Abstract | ||
---|---|---|
AbstractIn order to solve the problem of high computational complexity in block-based methods for copy-move forgery detection, we divide image into texture part and smooth part to deal with them separately. Keypoints are extracted and matched in texture regions. Instead of using all the overlapping blocks, we use nonoverlapping blocks as candidates in smooth regions. Clustering blocks with similar color into a group can be regarded as a preprocessing operation. To avoid mismatching due to misalignment, we update candidate blocks by registration before projecting them into hash space. In this way, we can reduce computational complexity and improve the accuracy of matching at the same time. Experimental results show that the proposed method achieves better performance via comparing with the state-of-the-art copy-move forgery detection algorithms and exhibits robustness against JPEG compression, rotation, and scaling. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1155/2018/1301290 | Periodicals |
Field | DocType | Volume |
Pattern recognition,Computer science,Computer network,Robustness (computer science),Preprocessor,Forgery detection,Hash function,Artificial intelligence,Jpeg compression,Cluster analysis,Scaling,Computational complexity theory | Journal | 2018 |
Issue | ISSN | Citations |
1 | 1939-0114 | 1 |
PageRank | References | Authors |
0.43 | 4 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yu Sun | 1 | 127 | 14.76 |
Rongrong Ni | 2 | 718 | 53.52 |
Yao Zhao | 3 | 1926 | 219.11 |