多通道多模式融合LBP特征的纹理相似度计算  

Texture similarity calculation with LBP features fused by multi-channel and multi-mode

作　　者：刘涛[1] 周先春[2] 严锡君[3] Liu Tao;Zhou Xianchun;Yan Xijun(School of Information ＆ Mechanical ＆ Electrical Engineering,Jiangsu Open University,Nanjing 210017,China;School of Electronic ＆ Information Engineering,Nanjing University of Information Science ＆ Technology,Nanjing 210044,China;College of Computer ＆ Information,Hohai University,Nanjing 210098,China)

机构地区：[1]江苏开放大学信息与机电工程学院,南京210017 [2]南京信息工程大学电子与信息工程学院,南京210044 [3]河海大学计算机与信息学院,南京210098

出　　处：《计算机应用研究》2018年第12期3803-3806,共4页Application Research of Computers

基　　金：国家自然科学基金资助项目(11202106;61201444);江苏省高校自然科学研究面上基金资助项目(15KJD520003)

摘　　要：针对现有纹理特征对彩色图像鉴别能力不强的问题,提出了一种改进LBP特征的纹理相似度计算方法。该方法提出了极值模式、求和模式和编码模式三种特征融合模式,对彩色图像的H、S和V三个通道上获取的LBP特征进行融合,得到彩色图像的纹理描述特征。融合操作在邻域像素点LBP计算、中心像素点LBP计算、直方图特征提取三个阶段进行,提高特征鉴别能力。在Vis Tex纹理数据库上进行纹理相似度计算实验,结果表明该方法的错误接受率、错误拒绝率和等错误率明显低于其他方法。For solving the problem that the existing texture features are not strong for color image discrimination,this paper proposed a texture similarity calculation method with improved local binary pattern features. This method proposed three modes for feature fusion,including extreme mode,addition mode and encoding mode. It fused the LBP features acquired on the three channels of H,S and V of color image by these modes to obtain the texture description of color image. It carried out the fusion operation in three stages including LBP calculation of neighborhood pixels,LBP calculation of central pixels,and histogram feature extraction,to improve the ability of feature discrimination. The results of texture similarity experiments on VisTex texture database show that,the false acceptance rate,flase rejection rate and equal error rate of this method are obviously lower than other of methods.

关 键 词：纹理相似度 局部二元模式 多通道 相似度测度 特征融合 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]