 (已被下载 次)  
获取PDF全文
作者 李君伟,刘光帅,刘望华,陈晓文
机构 西南交通大学 机械工程学院,成都 610031
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2020)07-055-2185-04
DOI 10.19734/j.issn.1001-3695.2018.12.0956
摘要 针对单一方法进行纹理图像分类时易受旋转、光照等干扰的情况,提出了一种结合颜色特征和纹理特征的共生纹理分类方法。将图像转换到HSV颜色空间后,对<i>H</i>通道使用SLIOP算法以及对<i>S和V</i>通道用CLBP算法提取特征,然后将各自提取到的特征进行串联共生,最后利用支持向量机对纹理图像进行分类。基于被广泛使用的纹理图像数据库,对提出方法与其他典型分类算法进行实验对比,分析表明在分类的准确率和计算效率上获得了较大提升。实验结果表明,提出了方法具有较强的旋转不变性、光照不变性以及抗噪性。
关键词 纹理分类; 特征提取; HSV颜色空间; 共生; 简化局部像素强度模式; 完备局部二值模式
基金项目 国家自然科学基金资助项目(51275431)
四川省科技支撑计划项目(2015GZ0200)
本文URL http://www.arocmag.com/article/01-2020-07-055.html
英文标题 Texture classification method based on co-occurrence of multi-pattern
作者英文名 Li Junwei, Liu Guangshuai, Liu Wanghua, Chen Xiaowen
机构英文名 School of Mechanical Engineering,Southwest Jiaotong University,Chengdu 610031,China
英文摘要 This paper proposed a co-occurrence texture classification method to improve the rotation invariance and illumination robustness by jointing the texture features and the color features. Firstly, the method transformed the color space to HSV space. Secondly, it utilized simplified local intensity order pattern and completed local binary pattern to extract the color features in the <i>H</i> channel and the texture features in both <i>S</i> channel and <i>V</i> channel respectively. Thirdly, it concatenated these features as the descriptors of a color texture image. At last, it adopted SVM for classification. Based on experiments applying to the popular image datasets, it could be conclude that the proposed method possessed better computational efficiency and identification precision than other classical algorithms. Experiment results prove that the proposed method possesses rotation invariance and illumination robustness when it is used classification of color texture images.
英文关键词 texture classification; feature extraction; HSV color space; co-occurrence; simplified local intensity order pattern(SLIOP); completed local binary pattern(CLBP)
参考文献 查看稿件参考文献
 
收稿日期 2018/12/25
修回日期 2019/2/15
页码 2185-2188
中图分类号 TP391.41
文献标志码 A