数字图像篡改鉴定的数学特征研究
摘要
基于数字签名和基于数字水印的取证技术合称为主动取证技术,是早期数字图像取证研究的热点。随着研究的深入,后来出现了被动取证技术,该技术不需要事先对图像做任何嵌入信息处理,其取证原理就是寻找图像篡改操作引起变化的特征,并运用相关数学理论量化特征变化程度,进而对图像是否存在篡改做出判断。图像被动取证技术具有很大的挑战性,是当下图像取证的研究热点。
本文在介绍图像被动取证技术的产生历史、分析取证技术在现实生活中的意义和总结国内外研究成果的基础上,开展了图像中汉字变造篡改鉴定技术的研究工作。系统分析了基于相机标定的文字取证技术和现有文字图像取证模型,重点研究由篡改汉字图像操作引起变化的数学特征,并将该特征作为图像中汉字真实性的鉴定依据。同时,为了扩展现有取证技术的适用范围,本文对比数码相机拍摄的文字图像与编辑软件获得的文字图像之间的差异,提出了用数学理论量化差异值,引入支持向量机训练分类模型,结合分类模型实现对文字图像真实性鉴定的取证方法。本文的研究成果包括以下内容：
1、在相机标定的基础上,利用汉字具有方块、基本笔画交汇处多的特点,引入汉字模型来估计汉字图像的投影规则。由于使用的汉字模型与实际被拍摄汉字的尺寸存在比例关系,因此估计出的投影规则和真实的单应性矩阵相差一个常数倍数。这一估计方法打破了传统相机标定需要己知标定物体一定尺寸信息的局限性。引入图像汉字重构的思想,并提取汉字一定数量的笔画交汇点来代表汉字,将重构的汉字与相应的汉字模型对比,利用多个交汇点处的差异均值描述投影偏离程度。估计多幅己知真实性的汉字图像偏离值,通过拟合偏离值曲线的方法来确定实验阈值,对于偏离程度大于实验阈值的汉字判定为篡改汉字。
2、为克服现阶段文字取证技术要求文字所在面为平面,局限于整个文字篡改的检测和对于篡改文字局部的鉴定存在困难等的局限性,本文研究了数码相机拍摄图片与图像编辑软件获取的文字图片之间的差别,运用峰态、差分等数学理论量化差异程度。提出拆分文字的思想,从图像中分割出怀疑的区域,提取汉字笔画边缘点的特征。在大量己知真实性的文字图片的基础上,使用支持向量机训练分类模型,实现对文字图像的真实性鉴定。
The image forensics based on signature and technology based on watermarking are together called active forensics, which was the research focus of digital image forensics, and then the passive forensics technology emerge. Passive forensics technology don't need embedded information before forensics, but need to find changes that caused by tampering, and trying to quantify the degree of changes with math theory, and then make a judgment whether the image exists tampering. Passive image forensics technology is the focus of image forensics area now.
An introduction of the history of image forensics, a detailed analysis of forensics significance in real life and summary of research results of home and abroad are given, and our research work are based on these. With the camera calibration technique, we analyze text image forensics model and study the mathematical characteristics which changes caused by tampering, and use such characteristics as the identification to detect Chinese characters'authenticity. Study of the difference between the image obtained by camera and image editing software, we use of mathematical theory to quantify the difference in value, with support vector machine to get classification model. We achieve detecting the authenticity image identification, and expansion of existing forensic technology scope. The research results include the following:
Based on camera calibration theory, using characteristics of Chinese characters with flat, strokes interchange, we introduced Chinese characters model to estimate the projection rule of Chinese characters in digital image. Since there is size of proportional between Chinese characters model and the actual Chinese character, and is constant difference between estimated projection rules and the homography. The estimation method to break the limitations that the traditional camera calibration needs to known a certain size of calibration object. Introduced the idea of Chinese characters reconstructed, and to extract a certain number of strokes in the intersection represent Chinese characters, compare reconstructed Chinese characters with the corresponding character model, we use the differences mean of more than one intersection to describe the degree of projection deviation. Projection deviation value of multiple character images that known authenticity is estimated. With the method of depicting the projection deviation value curve to determine threshold, when the projection deviation is greater than the threshold, we judge that image was tampered.
