J4 ›› 2014, Vol. 41 ›› Issue (5): 118-123.doi: 10.3969/j.issn.1001-2400.2014.05.020

• 研究论文 • 上一篇    下一篇

结合稳定兴趣点和Gabor小波的图像检索

闫允一;姜帅;郭宝龙   

  1. (西安电子科技大学 智能控制与图像工程研究所,陕西 西安  710071)
  • 收稿日期:2013-08-09 出版日期:2014-10-20 发布日期:2014-11-27
  • 通讯作者: 闫允一
  • 作者简介:闫允一(1979-),男,博士,副教授,E-mail: yyyan@xidian.edu.cn.
  • 基金资助:

    国家自然科学基金资助项目(61305041);中央高校基本科研业务费专项资金资助项目(K5051304024)

Image retrieval using stable interest points and Gabor wavelet

YAN Yunyi;JIANG Shuai;GUO Baolong   

  1. (Research Inst. of Intelligent Control & Image Engineering, Xidian Univ., Xi'an  710071, China)
  • Received:2013-08-09 Online:2014-10-20 Published:2014-11-27
  • Contact: YAN Yunyi

摘要:

提出了一种基于稳定兴趣点和纹理特征的图像检索算法.该算法首先利用优化的Hessian检测器检测图像中的稳定兴趣点,并计算稳定兴趣点的环形邻域的伪泽尼克矩;然后,利用Gabor小波变换提取图像的纹理特征;最后,用不同图像伪泽尼克矩和纹理之间的差异来衡量图像的相似度,实现图像检索.实验结果表明,与其他基于兴趣点或者纹理特征的检索方法相比,该算法能够降低不稳定兴趣点的影响,有效提高了图像检索的准确率和查全率.

关键词: 图像检索, 兴趣点, Hessian检测器, Gabor小波变换, 纹理特征

Abstract:

A new image retrieval method based on stable interest points and texture feature is proposed. Firstly, the optimal Hessian derivative filter is used to detect the stable interest points in the image. After that, pseudo-Zernike moments defined on the neighborhood of stable interest points in the annular region are calculated. Then, the texture feature is extracted by the Gabor wavelet transform. Finally, the difference in pseudo-Zernike moment and texture feature among images is used to depict image similarity. Experimental results show that this method reduces the effects of the unstable points and improves the image retrieval accuracy effectively comparied with other retrieval methods based on interest points.

Key words: image retrieval, interest points, Hessian detector, Gabor wavelet transform, texture feature

中图分类号: 

  • TP391.4