Robust image copy detection using multi-resolution histogram

  • Authors:

  • Zhihua Xu;Hefei Ling;Fuhan Zou;Zhengding Lu;Ping Li

  • Affiliations:

  • Huazhong University of Science and Technology, Wuhan, China;Huazhong University of Science and Technology, Wuhan, China;Huazhong University of Science and Technology, Wuhan, China;Huazhong University of Science and Technology, Wuhan, China;Huazhong University of Science and Technology, Wuhan, China

  • Venue:
  • Proceedings of the international conference on Multimedia information retrieval
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper proposes a novel robust image copy detection scheme using multi-resolution histogram. In this method, the multi-resolution histogram, a global feature descriptor, is exploited to characterize an image. It shares many desirable properties with the plain color histogram including that they are both fast to compute, efficient for storage, invariant to rigid motions, and robust to noise. In addition, it encodes spatial information directly, which is essential to the discrimination of image signature for an image copy detection scheme. In order to verify the robustness of the proposed method, an intensive simulation has been performed. The experimental results demonstrate that our method is robust against both geometric distortions and signal-processing like attacks. P-R curves obtained under various attacks show that the performance of our method is better than such a few classical methods selected for comparison.