结合关键点和块优点的复制粘贴检测算法

doi:10.16180/j.cnki.issn1007-7820.2020.03.008

摘要/Abstract

摘要：

数字图像应用广泛,但随着各种编辑图像软件的使用,使得图像的真实性有待考证。大多数基于关键点检测的算法由于关键点数量有限,导致最后检测结果不完整或者表示不明确,文中提出了一种基于分割结合关键点特征的检测算法,利用SIFT提取关键点特征,再使用g2NN算法匹配关键点,用设计的聚类去除误匹配,根据改进的自适应分割算法,标记匹配的图像块,然后找出周围邻居块进行对比匹配输出结果。该算法能有效快速地检测并标记大图片的复制篡改区域,对大多数后处理鲁棒,较完整地标记出篡改区域。

关键词: 复制粘贴检测, SIFT, 分割, 关键点匹配, 聚类, 鲁棒

Abstract:

Digital images are widely used, and the use of various software for editing images has led to the authenticity of the images to be verified. Most of the algorithms based on keypoint detection have a limited number of key points, resulting in incomplete or unclear final detection results.This paper proposed a detection algorithm based on segmentation combined with keypoint features. First, SIFT was used to extract keypoint features and then used. The g2NN algorithm matched the key points, used the designed clustering to remove the mismatch, and according to the improved adaptive segmentation algorithm, marked the matched image blocks, and then finded the surrounding neighbor blocks to compare and matched the output results. The algorithm could effectively detected and marked the copy tampering area of large pictures, and was robust to most post-processing, and marked the tampering area more completely.

Key words: copy-and-paste detection, SIFT, segmentation, key point matching, clustering, robust

中图分类号:

TP391

杨珊珊,张大兴,郭家伟,王诗迢. 结合关键点和块优点的复制粘贴检测算法[J]. 电子科技, 2020, 33(3): 38-43.

YANG Shanshan,ZHANG Daxing,GUO Jiawei,WANG Shitiao. Copy-move Detection Algorithm Combining Keypoints and Block Advantages[J]. Electronic Science and Technology, 2020, 33(3): 38-43.

图/表 14

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

表1

图11

图12

表2

参考文献 16

[1]	Fridrich J, Soukal D, Lukas J. Detection of copy-move forgery in digital images[C]. Boston:Proceedings of Digital Forensic Research Workshop, 2003.
[2]	Popescu A C, Farid H . Exposing digital forgeries by detecting duplicated image regions[M]. MA:University of Dartmouth, 2004.
[3]	Yadav P, Rathore Y . Detection of copy-move forgery of images using discrete wavelet transform[J]. International Journal on Computer Science and Engineering, 2012(4):565-570.
[4]	武健, 张大兴, 刘志发 . 基于WLD特征的图像复制粘贴篡改检测算法[J]. 电子科技, 2017,30(7):47-50.
	Wu Jian, Zhang Daxing, Liu Zhifa . Image copying and pasting tampering detection algorithm based on WLD feature[J]. Electronic Science and Technology, 2017,30(7):47-50.
[5]	Huang H, Guo W, Zhang Y. Detection of copy-move forgery in digital images using SIFT algorithm[C]. Houston:The Workshop on Computational Intelligence & Industrial Application,IEEE, 2009.
[6]	Satheesh S, Anit T M, Devasia A M . Copymove forgery detection using SURF[J]. International Journal of Engineering Trends and Technology, 2017,45(6):285-287.
[7]	Yang F, Li J, Lu W , et al. Copy-move forgery detection based on hybrid features[J]. Engineering Applications of Artificial Intelligence, 2017,59(8):73-83.
[8]	Zhu Y, Shen X, Chen H . Copy-move forgery detection based on scaled ORB[J]. Multimedia Tools and Applications, 2016,75(6):3221-3233.
[9]	Prasad S, Ramkumar B. Passive copy-move forgery detection using SIFT,HOG and SURF features[C]. San Antonio:IEEE International Conference on Recent Trends in Electronics,Information& Communication Technology (RTEICT),IEEE, 2016.
[10]	AmeriniI, 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):1099-2011.
[11]	Yang B, Sun X, Guo H , et al. A copy-move forgery detection method based on CMFD-SIFT[J]. Multimedia Tools and Applications, 2017(8):837-855.
[12]	Li J, Li X, Yang B , et al. Segmentation-based image copy-move forgery detection scheme[J]. IEEE Transactions on Information Forensics & Security, 2015,10(3):507-518.
[13]	申铉京, 朱叶, 吕颖达 , 等. 基于SIFT和HSI模型的彩色图像复制-粘贴盲鉴别算法[J]. 吉林大学学报:(工学版), 2014(1):171-176.
	Shen Yijing, Zhu Ye, Lü Yingda , et al. Color image copy-paste blind identification algorithm based on SIFT and HSI model[J]. Journal of Jilin University(Engineering Edition), 2014(1):171-176.
[14]	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 & Security, 2011,6(3):1099-1110.
[15]	Achanta R, Shaji A, Smith K , et al. SLIC superpixels compared to state-of-the-art superpixel methods[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2012,34(11):2274-2282.
[16]	Pun C M, Yuan X C, Bi X L . Image forgery detection using adaptive over-segmentation and feature point matching[J]. IEEE Transactions on Information Forensics & Security, 2015,10(8):1705-1716.

	clean_walls	dark_and_bright	egyptian	red_tower
图像大小	1 024×754	2 592×3 888	3 039×2 014	3 264×2 448
运行时间	38.04 s	887.47 s	605.32 s	1117.94 s