The limitations of text image forensics technology in the actual operation are that the text surface is flat, and has difficulties to detect tampering part text. In order to break these limitations, we study the differences between digital camera photo and image obtained by editing software, we use kurtosis, differential and so on to quantify the degree of differences. Using the idea of splitting the text to solve the problem that the existing forensics technology can't detect text part tampering, suspected from the image divided stroke region, we extract characteristics of strokes of the edge point. On the basis of a large number pictures that known authenticity, we use support vector machine to training classification model, and then to achieve authenticity of text image the identification.
本文在介绍图像被动取证技术的产生历史、分析取证技术在现实生活中的意义和总结国内外研究成果的基础上,开展了图像中汉字变造篡改鉴定技术的研究工作。系统分析了基于相机标定的文字取证技术和现有文字图像取证模型,重点研究由篡改汉字图像操作引起变化的数学特征,并将该特征作为图像中汉字真实性的鉴定依据。同时,为了扩展现有取证技术的适用范围,本文对比数码相机拍摄的文字图像与编辑软件获得的文字图像之间的差异,提出了用数学理论量化差异值,引入支持向量机训练分类模型,结合分类模型实现对文字图像真实性鉴定的取证方法。本文的研究成果包括以下内容：
1、在相机标定的基础上,利用汉字具有方块、基本笔画交汇处多的特点,引入汉字模型来估计汉字图像的投影规则。由于使用的汉字模型与实际被拍摄汉字的尺寸存在比例关系,因此估计出的投影规则和真实的单应性矩阵相差一个常数倍数。这一估计方法打破了传统相机标定需要己知标定物体一定尺寸信息的局限性。引入图像汉字重构的思想,并提取汉字一定数量的笔画交汇点来代表汉字,将重构的汉字与相应的汉字模型对比,利用多个交汇点处的差异均值描述投影偏离程度。估计多幅己知真实性的汉字图像偏离值,通过拟合偏离值曲线的方法来确定实验阈值,对于偏离程度大于实验阈值的汉字判定为篡改汉字。
2、为克服现阶段文字取证技术要求文字所在面为平面,局限于整个文字篡改的检测和对于篡改文字局部的鉴定存在困难等的局限性,本文研究了数码相机拍摄图片与图像编辑软件获取的文字图片之间的差别,运用峰态、差分等数学理论量化差异程度。提出拆分文字的思想,从图像中分割出怀疑的区域,提取汉字笔画边缘点的特征。在大量己知真实性的文字图片的基础上,使用支持向量机训练分类模型,实现对文字图像的真实性鉴定。
The image forensics based on signature and technology based on watermarking are together called active forensics, which was the research focus of digital image forensics, and then the passive forensics technology emerge. Passive forensics technology don't need embedded information before forensics, but need to find changes that caused by tampering, and trying to quantify the degree of changes with math theory, and then make a judgment whether the image exists tampering. Passive image forensics technology is the focus of image forensics area now.
An introduction of the history of image forensics, a detailed analysis of forensics significance in real life and summary of research results of home and abroad are given, and our research work are based on these. With the camera calibration technique, we analyze text image forensics model and study the mathematical characteristics which changes caused by tampering, and use such characteristics as the identification to detect Chinese characters'authenticity. Study of the difference between the image obtained by camera and image editing software, we use of mathematical theory to quantify the difference in value, with support vector machine to get classification model. We achieve detecting the authenticity image identification, and expansion of existing forensic technology scope. The research results include the following:
Based on camera calibration theory, using characteristics of Chinese characters with flat, strokes interchange, we introduced Chinese characters model to estimate the projection rule of Chinese characters in digital image. Since there is size of proportional between Chinese characters model and the actual Chinese character, and is constant difference between estimated projection rules and the homography. The estimation method to break the limitations that the traditional camera calibration needs to known a certain size of calibration object. Introduced the idea of Chinese characters reconstructed, and to extract a certain number of strokes in the intersection represent Chinese characters, compare reconstructed Chinese characters with the corresponding character model, we use the differences mean of more than one intersection to describe the degree of projection deviation. Projection deviation value of multiple character images that known authenticity is estimated. With the method of depicting the projection deviation value curve to determine threshold, when the projection deviation is greater than the threshold, we judge that image was tampered.
