基于CFA插值特性不一致的图像真伪鉴别

doi:10.3969/j.issn.0255-8297.2019.01.004

应用科学学报 ›› 2019, Vol. 37 ›› Issue (1): 33-40.doi: 10.3969/j.issn.0255-8297.2019.01.004

基于CFA插值特性不一致的图像真伪鉴别

苏文煊, 方针

上海大学通信与信息工程学院, 上海 200444

收稿日期:2018-02-06 修回日期:2018-05-17 出版日期:2019-01-31 发布日期:2019-01-31
通信作者: 方针,副教授,图像处理、数字媒体内容安全,E-mail:zhfang@staff.shu.edu.cn E-mail:zhfang@staff.shu.edu.cn
基金资助:
国家自然科学基金（No.U1536109）资助

Identifying Image Authenticity Based on CFA Inconsistency of Interpolation Characteristics

SU Wen-xuan, FANG Zhen

School of Communication and Information Engineering, Shanghai University, Shanghai 200444, China

Received:2018-02-06 Revised:2018-05-17 Online:2019-01-31 Published:2019-01-31

摘要/Abstract

摘要：

单传感器数码相机一般通过颜色滤波阵列（color filter array，CFA）插值得到彩色图像.利用CFA插值特性检测图像篡改，根据插值图像与理想全色图像的频谱差异分块提取频谱变化和色度失真特征以反映CFA插值特性，计算重插值前后的插值特性变化作为取证特征；使用支持向量机（support vector machine，SVM）分类并根据相邻块间取证特征的不一致来鉴别图像真伪.实验结果表明：该方法可以有效辨别篡改图像，且对JPEG压缩有较好的鲁棒性.

关键词: 颜色滤波阵列插值, 频谱相关性, 篡改检测, 支持向量机

Abstract:

Single-sensor digital cameras generally acquire the missing color components by color filter array (CFA) interpolation. In this work, CFA interpolation characteristics are exploited to identify image forgery. Using the differences in frequency spectrum between interpolated images and ideal full color ones, the interpolation characteristics are described by block spectral change and chrominance artifacts features. The feature difference between test images and their re-interpolated version are computed as forensic features. Finally, support vector machine (SVM) is exploited to classify the authentic and tampered images using the block-wise inconsistency of forensic features. Experimental results verify effectiveness of the proposed method and its robustness against JPEG compression.

Key words: forgery detection, support vector machine (SVM), spectral correlation, color filter array (CFA) interpolation

中图分类号:

TP391

苏文煊, 方针. 基于CFA插值特性不一致的图像真伪鉴别[J]. 应用科学学报, 2019, 37(1): 33-40.

SU Wen-xuan, FANG Zhen. Identifying Image Authenticity Based on CFA Inconsistency of Interpolation Characteristics[J]. Journal of Applied Sciences, 2019, 37(1): 33-40.

参考文献

[1] Gallagher A C, Chen T. Image authentication by detecting traces of demosaicking[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 2008:1-8.
[2] Ferrara P, Bianchi T, de Rosa A. Image forgery localization via fine-grained analysis of CFA artifacts[J]. IEEE Transactions on Information Forensics and Security, 2012, 7(5):1566-1577.
[3] Li L, Xue J, Wang X. A robust approach to detect digital forgeries by exploring correlation patterns[J]. Pattern Analysis Applications, 2013:1-15.
[4] 张晓琳,方针,张新鹏. 利用通道间相关性的CFA图像盲取证[J]. 应用科学学报,2015, 33(1):87-94. Zhang X L, Fang Z, Zhang X P. Forgery detection via inter-channel correlation of CFA images[J]. Journal of Applied Sciences, 2015, 33(1):87-94. (in Chinese)
[5] Lian N X, Chang L, Tan Y P. Adaptive filtering for color filter array demosaicking[J]. IEEE Transactions on Image Processing, 2007, 16(10):2515-2525.
[6] Kwon J Y, Park S W, Park M K, Kang M G. Aliasing artifacts reduction with subband signal analysis for demosaicked images[J]. Digital Signal Processing, 2016, 59:115-128.
[7] Wei W, Wang S, Zhang X, Tang Z. Estimation of image rotation angle using interpolationrelated spectral signatures with application to blind detection of image forgery[J]. IEEE Transactions on Information Forensics and Security, 2010, 5(3):507-517.
[8] Condat L. Laurent condat's image database (preliminary version)[OL].[2009-06-01] http://www.greyc.ensicaen.fr/~lcondat/imagebase.html
[9] Technische Universität Dresden, Dresden, Germany. Dresden image database[OL].[2015-05-01]. http://forensics.inf.tu-dresden.de/ddimgdb
[10] Schaefer G, Stich M, Ucid S M. An uncompressed color image database[C]//Proceeding of SPIE in Storage and Retrieval Methods and Applications for Multimedia 2004, San Jose, USA:472-480.
[11] Gunturk B K, Altunbasak Y R, Mersereau M. Color plane interpolation using alternating projections[J]. IEEE Transactions on Image Processing, 2002, 11(9):997-1013.
[12] Hamilton J F, Adams J E. Adaptive color plane interpolation in single sensor color electronic camera:U.S. Patent, 5629734[P]. 1997.
[13] Zhang L, Wu X. Color demosaicking via directional linear minimum mean square-error estimation[J]. IEEE Transactions on Image Processing, 2005, 14(12):2167-2178.

