基于WBCT与平滑共生矩阵的图像检索

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。

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

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.