An Efficient Copy-Move Detection Algorithm Based on Superpixel Segmentation and Harris Key-Points
Region duplication is a commonly used operation in digital image processing. Since region duplication could be utilized to easily tamper the raw content by intentional attackers, it has become a very important topic in image forensics. Most of the existing detection methods designed to region duplication are based on the exhaustive block-matching of image pixels or transformed coefficients. They may be not efficient when the duplicate regions are relatively smooth, or processed by some geometrical transformations. This has motivated us to propose a reliable copy-move forgery detection algorithm based on super-pixel segmentation and Harris key-points to improve the detection accuracy due to these specified attacks. For a given image, the proposed method first uses SLIC super-pixel segmentation and cluster analysis technique to partition the image content into complex regions and smooth regions. Then, a region description method based on sector mean is introduced to represent the relatively small image regions around each Harris point by adopting a well-designed feature vector. Thereafter, for both complex regions and smooth regions, we perform the feature matching operation, which is finally exploited to locate the tampered region. Experimental results have shown that, our algorithm significantly outperform some related works in terms of the detection accuracy when the test images are processed by blurring, adding noise, JPEG compression and rotating, which has shown the superior of our work.
KeywordsCopy-move forgery detection Image segmentation Cluster analysis Harris points Sector mean
This work is supported by the National Natural Science Foundation of China (NSFC) under the grant No. U1536110.
- 2.Fridrich, J., Soukal, D., Lukas, J.: Detection of copy-move forgery in digital images. In: Proceeding on Digital Forensic Research Workshop, August 2003Google Scholar
- 3.Popescu, A.C., Farid, H.: Exposing digital forgeries by detecting duplicated image regions in computer science. Dartmouth College, Technical Report TR2004-515 (2004)Google Scholar
- 4.Li, G., Wu, Q., Tu, D., Sun, S.J.: A sorted neighborhood approach for detecting duplicated regions in image forgeries based on DWT and SVD. In: Proceeding of IEEE International Conference on Multimedia Expo (ICME), Beijing, 1750–1753, July 2007Google Scholar
- 5.Bayram, S., Sencar, H.T., Memon, N.: An efficient and robust method for detecting copy-move forgery. In: IEEE International Conference on Acoustics, Speech and Signal Processing, 1053–1056. IEEE (2015)Google Scholar
- 7.Luo, W., Huang, J., Qiu, G.: Robust detection of region-duplication forgery in digital image. Chin. J. Comput. 4(11), 746–749 (2007)Google Scholar
- 8.Khan, E.S., Kulkarni, E.A.: An efficient method for detection of copy-move forgery using discrete wavelet transform. Int. J. Comput. Sci. Eng. 2(5), 1801–1806 (2010)Google Scholar
- 11.Huang, H., Guo, W., Zhang, Y.: Detection of copy-move forgery in digital images using sift algorithm. In: The Workshop on Computational Intelligence & Industrial Application, pp. 272–276. IEEE (2008)Google Scholar
- 19.Zheng, Y., Jeon, B., Xu, D., Wu, J.Q.M., Zhang, H.: Image segmentation by generalized hierarchical fuzzy C-means algorithm. J. Intell. Fuzzy Syst. 28(2), pp. 961–973 (2015). DOI: 10.3233/IFS-141378,2015
- 20.Harris, C.; Stephens, M.: A combined corner and edge detector. In: Proceedings of the Alvey Vision Conference, Manchester, UK, 2 September 1988Google Scholar
- 21.Yan-Ming, M., Mei-Hui, L., Yun-Qiong, W., Qiao-Sheng, F.: An improved corner detection method based on Harris. Comput. Technol. Develop. 19(5), 130–133 (2009)Google Scholar
- 24.Zandi, M., Mahmoudi-Aznaveh, A., Mansouri, A.: Adaptive matching for copy-move forgery detection. In: IEEE International Workshop on Information Forensics and Security (WIFS), 119–124 (2014)Google Scholar