Feature point-based copy-move forgery detection: covering the non-textured areas

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.

Image Copy Move Forgery Detection: A Review

“…Recently Harris corner detectors have also been employed for key point extraction [43][44][45]. SIFT techniques are highly robust against post processing and intermediate operations [47] however they are computationally complex and incapable to determine forgeries in area which are flat due to lack of reliable key points [46].…”

“…This technique exhibited robustness against scaling and rotation. Recently Yu et al, [45] proposed to use non maximal suppression technique to obtain evenly and roughly distributed points. This technique increased the running time than SIFT and SURF feature based techniques.…”

Copy-move forgery detection: Survey, challenges and future directions

“…(Amerini et al, 2013(Amerini et al, , 2011Anand and Hashmi, Mohammad Farukh Keskar, 2014;Ardizzone et al, 2010;Farukh et al, 2014;Huang et al, 2008;Jaberi et al, 2013aJaberi et al, , 2013bJ. Li et al, 2014;Mohamadian and Pouyan, 2013;Shen et al, 2013) Harris Corner Detector Guo et al, 2013;Kakar and Sudha, 2012;Yu et al, 2014;Zheng and Chang, 2014) SURF (Bo et al, 2010;Mishra et al, 2013) SIFT technique has been adopted in CMFD due to the high stability for both intermediate and post-processing operations (Ardizzone et al, 2010). Nevertheless, four limitations of SIFT in CMFD are identified and presented in Table 8.…”

Region Duplication Detection Based On Statistical Features of Image

“…SURF reduces the false acceptance rate considerably that too for high resolution images but lacks in detection if the copy pasted area is very small [13]. Recently Harris corner detectors have also been employed for key point extraction to improve performance of SIFT features [16][17][18]. The problem with key point based approach is that they do not give the exact shape and location of the forged region [6].…”