基于分形和统计的复制—粘贴篡改图像的检测

doi:10.3724/SP.J.1087.2011.02236

计算机应用 ›› 2011, Vol. 31 ›› Issue (08): 2236-2239.DOI: 10.3724/SP.J.1087.2011.02236

基于分形和统计的复制—粘贴篡改图像的检测

刘美红,徐蔚鸿

长沙理工大学计算机与通信工程学院，长沙410114

收稿日期:2011-03-02 修回日期:2011-04-28 发布日期:2011-08-01 出版日期:2011-08-01
通讯作者: 刘美红
作者简介:刘美红(1986-),女,河北廊坊人，硕士研究生,主要研究方向：图像处理、智能信息处理；徐蔚鸿(1963-)，男，湖南湘潭人，教授，博士生导师，主要研究方向：人工智能、图像处理、模式识别。
基金资助:
国家教育部重点科研基金资助项目(208098);湖南省教育厅重点科研基金资助项目(07A056)

Detection of copy-move forgery image based on fractal and statistics

Mei-hong LIU,Wei-hong XU

School of Computer and Communication Engineering, Changsha University of Science and Technology, Changsha Hunan 410114, China

Received:2011-03-02 Revised:2011-04-28 Online:2011-08-01 Published:2011-08-01
Contact: Mei-hong LIU

摘要/Abstract

摘要： 现在大多数图像“复制—粘贴”篡改检测算法对于区域复制后的进一步混合处理不能进行有效检测。为此提出了一种新的基于分形和统计的检测方法。首先将图像分块并提取每块的特征向量，该特征向量由分形维数和三个统计量组成；接着对所有特征向量进行字典排序；最后,利用图像块的位置信息和欧氏距离定位篡改区域。此方法不仅能够检测传统的复制—粘贴型篡改，而且还能够检测经过旋转、翻转以及旋转和翻转混合的多区域复制—粘贴型篡改；此方法也能够抵抗高斯模糊、对比度调整和亮度调整等攻击。实验结果表明了该方法的有效性。

关键词: 图像处理, 篡改, 分形维数, 翻转, 多区域

Abstract: Most of the existing detection algorithms for image copy-move forgery cannot effectively detect the sequential mixed image forgeries with regional duplication, so a new detection method based on fractal and statistics was proposed. The presented method first divided an image into overlapping blocks, and the each block would respectively be extracted to an eigenvector, which was composed by fractal dimension and three statistical data. Then, all the eigenvectors were lexicographically sorted. Finally, the forgery part was localized by means of the location information of the blocks and the Euclidean distance. The proposed method can not only detect the traditional copy-move forgery, but also detect the multi-region forgery for images subjected to rotation, flipping, and a mixture of these processing operations. The method is also robust to tampered images undergoing some attacks like Gaussian blurring, contrast adjustment, brightness adjustment, etc. The experimental results show the validity of the method.

Key words: image processing, fractal dimension, flipping, multi-region

中图分类号:

TP391.413

刘美红徐蔚鸿. 基于分形和统计的复制—粘贴篡改图像的检测[J]. 计算机应用, 2011, 31(08): 2236-2239.

Mei-hong LIU Wei-hong XU. Detection of copy-move forgery image based on fractal and statistics[J]. Journal of Computer Applications, 2011, 31(08): 2236-2239.

参考文献

[1] 李亚琴.利用图像纹理和边缘特征的数字水印方法[J].计算机工程与应用,2010,46(22):124-125.

[2] 段保护,王键.数字签名技术的新探讨[J].计算机工程与科学，2009，31（4）：84-86.

[3] FRIDRICH J, SOUKAL D, LUKAS J. Detection of copy-move forgery in digital images [C]// Proceedings of Digital Forensic Research Workshop. Washington, DC: IEEE Computer Society, 2003: 55-61.

[4] POPESCU A C, FARID H. Exposing digital forgeries by detecting duplicated image regions, TR2004-515 [R]. Hanover, NH, USA: Dartmouth College, 2004.

[5] MAHDIAN B, SAIC S. Detection of copy-move forgery using a method based on blur moment invariants [J]. Forensic Science International, 2007, 171 (2/3): 180-189.

[6] 骆伟祺,黄继武,丘国平.鲁棒的区域复制图像篡改检测技术[J].计算机学报，2007,30(11):1998-2007.