[1]	迟楠, 牛文清, 贾俊连, 哈依那尔. 基于抗非线性SVM的几何整形可见光通信系统[J]. 应用科学学报, 2020, 38(4): 647-658.
[2]	赵琰, 周晓炜, 沈麒. 基于对立色与显著区域的紧凑图像哈希算法[J]. 应用科学学报, 2019, 37(5): 691-703.
[3]	范书瑞, 贾雅亭, 刘晶花. 基于三轴加速度传感器人体姿态识别的特征选择[J]. 应用科学学报, 2019, 37(3): 427-436.
[4]	王金伟, 徐春晖. 基于QPCA的彩色图像复制粘贴检测[J]. 应用科学学报, 2019, 37(2): 291-300.
[5]	许忠雄, 邵瑰玮, 谢予星, 吴亮, 季铮. 基于编码标志的无人机电力巡检自主定位方法[J]. 应用科学学报, 2018, 36(5): 845-858.
[6]	冯发杰, 吏军平, 丁亚洲, 朱坤, 崔卫红. 基于多尺度视觉特征组合的高分遥感影像目标检测[J]. 应用科学学报, 2018, 36(3): 471-484.
[7]	李纪成, 胡永健, Al-Alas Mohammed, 熊艺纯, 文东霞, 任圆圆, 廖广军. 视频篡改检测数据库的扩充及其有效性验证[J]. 应用科学学报, 2018, 36(2): 347-361.
[8]	杨晋生, 林振军. 一种改进支持向量机的无线定位方法[J]. 应用科学学报, 2017, 35(6): 685-692.
[9]	翟旭平, 孟田, 王涛. 采用对数预处理的SVM频谱感知方法[J]. 应用科学学报, 2017, 35(6): 726-734.
[10]	张伟伟, 杨正洪, 韩洪立, 王珺斌, 牛少彰. 特征增强的平滑区域篡改检测算法[J]. 应用科学学报, 2017, 35(5): 537-544.
[11]	熊邦书, 吴强镪, 李新民, 莫燕, 黄建萍. 基于频段能量特征的低速滚动轴承故障诊断[J]. 应用科学学报, 2017, 35(3): 366-372.
[12]	熊邦书, 刘雨, 莫燕, 黄建萍, 李新民. 基于SVM的直升机飞行状态识别[J]. 应用科学学报, 2016, 34(4): 469-474.
[13]	陈竺益, 方针. 基于色像差特性的图像篡改检测[J]. 应用科学学报, 2015, 33(6): 604-614.
[14]	季平, 秦川. 基于多码本矢量量化的图像篡改恢复[J]. 应用科学学报, 2015, 33(6): 615-627.
[15]	胡昭华, 徐玉伟, 赵孝磊, 何军, 周游. 基于支持向量机的多特征选择目标跟踪[J]. 应用科学学报, 2015, 33(5): 502-517.

基于CFA插值特性不一致的图像真伪鉴别

Identifying Image Authenticity Based on CFA Inconsistency of Interpolation Characteristics

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

本文评价