说明：  针对医学图像数据库,提出一种新的基于纹理和形状的图像检索方法。非下采样Contourlet变换具有多尺度多分辨率 分析和平移不变性的特点,用来提取纹理特征。Zernike矩作为一种基于区域的形状描述子,具有良好的旋转不变性,用来提取 形状特征. 然后综合两种特征。对CT图像数据库进行检索实验,实验结果表明,该方法具有良好的检索性能,并具有平移、尺 度、旋转不变性。
(Aiming atmedical image database, a novelmedical image retrieval algorithm based on texture and shape information is p roposed. The nonsubsamp led Contourlet transform p rovides a flexible multi2scale, multi2direction and shift2invariant image rep resentation. It is used for texture feature extraction. As a region2based shape descrip tor, Zernike moments have good rotation invariance. It is used to extract shape feature. Then, the two features are inte2 grated into image retrieval. A CT image database was retrieved using thismethod. Experimental results show that the new method has good retrieval performance and the p roperties of translation, scaling and rotation invariance. Key words: nonsubsamp led Contourlet transform Zernike moment texture extraction shape extraction)