Image copy detection using a robust gabor texture descriptor

  • Authors:
  • Zhi Li;Guizhong Liu;Haixia Jiang;Xuemin Qian

  • Affiliations:
  • Xi'an Jiaotong University, Xi'an, China;Xi'an Jiaotong University, Xi'an, China;Xi'an Jiaotong University, Xi'an, China;Xi'an Jiaotong University, Xi'an, China

  • Venue:
  • LS-MMRM '09 Proceedings of the First ACM workshop on Large-scale multimedia retrieval and mining
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, we propose a novel scale and rotation invariant Gabor texture descriptor for content-based image copy detection. Firstly, the Gabor filters with different orientations and scales using a fixed-size window are constructed. Secondly, the Discrete Fourier Transform is implemented on each image. The low-frequency region of an image with the fixed size is extracted, and is filtered by the Gabor filters with the same fixed-size window. Thirdly, a statistical feature of these Gabor-filtered images is extracted as a scale invariant Gabor texture descriptor. At last, the circular shift method is employed on the scale invariant feature to achieve the rotation invariance. Experimental results demonstrate that the proposed feature is effective to resist various types of image transformations, such as scaling, rotation, flip, cut, crop, intensity, contrast, texts-inserting, blurring, noise, shift, and various combined-attacks.