The limitations of text image forensics technology in the actual operation are that the text surface is flat, and has difficulties to detect tampering part text. In order to break these limitations, we study the differences between digital camera photo and image obtained by editing software, we use kurtosis, differential and so on to quantify the degree of differences. Using the idea of splitting the text to solve the problem that the existing forensics technology can't detect text part tampering, suspected from the image divided stroke region, we extract characteristics of strokes of the edge point. On the basis of a large number pictures that known authenticity, we use support vector machine to training classification model, and then to achieve authenticity of text image the identification.
引文
[1]赵文清等.基于PKI的数字签名和数字信封的实现.华北电力大学学报,2003,11：71-75.
[2]于工,张祥光.隐藏域图像中的数字签名.青岛科技大学学报.2004,25(2)：171-173.
[3]E T Lin, C I Podilchuk, E J Delp. Detection of Image Alterations Using Semi-fragile Watermarks. In Proceedings of the SPIE International Conference on Security and Watermarking of Multimedia Contents II,2000, Volume 3971:152-163.
[4]D Kundur, D Hatzinakos. Digital Watermarking for Tell-tale Tamper Proofing and Authentication. Proceeding of the IEEE,1999, (87)7:1167-1180.
[5]M U Celik, G Sharma, E Saber, A M Tekalp. Hierarchical Watermarking for Secure Image Authentication with Localization. IEEE Transaction on Image Proceeding, June 2002,11(6):585-595.
[6]Jessica Fridrich, David Sokal.Jan Lukas. Detecting of Copy-Move Forgery in Digital Images.in Proceedings of Digital Forensic Research Workshop,2003.
[7]Posecu A C, Farid H. Exposing Digital Forgeries by Detecting Duplicated Image Regions[R]. USA:Department of Computer Science, Dartmouth College,2004.
[8]Li G H, Wu Q, Tu D, Sun S J. A Sorted Neighborhood Approach for Detecting Duplicated Image Regions in Image Forgeries Based on DWT and SVD. In Processing of 2007 IEEE International Conference on Multimedia and Expo. Beijing, China. IEEE,2007.1750-1753.
[9]T-T Ng, S-F Chang,Sun Q. Blind Detection of Photomontage Using Higher Order Statistics. IEEE ISCAS,2004.
[10]T-T Ng, S-F Chang. Blind Image Splicing and Photomontage Detection of Photomontage Using Higher Order Statistics. ADVENT Technical Rport,201-2004-1,Columbia University,2004.
[11]T-T Ng, S-F Chang. A Model for Image Splicing. IEEE ISCAS,2004.
[12]Fridrich J., Goljan M, Du R. Steganalysis based on JPEG compatibility [A]. In:Proceedings of SPIE Multimedia Systems and Applications IV [C]. Washington D. C., USA:SPIE,2001:275-280.
[13]Fridrich J., Luka J. Estimation of primary quantization matrix in double compressed JPEG images [A]. In:Proceedings of Digital Forensic Research Workshop[C].2003:5-8.
[14]F Huang, J Huang, and Q Yun. Detecting Double JPEG Compression with the Same Quantization Matrix. Information Forensics and Security, IEEE Transactions.5(4):848-856,2010.
[15]Posecu A C, Farid H. Exposing Forgeries by Detecting Traces of Resampling. IEEE Trans. On Signal Processing,2005,53(2):758-767.
[16]朱秀明,宣国荣,姚秋明,童学锋,施云庆.信息取证中图像重采样的检测.计算机应用,2006,26(11)：2569-2597.
[17]Hsiao D Y, Pei S C. Detecting digital Tampering by Blur Estimation. In:Proceedings of the 1st International Workshop on Systematic Approaches to Digital Forensic Engineering. Taipei, China:IEEE,2005.264-278.
