Computer Engineering and Applications ›› 2011, Vol. 47 ›› Issue (26): 177-180.
• 图形、图像、模式识别 • Previous Articles Next Articles
CHEN Xinwu1,2,LI Xiangying1,GONG Junbin2,TIAN Jinwen2
Received:
Revised:
Online:
Published:
陈新武1,2,李湘英1,龚俊斌2,田金文2
Abstract: Focusing on the low retrieval rate of contourlet texture image retrieval system,an anti-aliasing Contourlet-1.3 transform based texture image retrieval system is proposed.In the system,the Contourlet-1.3 transform is constructed by anti-aliasing critical subsampled Laplacian pyramid cascaded by critical subsampled directional filter banks,sub-bands energy and standard deviations in contourlet domain are cascaded to form feature vectors,and the similarity metric is Canberra distance.Experimental results show that anti-aliasing contourlet transform based image retrieval system is superior to those of the original contourlet transform,nun-subsampled contourlet system and Contourlet-2.3 under the same system structure with almost same length of feature vectors,retrieval time and memory needed;and anti-aliasing contourlet decomposition structure parameter can make significant effects on retrieval rates.
Key words: texture image, retrieval system, Contourlet-1.3 transform, retrieval rate
摘要: 针对轮廓波变换纹理图像检索系统检索率较低的问题,提出了一种基于较强抗混叠能力的Contourlet-1.3纹理图像检索系统。该系统采用的Contourlet-1.3变换由抗混叠临界下采样拉普拉斯金字塔级联临界下采样方向滤波器构成,特征向量采用变换域子带系数的能量和标准偏差连接而成,以Canberra距离为相似度度量标准。实验结果表明:在特征向量长度、检索时间、所需存储空间基本相同的情况下,基于抗混叠Contourlet-1.3的检索系统比相同架构的轮廓波变换、无下采样轮廓波变换以及Contourlet-2.3检索系统具有更高的检索率;该检索系统中抗混叠Contourlet变换分解结构参数的选择对于检索率也有较大影响。
关键词: 纹理图像, 检索系统, Contourlet-1.3变换, 检索率
CHEN Xinwu1,2,LI Xiangying1,GONG Junbin2,TIAN Jinwen2. Contourlet-1.3 texture image retrieval system[J]. Computer Engineering and Applications, 2011, 47(26): 177-180.
陈新武1,2,李湘英1,龚俊斌2,田金文2. Contourlet-1.3纹理图像检索系统[J]. 计算机工程与应用, 2011, 47(26): 177-180.
0 / Recommend
Add to citation manager EndNote|Ris|BibTeX
URL: http://cea.ceaj.org/EN/
http://cea.ceaj.org/EN/Y2011/V47/I26/177