融合显著区域和非下采样Contourlet变换的图像检索方法  

Image retrieval based on salient regions and nonsubsampled Contourlet transform

作　　者：张慧云[1] 张新明[1] 李双[1] 郭文鹭[1] 

机构地区：[1]河南师范大学计算机与信息技术学院,河南新乡453007

出　　处：《山东大学学报（理学版）》2011年第5期63-66,76,共5页Journal of Shandong University(Natural Science)

基　　金：河南省重点科技攻关项目(092102210017);河南省教育厅科技攻关项目(2007520024;2008B520021)

摘　　要：为了提高图像的检索性能,基于显著区域直方图和非下采样Contourlet变换技术,提出了一种图像检索新方法。首先,以兴趣点为基础实现图像显著区域和背景区域的划分,并提取这两个区域的直方图作为颜色特征;其次,对图像进行非下采样Contourlet分解,获得高频子带的均值和方差作为图像的纹理信息;最后,将得到的颜色特征和纹理信息有机结合对图像进行检索。实验结果表明,该方法性能稳定,具有较高的检索效率。To improve the quality of image retrieval,a new method for image retrieval is proposed based on the salient region′s histogram and non-sub-sampled Contourlet transform.First,the image was divided into the salient region and the background region with the salient points and compute the two region′s histogram as the color features.Second,the image was decomposed by nonsubsampled Contourlet transform to get the texture information.Finally,the images were effectively retrieved with the combination of color features and texture information.Experimental results show that the proposed method has better retrieval performance and higher efficiency.

关 键 词：图像检索 显著区域 直方图 非下采样CONTOURLET变换 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]