一种有效的基于小波信息分布熵的图像检索技术  

Effective Wavelet Information Distribution Entropy Techniques for Image Retrieval

作　　者：曾智勇[1] 刘侍刚[2] 

机构地区：[1]福建师范大学软件学院,福建福州350001 [2]西安交通大学电子与信息工程学院,陕西西安710049

出　　处：《小型微型计算机系统》2010年第5期974-977,共4页Journal of Chinese Computer Systems

基　　金：国家自然科学基金项目(90204012)资助;福建省自然科学基金项目(2008J04003)资助;福建省教育厅A类基金项目(JA07035)资助

摘　　要：在分析基于小波域图像索引技术的缺点后,提出一种基于小波信息分布熵的图像检索新方法.该方法首先将图像分割成若干个子图像,然后对这些子图像进行三层小波变换,并对小波变换后的各个子带图像进行处理以获取纹理图像,从而大大减少了计算的复杂性.最后以小波纹理直方图为概率密度函数,计算各个子图像的信息分布熵,不但使图像特征有紧密表示,而且也使图像检索的速度大大加快.实验结果表明,该方法对图像检索是有效的.Having analyzed the drawbacks of image index techniques based on wavelet domain,a novel image retrieval algorithm based on wavelet information distributed entropy is proposed in this paper.First,an image is segmented several sub-images by this algorithm.Second,each sub-image is decomposed three stages using wavelets,and each sub-band image by wavelet transform is processed to obtain a texture channel,so the computatinal complexity of this method is greatly reduced.Third,the wavelet information distributed entropy of each sub-image is computed using wavelet texture histogram for probability density funcion,therefore,not only is the image feature presented compactly,but also image retrieval speed is greatly quicken.Experimental results show that the proposed algorithm is effective for image retrieval.

关 键 词：图像检索 小波变换 小波直方图 小波信息分布熵 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]