Image copy-move forgery detection using SURF in opponent color space

Abstract

Most existing methods for image copy-move forgery detection(CMFD)operate on grayscale images. Although the keypoint-based methods have the advantages of strong robustness and low computational cost, they cannot identify the flat duplicated regions without reliable extracted features. In this paper, we propose a new CMFD method by using speeded-up robust feature(SURF)in the opponent color space. Our method starts by converting the inspected image from RGB to the opponent color space. The color gradient per pixel is calculated and taken as the work space for SURF to extract the keypoints. The matched keypoints are clustered and their geometric transformations are estimated. Finally, the false matches are removed. Experimental results show that the proposed technique can effectively expose the duplicated regions with various transformations, even when the duplication regions are flat.

Keywords

copy-move forgery / flat region / color descriptor / OwSURF

References

[1] Birajdar G K, Mankar V H. Digital image forgery detection using passive techniques: A survey[J]. Digital Investigation, 2013, 10(3): 226-245.

[2] Fridrich J, Goljan M, Soukal D, et al. Forensic steganalysis: Determining the stego key in spatial domain steganography[C]. SPIE Proceedings 5681. Security Steganography & Watermarking of Multimedia Contents VII, 2005, USA: San Jose.

[3] Wang X, Zhang Jiming. A novel image authentication and recovery algorithm based on chaos and Hamming code[J]. Acta Physica Sinica, 2014, 63(2): 020701.

[4] Wang X, Zhang Jiming. A novel image authentication and recovery algorithm based on dither and chaos[J]. Acta Physica Sinica, 2014, 63(21): 210701.

[5] Wang X, Zhang D, Guo Xing. Authentication and recovery of images using standard deviation[J]. Journal of Electronic Imaging, 2013, 22(3): 033012

[6] Fridrich J, Soukal D, Lukas J. Detection of copy-move forgery in digital images[C]. In: Proceedings of Digital Forensic Research Workshop. USA, 2003.

[7] Popescu A C, Farid H. Exposing Digital Forgeries by Detecting Duplicated Image Regions[R], 2004, USA: Department of Computer Science, Dartmouth College.

[8] Ryu S J, Lee M J, Lee H K. Detection of copy-rotate-move forgery using Zernike moments[C]. In: Proceedings of Information Hiding Conference. Canada, 2010.

[9] Lowe D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2): 91-110.

[10] Huang H, Guo W, Zhang Y. Detection of copy-move forgery in digital images using SIFT algorithm[C]. Proceedings of the 2008 IEEE Pacific-Asia Workshop on Computational Intelligence and Industrial Application, 2008, China: Wuhan.

[11] Pan X, Lyu S. Region duplication detection using image feature matching[J]. IEEE Transactions on Information Forensics and Security, 2010, 5(4): 857-867.

[12] Amerini I, Ballan L, Caldelli R, et al. A SIFT-based forensic method for copy-move attack detection and transformation recovery[J]. IEEE Transactions on Information Forensics and Security, 2011, 6(3): 1099-1110.

[13] Herbert B, Andreas E, Tinne T, et al. Speededup robust features(SURF)[J]. Computer Vision and Image Understanding, 2008, 110(3): 346-359.

[14] Bo X, Wang J, Liu G, et al. Image copy-move forgery detection based on SURF[J]. 2010 International Conference on Multimedia Information Networking and Security, 2010, China: Nanjing.

[15] Shivakumar B L, Baboo S S. Detection of region duplication forgery in digital images using SURF[J]. International Journal of Computer Science Issues, 2011, 8(4): 199-205.

[16] Gong J, Guo Jichang. Image copy-move forgeries detection using CSURF[J]. Journal of Tianjin University (Science and Technology), 2014, 47(9): 759-764.

[17] van de Weijer J, Gevers T. Boosting saliency in color image features[C]. IEEE Conference on Computer Vision and Pattern Recognition, 2005, USA: San Diego.

[18] van de Sande K E A, Gevers T, Snoek C G M. Evaluating color descriptors for object and scene recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(9): 1582-1596.

[19] Hastie T, Tibshirani R, Friedman J. The Elements of Statistical Learning[M], 2009, New York, USA: Springer-Verlag

[20] Fischler M A, Bolles R C. Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography [J]. Communication of ACM, 1981, 24(6): 381-395.

[21] Christlein V, Riess C, Jordan J, et al. An evaluation of popular copy-move forgery detection approaches[J]. IEEE Transactions on Information Forensics and Security, 2012, 7(6): 1841-1854.

[22] Franzen R. Kodak Lossless True Color Image Suite [EB/OL). http://r0k. us/graphics/kodak/, 2012.