[18]Sutcu Y, Coskun B, Sencar H T,Memon N. Tamper Detection Based on Regurality o Wavelet Transform Coefficients. In:Proceedings of 2007 IEEE International Conference on Image Procesing. San Antonio, USA:IEEE,2007.397-400.
[19]周琳娜,王东明,郭云彪,杨义先.基于数字图像边缘特性的形态学滤波取证技术.电子学报(6),2008.6.
[20]孙堡垒,周琳娜,张茹.基于Benford定律的高斯模糊取证.计算机研究与发展,2009(46)：211-216.
[21]王波,孙璐璐,孔祥维,等.图像伪造中模糊操作的异常色调率取证技术.电子学报,2006(12A)：2451-2454.
[22]Posecu A C, Farid H. Exposing Digital Forgeries in Color Filter Array Interpolated Images. IEEE Transactions on Signal Processing,2005,53(10):3948-3959.
[23]Lukas J, Fridrich J, Goljian M. Detecting Digital Image Forgeries Using Sensor Pattern Noise. In:Proceeding of the SPIE. San Jose, USA:SPIE,2006.362-372.
[24]Lukas J, Fridrich J. Detecting Image Forensics Using Sensor Noise. IEEE Signal Processing Magazine, vol.26, no.2, March 2009, pp.26-37.
[25]Johnson M K, Farid H. Exposing Digital Forgeries through Chromatic Aberration. In:Proceedings of the 8th Workshop on Multimedia and Security. Geneva, Switzerland:ACM,2006.48-55.
[26]Hsu Y F, Chang S F. Detecting Image Splicing Using Geometry Invariants and Camera. In:Processing of 2006 IEEE International Conference on Multimedia and Expo. Toronto, Canada:IEEE,2006.549-552.
[27]Johnson M. K., Farid H. Exposing Digital Forgeries by Detecting Inconsistencies in Lighting. In:Proceedings of ACM Multimedia and Security Workshop. New York, NY, USA:ACM,2005:1-10.
[28]Micah K. Johnson, Hanny Farid. Exposing Digital Forgeries Through Specular Highlights on the Eyes.9th International Workshop on Information Hiding, Saint Ma-lo,France,2007.
[29]Micah K. Johnson, Hanny Farid. Exposing Digital Forgeries in Complex Lighting Environments. IEEE Transactions on Information Forensics and Security,2007.
[30]Eric Kee, Farid H. Exposing Digital Forgeries From 3-D Lighting Environments. Information Forensics and Security (WIFS),2010 IEEE International Workshop on Digital Object Identifier:1-6.
[31]Micah K. Johnson, Hanny Farid. Detecting Photographic Composites of People. In 6th International Workshop on Digital Watermarking, Guangzhou, China,2007.
[32]Eric Kee, Farid H. Detecting Photographic Composites of Famous People. Technical Report, TR2009-656, Dartmouth College, Computer Science.
[33]Conotter. V, Boato. G, Farid. H, Detecting Photo Manipulation on Signs and Billboards [C], Proc ICIP 2010, Hong Kong,2010.
[34]]D R Cok. Signal Processing Method and Apparatus for Producing Interpolated Chrominance Values in A Sampled Color Image Signal. USA,Patent,4642678,1987.
[35]孟海岗,寇尊权.基于平面约束的CCD相机标定方法改进.吉林：吉林大学,2009.
[36]李玉景.支持向量机在模式识别领域中的应用研究.山东：青岛大学,2008.
[37]王波,孔祥维,尤新刚.利用彩色一致性的数字伪造图像取证方法.全国计算机安全学术交流会议论文集(vo123),2008.
[38]汉字基本笔画名称及写法.http://wenku. baidu. com/view/c359c400-02020-740bele9b78. html
[39]Dalong Li, Russell M. Mersereau, Simske. S, Blur Identification Based on Kurtosis minimization, Image Processing. IEEE. ICIP 2005.
[40]EePing Ong. Weisi Lin, Zhongkaiig Lu, Xiaokang Yang, Susir Yao, Feng Pan, Lijilrn Jiarrg, and Fulvio Moscheni,A No-reference Quality Metric for Measuring Image Blur. Proceedings of the International Conference on Image Processing, Vol.3, Rochester, NY, 2002, pp.57-60.
