一种综合颜色和纹理特征的图像检索算法  

Image retrieval algorithm using both color and texture features

作　　者：宋琳琳[1,2] 王相海[2] 

机构地区：[1]内蒙古民族大学计算机科学与技术学院,内蒙古通辽028043 [2]辽宁师范大学计算机与信息技术学院,辽宁大连116029

出　　处：《计算机工程与应用》2011年第34期203-207,共5页Computer Engineering and Applications

基　　金：辽宁省自然科学基金(No.20072156);南京邮电学院图像处理与图像通信江苏省重点实验室开放基金(No.ZK207008);内蒙古教育厅项目(No.NJ10112)~~

摘　　要：对图像颜色特征和纹理特征进行了研究。在图像颜色特征方面,利用人类的视觉特性,对图像不同分块的主色进行确认和加权处理,获得加权主色颜色特征;在纹理特征方面,利用统计法和结构法构造灰度-差分基元共生矩阵来提取纹理特征。在此基础上,通过高斯归一化方法将颜色特征和纹理特征进行综合,形成最后的图像检索特征,并给出了利用该特征的图像检索算法。实验结果表明,所提出的灰度-差分基元共生矩阵特征提取较传统的灰度共生矩阵特征更加精细,在此基础上综合利用颜色和纹理特征的图像检索方法具有更好的检索精度。This paper studies the color and texture features.In the image color features aspect,it confirms and adds weight to the dominant colors in each sub-block by making use of Human Visual System.So it can obtain the weighted dominant color features.In the texture features aspect,this paper constructs a gray-difference primitive co-occurrence matrix to extract texture features by combining statistical methods with structural ones.On this foundation,the Gaussian model is used to normalize the different sub-characters distance.Then it can gain the last image retrieval features by combining the color features with the texture features,and also gives the image retrieval algorithm by this combined features.The experimental results show that the features of the gray-difference primitive co-occurrence matrix are more delicate than the traditional gray co-occurrence matrix.On this foundation,the image retrieval algorithm using both color and texture features has better retrieval precision.

关 键 词：颜色特征 纹理特征 共生矩阵 主色 图像检索 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]