金字塔結構之複製移動竄改影像偵測

Pyramid Structure for Copy-Move Forgery Detection

陳怜穎(Ling-Ying Chen)

指導教授 ： 陳建彰

淡江大學/工學院/資訊工程學系碩士班/碩士(2015年)

https://doi.org/10.6846/TKU.2015.00116

摘要

本論文提出一個被動式偵測影像是否遭到複製移動竄改的方法，不需原本未經竄改的影像也能夠偵測出被複製移動竄改的區塊，在一被複製移動竄改的影像中，假設在此影像中被複製移動竄改的區域為大於限定的範圍，對影像進行區塊分割，計算區塊中相互之間的關係，得到被竄改區域中的部分區塊，再藉由這些部分區塊往周圍以金字塔結構進行區塊比對至偵測被竄改區域的所有部分，此方法可降低影像中區塊之間比對的時間及次數。相較其他學者所提出的偵測方法，本論文之偵測方法相較於地毯式偵測的相同條件下，能有一樣的結果但大幅減少執行時間。

關鍵字

複製移動竄改 ； 被動式偵測 ； 金字塔結構

並列摘要

This paper solves the passive copy-move detection efficiently. A copy-move attack is defined as a region of an image being replaced by a copy of other region in the same image. The proposed scheme improves the performance on the assumption of the copy-move area being larger than a predefined block size. Test image is partitioned to non-overlapping segmented block according to previous predefined block size. Each comparison block, which is overlapped extracted from a segmented block, is compared with upper-left comparison block of all segmented block. Experimental results show that the computation time can be greatly reduced with the similar performance to other conventional schemes.

並列關鍵字

copy-move forgery ； passive detection ； pyramid structure

參考文獻

[1] I. Amerini, L. Ballan, R. Caldelli, A. D. Bimbo, G. Serra, “A SIFT-based forensic method for copy-move attack detection and transformation recovery,” IEEE Transactions on Information Forensics and Security, vol. 6, pp. 1099–1110, 2011.

[2] Y. Cao, T. Gao, L. Fan, Q. Yang, “A Robust Detection Algorithm for Copy-Move Forgery in Digital Images,” Journal of Forensic Science International, vol. 214, pp.33–43, 2012.

[3] T. Chihaoui, S. Bourouis, K. Hamrouni, “Copy-move imageforgery detection based on SIFT descriptors and SVD-matching,” International Conference on Advanced Technologies for Signal and Image Processing, pp. 125–129, 2014.

[4] V. Christlein, C. Riess, J. Jordan, C. Riess and E. Angelopoulou, “An evaluation of popular copy-move forgery detection approaches,” IEEE Transaction on Information Forensics and Security, vol. 7, no. 6, pp.1841–1854 2012.

[5] H. Farid, “A Survey of image forgery detection,” IEEE Signal Processing Magazine, vol. pp. 16–25, 2009.