• Opto-Electronic Engineering
  • Vol. 36, Issue 12, 97 (2009)
CHEN Xin-wu1、2、* and GUO Jian-tao1
Author Affiliations
  • 1[in Chinese]
  • 2[in Chinese]
  • show less
    DOI: 10.3969/j.issn.1003-501x.2009.12.019 Cite this Article
    CHEN Xin-wu, GUO Jian-tao. Non-subsampled Contourlet Transform Texture Image Retrieval System[J]. Opto-Electronic Engineering, 2009, 36(12): 97 Copy Citation Text show less

    Abstract

    Referring to the low retrieval rate of basic contourlet transform,a Non-subsampled Contourlet Transform (NSCT) texture image retrieval system is proposed. In the system,the contourlet transform is constructed by non-subsampled Laplacian pyramid and non-subsampled directional filter banks,sub-bands energy and standard deviations are cascaded to form feature vectors,and the similarity metric is Canberra distance. Experimental results show that NSCT image retrieval system is superior to that of the original contourlet transform under the same system structure with almost the same length of feature vectors,retrieval time and memory needed. Moreover,NSCT decomposition structural parameters and image type can make significant effects on average retrieval rates.
    CHEN Xin-wu, GUO Jian-tao. Non-subsampled Contourlet Transform Texture Image Retrieval System[J]. Opto-Electronic Engineering, 2009, 36(12): 97
    Download Citation