Abstract | ||
---|---|---|
Detection of copy-move forgery has recently attracted much attention. During the past decade, two categories of methods, namely block-based and feature point-based methods, gradually developed. Compared with block-based methods, feature point-based methods exhibit remarkable performance with respect to robustness and computational cost. However, the feature point-based methods are still incomplete especially in terms of forgeries involving small smooth regions. In this paper, we solve this problem by cautiously supplementing redundant feature points and feature fusion. We propose two-stage feature detection to obtain better feature coverage and enhance the matching performance by combining the MROGH and HH descriptor. We evaluated our method on two representative datasets. We use precision, recall and F 1 score to quantitatively evaluate the performance. Experimental results confirm the efficacy of our work. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1007/s11042-014-2362-y | Multimedia Tools and Applications |
Keywords | Field | DocType |
Copy-Move Detection, MROGH Descriptor, Hue Histogram, Feature matching, Feature fusion | F1 score,Computer vision,Feature fusion,Feature detection,Pattern recognition,Feature detection (computer vision),Feature (computer vision),Computer science,Robustness (computer science),Forgery detection,Artificial intelligence,Kanade–Lucas–Tomasi feature tracker | Journal |
Volume | Issue | ISSN |
75 | 2 | 1573-7721 |
Citations | PageRank | References |
15 | 0.55 | 20 |
Authors | ||
3 |