[41]N. F. Zhang, M. T. Postek, R. D. Larrabee, A. E. Vladar, W. J. Keery, and S. N. Jones, Image Sharpness Measurement in Scanning, Electron Microscope-Part 111, Scanning,21,1999, pp.246-252.
[42]李洋.支持向量机软件包.http://www.ilovematlab.cn/thread52388-1-1.html.
[2]于工,张祥光.隐藏域图像中的数字签名.青岛科技大学学报.2004,25(2)：171-173.
[3]E T Lin, C I Podilchuk, E J Delp. Detection of Image Alterations Using Semi-fragile Watermarks. In Proceedings of the SPIE International Conference on Security and Watermarking of Multimedia Contents II,2000, Volume 3971:152-163.
[4]D Kundur, D Hatzinakos. Digital Watermarking for Tell-tale Tamper Proofing and Authentication. Proceeding of the IEEE,1999, (87)7:1167-1180.
[5]M U Celik, G Sharma, E Saber, A M Tekalp. Hierarchical Watermarking for Secure Image Authentication with Localization. IEEE Transaction on Image Proceeding, June 2002,11(6):585-595.
[6]Jessica Fridrich, David Sokal.Jan Lukas. Detecting of Copy-Move Forgery in Digital Images.in Proceedings of Digital Forensic Research Workshop,2003.
[7]Posecu A C, Farid H. Exposing Digital Forgeries by Detecting Duplicated Image Regions[R]. USA:Department of Computer Science, Dartmouth College,2004.
[8]Li G H, Wu Q, Tu D, Sun S J. A Sorted Neighborhood Approach for Detecting Duplicated Image Regions in Image Forgeries Based on DWT and SVD. In Processing of 2007 IEEE International Conference on Multimedia and Expo. Beijing, China. IEEE,2007.1750-1753.
[9]T-T Ng, S-F Chang,Sun Q. Blind Detection of Photomontage Using Higher Order Statistics. IEEE ISCAS,2004.
[10]T-T Ng, S-F Chang. Blind Image Splicing and Photomontage Detection of Photomontage Using Higher Order Statistics. ADVENT Technical Rport,201-2004-1,Columbia University,2004.
[11]T-T Ng, S-F Chang. A Model for Image Splicing. IEEE ISCAS,2004.
[12]Fridrich J., Goljan M, Du R. Steganalysis based on JPEG compatibility [A]. In:Proceedings of SPIE Multimedia Systems and Applications IV [C]. Washington D. C., USA:SPIE,2001:275-280.
[13]Fridrich J., Luka J. Estimation of primary quantization matrix in double compressed JPEG images [A]. In:Proceedings of Digital Forensic Research Workshop[C].2003:5-8.
[14]F Huang, J Huang, and Q Yun. Detecting Double JPEG Compression with the Same Quantization Matrix. Information Forensics and Security, IEEE Transactions.5(4):848-856,2010.
[15]Posecu A C, Farid H. Exposing Forgeries by Detecting Traces of Resampling. IEEE Trans. On Signal Processing,2005,53(2):758-767.
[16]朱秀明,宣国荣,姚秋明,童学锋,施云庆.信息取证中图像重采样的检测.计算机应用,2006,26(11)：2569-2597.
[17]Hsiao D Y, Pei S C. Detecting digital Tampering by Blur Estimation. In:Proceedings of the 1st International Workshop on Systematic Approaches to Digital Forensic Engineering. Taipei, China:IEEE,2005.264-278.
[18]Sutcu Y, Coskun B, Sencar H T,Memon N. Tamper Detection Based on Regurality o Wavelet Transform Coefficients. In:Proceedings of 2007 IEEE International Conference on Image Procesing. San Antonio, USA:IEEE,2007.397-400.
[19]周琳娜,王东明,郭云彪,杨义先.基于数字图像边缘特性的形态学滤波取证技术.电子学报(6),2008.6.
[20]孙堡垒,周琳娜,张茹.基于Benford定律的高斯模糊取证.计算机研究与发展,2009(46)：211-216.
