23 April 2015 Qualified matching feature collection for feature point-based copy-move forgery detection
Author Affiliations +
J. of Electronic Imaging, 24(2), 023035 (2015). doi:10.1117/1.JEI.24.2.023035
The feature matching step plays a critical role during the copy-move forgery detection procedure. However, when several highly similar features simultaneously exist in the feature space, current feature matching methods will miss a considerable number of genuine matching feature pairs. To this end, we propose a clustering-based method to collect qualified matching features for the feature point-based methods. The proposed method can collect far more genuine matching features than existing methods do, and thus significantly improve the detection performance, especially for multiple pasting cases. Experimental results confirm the efficacy of the proposed method.
© 2015 SPIE and IS&T
Liyang Yu, Qi Han, Xiamu Niu, "Qualified matching feature collection for feature point-based copy-move forgery detection," Journal of Electronic Imaging 24(2), 023035 (23 April 2015). https://doi.org/10.1117/1.JEI.24.2.023035

Image compression

Image processing

Image quality

Computer science

Expectation maximization algorithms

Feature extraction


Back to Top