全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

采用指数矩的图像区域复制粘贴篡改检测

DOI: 10.11834/jig.20150908

Keywords: 图像取证,区域复制粘贴,指数矩,字典排序

Full-Text   Cite this paper   Add to My Lib

Abstract:

目的图像区域复制粘贴篡改是目前众多图像篡改技术中一种简单而且常见的方式。针对目前大多数区域复制粘贴篡改检测算法鲁棒性不强,提出一种基于指数矩的图像篡改检测算法。方法首先将图像分成重叠的图像子块,然后提取每一图像子块的指数矩作为特征向量进行字典排序,利用向量相似度和位移初步确定疑似图像子块,再根据疑似图像子块的相邻子块个数和角度方差去除误匹配块,得到最终篡改区域。结果该算法具有良好的鲁棒性,与采用圆谐-傅里叶矩的算法相比,在图像受到噪声干扰时,检测率平均提高26.66%,错误率平均降低33.77%。结论本文算法利用图像的指数矩,针对图像区域复制粘贴篡改操作,能有效检测出图像的篡改区域。检测图像在经过旋转、高斯模糊和添加噪声等后期处理时,算法依然有效。

References

[1]  Zhou L N, Wang D M. Digital Image Forensics[M]. Beijing: Beijing University of Posts and Telecomm unications Press, 2008: 1-2. [周琳娜, 王东明. 数字图像取证技术[M]. 北京:北京邮电大学出版社, 2008: 1-2.]
[2]  Bayram S, Sencar H T, Memon N. A survey of copy-move forgery detection techniques[C]//Proceedings of IEEE Western New York Image Processing Workshop. Rochester, NY, USA: IEEE,2008:1-5.
[3]  Luo W Q, Huang J W, Qiu G P. Robust detection of region-duplication forgery in digital image[J]. Chinese Journal of Computers, 2007,30(11): 1998-2007.[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.][DOI:10.3321/j.issn:0254-4164.2007.11.013]
[4]  Bayram S, Sencar H T, Memon N. An efficient and robust method for detecting copy-move forgery[C] //Proceedings of International Conference on Acoustics, Speech, and Signal Processing. Washington DC, USA: IEEE,2009: 1053-1056.[DOI:10.1109/I CASSP.2009.4959768]
[5]  Xu B, Wang J W, Liu G J, et al. Image copy-move forgery detection based on SURF[C]//Proceedings of the International Conference on Multimedia Information Networking and Security. Nanjing, China: IEEE,2010:889-892.[DOI:10.1109/MINES. 2010.189]
[6]  Hu H T, Qiao L. Radical harmonic Fourier moments[C]//Proceedings of International Conference on Intelligent Computation Technology and Automation.Washington DC, USA: IEEE, 2011: 468-?471.[DOI:10.1109/ICICTA.2011.130]
[7]  Meng M, Ping Z L. Decompose and reconstruct ima ges based on Exponential-Fourier moments[J]. Journal of Inner Mongolia Normal University: Natural Science Edition, 2011,40(3): 258-260. [孟敏, 平子良. 基于指数矩的图像分解和重建[J]. 内蒙古师范大学学报:自然科学版,2011,40(3): 258-260.][DOI:10.3969/j.issn.1001-8735.2011.03.011]
[8]  Li Y N. Image copy-move forgery detection based on polar cosine transform and approximate nearest neighbor searching[J]. Forensic Science International, 2013, 224(1): 59-67.[DOI:10. 1016/j.forsciint.201 2.10.031].
[9]  Gonzalez R C, Woods R E, Eddins S L. Digital Image Processing Using Matlab[M]. Beijing: Publishing House of Electronics Industry, 2005: 255-256. [冈萨雷斯, 伍兹, 埃丁斯. 数字图像处理: MAT- LA版[M]. 北京:电子工业出版社, 2005:255-256.]
[10]  UCID. Uncompressed Colour Image Dataset [DB/OL].[2015-01-14].http://homepages.lboro.ac.uk/cogs/datasets/ucid/ucid.html.
[11]  CASIA V2.0. CASIA V2.0 tampered image detection evaluation(TIDE) database, v2.0 (2011) [DB/OL].[2015-01-14]. http://forensics. idealtest.org.
[12]  Ping Z L,Jiang Y J. Complex exponent moments FFT algorithm and its application[C]//Proceedings of the 4th International Conference on Agents and Artificial Intelligence. Algarve, Portugal: SciTePress,2012: 465-468.[DOI:10.5220/000370090465046]
[13]  Jiang Y J. Exponent moments and its application in pattern recognition [D]. Beijing: Beijing University of Posts and Telecommunication, 2011. [姜永静. 指数矩及其在模式识别中的应用[D]. 北京:北京邮电大学, 2011.]
[14]  Ping Z L,Jiang Y J. FFT algorithm of complex exponent moments and its application in image recognition[C]//Proceedings of the 6th International Conference on Digital Image Processing. Athens, Greece: SPIE, 2011: 468-471. [DOI:10.1117/12. 2064619]
[15]  Qin J, Li F, Xiang L Y, et al. Detection of image region copy-move forgery using radial harmonic Fourier moments[J]. Journal of Image and Graphics, 2013,18(8): 919-923. [秦娟, 李峰, 向凌云, 等. 采用圆谐-傅里叶矩的图像区域复制粘贴篡改检测[J]. 中国图象图形学报,2013,18(8):919-923.] [DOI:10.11834/jig.20130805]
[16]  Wang J W, Liu G J, Li H Y, et al. Detection of image region duplication forgery using model with circle block[C]//Proceedings of International Conference on Multimedia Information Networking and Security. Hubei, China: IEEE, 2009: 25-29.[DOI:10.1109/MINES. 2009.142]

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133