一种主动感知的纹理图像检索方法(英文)  

An Active Perceptual Texture Image Retrieval Method

作　　者：曲怀敬[1,2] 彭玉华[1] 吴延荣[2] 万洪林[1] 韩民[1] 

机构地区：[1]山东大学信息科学与工程学院,济南250100 [2]山东建筑大学信息与电气工程学院,济南250101

出　　处：《计算机科学与探索》2009年第5期550-560,共11页Journal of Frontiers of Computer Science and Technology

基　　金：The Project-sponsored by SRF for ROCS,SEM under Grant No.2004.176.4;the Natural Science Foundation of Shandong Province of China under Grant No.2004ZRC03061~~

摘　　要：基于Contourlet变换和支持向量机提出了一种新的纹理图像检索方法。在这种方法中,能量和广义高斯分布参数被用做Contourlet子带图像的特征。通过这种表示,提出了由一类和二类支持向量机组成的两阶段检索算法来完成感知相似性测度。通过具有640个纹理图像的VisTex库和具有1760个纹理图像的Brodatz库证明了所提方法的有效性。实验结果表明,对于这两个纹理库,新的纹理图像检索方法的平均检索率分别达99.38%和98.07%。A new texture image retrieval method based on Contourlet transform and support vector machines （SVMs） is proposed. In this method, the energies and the generalized Gaussian distribution （GGD） parameters are used to represent the Contourlet subband features. Using the representations, a two-run SVM retrieval algorithm which employs an one-class SVM followed by a two-class SVM is proposed to carry out the perceptual similarity measurement. demonstrated 1 760 texture Compared with existing texture image retrieval methods, the proposed retrieval scheme is database of 99.38% and respectively to be effective on the VisTex database of 640 texture images and the Brodatz images. Experimental results have shown that the proposed retrieval scheme can attain 98.07% of the average rates respectively for the two databases.

关 键 词：CONTOURLET变换 广义高斯分布 支持向量机 相关反馈 纹理图像检索 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]