基于WBCT与平滑共生矩阵的图像检索  

Texture Image Retrieval Based on WBCT and Smooth Co-Occurrence Matrix

作　　者：向丽[1] 

机构地区：[1]重庆师范大学影视传媒学院,重庆400047

出　　处：《通信技术》2009年第12期150-152,共3页Communications Technology

基　　金：国家863计划(2006AA01Z119);江苏省自然科学基金-青年科技创新人才启动项目资助(BK2007594)

摘　　要：利用WBCT变换良好的稀疏特性及其能准确地捕获图像中边缘信息的特性,分析了纹理图像WBCT系数的统计特征,提出了一种滤波算法。该算法根据纹理图像WBCT系数分布的特点,提取纹理特征。加入在低频子带上提取的灰度—平滑共生矩阵统计量,形成最终的特征向量。仿真实验结果表明,该方法在纹理图像检索上有一定的优越性。Based on WBCT＇ s characteristics of good sparsity and accurately capturing smooth contours in natural images, the statistical features for WBCT coefficient of texture image is analyzed, and a filter algorithm is proposed. According to distribution characteristics of WBCT coefficients, the texture feature is extracted. By adding the statistic properties of the gray level co-occurrence matrix extracted from the low-frequency sub-band the final characteristic vector is thus formed. The simulation experiment indicates that this method holds certain superiority in the texture image retrieval.

关 键 词：滤波算法 特征提取 图像检索 

分 类 号：TN91[电子电信—通信与信息系统]