Abstract
Copy-move is one of the most common image tampering method. Many schemes have been proposed to detect and locate the forged regions. However, many existing schemes fail when the copied region is rotated or ipped before being pasted. To solve the problem, this paper presents a new method for detecting the copy-move forgery. The image is first filtered and divided into overlapping circular blocks. Then the features of the circular blocks are extracted using rotation invariant uniform local binary patterns (LBP). The feature vectors are then compared and the forged regions can be located by tracking the corresponding blocks. Experimental results demonstrate that this method is robust not only to JPEG compression, noise contamination and blurring, but also to region rotation and ipping.
Original language | English |
---|---|
Pages (from-to) | 46-56 |
Number of pages | 11 |
Journal | Journal of Information Hiding and Multimedia Signal Processing |
Volume | 4 |
Issue number | 1 |
Publication status | Published - 2013 |
Keywords
- Copy-move forgery
- Flipping
- LBP
- Rotation