[21]王波,孙璐璐,孔祥维,等.图像伪造中模糊操作的异常色调率取证技术.电子学报,2006(12A)：2451-2454.
[22]Posecu A C, Farid H. Exposing Digital Forgeries in Color Filter Array Interpolated Images. IEEE Transactions on Signal Processing,2005,53(10):3948-3959.
[23]Lukas J, Fridrich J, Goljian M. Detecting Digital Image Forgeries Using Sensor Pattern Noise. In:Proceeding of the SPIE. San Jose, USA:SPIE,2006.362-372.
[24]Lukas J, Fridrich J. Detecting Image Forensics Using Sensor Noise. IEEE Signal Processing Magazine, vol.26, no.2, March 2009, pp.26-37.
[25]Johnson M K, Farid H. Exposing Digital Forgeries through Chromatic Aberration. In:Proceedings of the 8th Workshop on Multimedia and Security. Geneva, Switzerland:ACM,2006.48-55.
[26]Hsu Y F, Chang S F. Detecting Image Splicing Using Geometry Invariants and Camera. In:Processing of 2006 IEEE International Conference on Multimedia and Expo. Toronto, Canada:IEEE,2006.549-552.
[27]Johnson M. K., Farid H. Exposing Digital Forgeries by Detecting Inconsistencies in Lighting. In:Proceedings of ACM Multimedia and Security Workshop. New York, NY, USA:ACM,2005:1-10.
[28]Micah K. Johnson, Hanny Farid. Exposing Digital Forgeries Through Specular Highlights on the Eyes.9th International Workshop on Information Hiding, Saint Ma-lo,France,2007.
[29]Micah K. Johnson, Hanny Farid. Exposing Digital Forgeries in Complex Lighting Environments. IEEE Transactions on Information Forensics and Security,2007.
[30]Eric Kee, Farid H. Exposing Digital Forgeries From 3-D Lighting Environments. Information Forensics and Security (WIFS),2010 IEEE International Workshop on Digital Object Identifier:1-6.
[31]Micah K. Johnson, Hanny Farid. Detecting Photographic Composites of People. In 6th International Workshop on Digital Watermarking, Guangzhou, China,2007.
[32]Eric Kee, Farid H. Detecting Photographic Composites of Famous People. Technical Report, TR2009-656, Dartmouth College, Computer Science.
[33]Conotter. V, Boato. G, Farid. H, Detecting Photo Manipulation on Signs and Billboards [C], Proc ICIP 2010, Hong Kong,2010.
[34]]D R Cok. Signal Processing Method and Apparatus for Producing Interpolated Chrominance Values in A Sampled Color Image Signal. USA,Patent,4642678,1987.
[35]孟海岗,寇尊权.基于平面约束的CCD相机标定方法改进.吉林：吉林大学,2009.
[36]李玉景.支持向量机在模式识别领域中的应用研究.山东：青岛大学,2008.
[37]王波,孔祥维,尤新刚.利用彩色一致性的数字伪造图像取证方法.全国计算机安全学术交流会议论文集(vo123),2008.
[38]汉字基本笔画名称及写法.http://wenku. baidu. com/view/c359c400-02020-740bele9b78. html
[39]Dalong Li, Russell M. Mersereau, Simske. S, Blur Identification Based on Kurtosis minimization, Image Processing. IEEE. ICIP 2005.
[40]EePing Ong. Weisi Lin, Zhongkaiig Lu, Xiaokang Yang, Susir Yao, Feng Pan, Lijilrn Jiarrg, and Fulvio Moscheni,A No-reference Quality Metric for Measuring Image Blur. Proceedings of the International Conference on Image Processing, Vol.3, Rochester, NY, 2002, pp.57-60.
[41]N. F. Zhang, M. T. Postek, R. D. Larrabee, A. E. Vladar, W. J. Keery, and S. N. Jones, Image Sharpness Measurement in Scanning, Electron Microscope-Part 111, Scanning,21,1999, pp.246-252.
[42]李洋.支持向量机软件包.http://www.ilovematlab.cn/thread52388-1-1.html.