[7] HUANG H, GUO W, ZHANG Y. Detection of copy-move forgery in digital images using SIFT algorithm [C]// IEEE Pacific-Asia Workshop on Computational Intelligence and Industrial Application. Washington, DC: IEEE Computer Society, 2008: 272-276.

[8] AMERINI I, BALLAN L, CALDELLI R, et al. Geometric tampering estimation by means of a SIFT-based forensic analysis [C]// Proceeding of IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway, NJ: IEEE Press, 2010: 1702-1705.

[9] 张志,董福安,伍友利.二维灰度图像的分形维数计算[J].计算机应用,2005,25(12):2853-2854.

[10] SARKAR N, CHAUDHURI B B. An efficient differential box-counting approach to compute fractal dimension of image [J]. IEEE Transactions on Systems, Man and Cybernetics, 1994, 24(1): 115-120.

[11] BISWAS M K, GHOSE T. Fractal dimension estimation for texture image: A parallel approach [J]. Pattern Recognition Letters, 1998, 19(3/4): 309-313.

[12] 曹伟国.旋转与缩放的纹理不变量研究[D].山东东营:中国石油大学,2007.

[13] 张伟,何金国.HU不变矩的构造与推广[J].计算机应用,2010,30(9):2449-2452.

[14] FARID H. Exposing digital forgeries in scientific images [C]// Proceeding of the 8th Workshop on Multimedia and Security. New York: ACM Press, 2006: 29-36.

[1]	张闻强, 邢征, 杨卫东. 基于多区域采样策略的混合粒子群优化求解多目标柔性作业车间调度问题[J]. 计算机应用, 2021, 41(8): 2249-2257.
[2]	谭兆一, 陈白帆. 基于坐标逆映射的增强型车辆三维全景影像[J]. 计算机应用, 2021, 41(4): 1165-1171.
[3]	高昊昱, 李雷孝, 林浩, 李杰, 邓丹, 李少旭. 区块链在数据完整性保护领域的研究与应用进展[J]. 计算机应用, 2021, 41(3): 745-755.
[4]	刘太亨, 何昭水. 基于自编码和知识蒸馏的表面缺陷检测方法[J]. 《计算机应用》唯一官方网站, 2021, 41(11): 3200-3205.
[5]	张永宏, 刘昊, 田伟, 王剑庚. 基于DeepLab v3的西藏地区降雨云团分割方法[J]. 计算机应用, 2020, 40(9): 2781-2788.
[6]	张淑萍, 吴文, 万毅. 基于多阶段生成对抗网络的单幅图像阴影去除方法[J]. 计算机应用, 2020, 40(8): 2378-2385.
[7]	袁园, 吴文, 万毅. 基于熵驱动域适应学习的单幅图像阴影检测方法[J]. 计算机应用, 2020, 40(7): 2131-2136.
[8]	徐金荣, 郭彩萍, 童恩栋. 面向服务遥感图像处理平台中时间感知的服务质量预测[J]. 计算机应用, 2020, 40(6): 1714-1721.
[9]	周思羽, 包国琦, 刘凯. 低通滤波下约束对数强度熵的图像渐晕校正[J]. 计算机应用, 2020, 40(6): 1812-1817.
[10]	付磊, 任德均, 吴华运, 郜明, 邱吕, 胡云起. 基于改进Fast-SCNN的塑瓶气泡缺陷实时分割算法[J]. 计算机应用, 2020, 40(6): 1824-1829.
[11]	徐代, 岳璋, 杨文霞, 任潇. 基于改进的三向流Faster R-CNN的篡改图像识别[J]. 计算机应用, 2020, 40(5): 1315-1321.
[12]	梁雪慧, 程云泽, 张瑞杰, 赵菲. 基于卷积神经网络的桥梁裂缝识别和测量方法[J]. 计算机应用, 2020, 40(4): 1056-1061.
[13]	廖斌, 谭道强, 吴文. 基于衰减式生成对抗网络的单幅图像阴影去除[J]. 计算机应用, 2019, 39(9): 2712-2718.
[14]	陈龙彪, 谌雨章, 王晓晨, 邹鹏, 胡学敏. 基于深度学习的水下图像超分辨率重建方法[J]. 计算机应用, 2019, 39(9): 2738-2743.
[15]	薛倩, 罗其俊, 王岳. 基于图像分析的飞机蒙皮裂纹检测[J]. 计算机应用, 2019, 39(7): 2116-2120.

基于分形和统计的复制—粘贴篡改图像的检测

Detection of copy-move forgery image based on fractal and statistics

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics