Learning images using compositional pattern-producing neural networks for source camera identification and digital demographic diagnosis

In this work, we propose a neural network based framework to explore the statistical correlation intrinsically embedded due to interpolations in a relatively small neighborhood, in which the interpolation process is cognized from the interpolation results and the spatially invariant stylized computational rules in interpolation algorithms are simulated and learned by adjusting weights and bias values of neural networks. Experiments show that, our approach is competitive among the state of the art of source camera identification methods. It is also effective for digital forgery detection and other interesting experiments such as the digital demographic diagnosis and prediction. The framework can also be applied to other types of image interpolations such as super-resolution.

[1]  Michael Elad,et al.  Multiframe demosaicing and super-resolution of color images , 2006, IEEE Transactions on Image Processing.

[2]  Nasir D. Memon,et al.  Source camera identification based on CFA interpolation , 2005, IEEE International Conference on Image Processing 2005.

[3]  Matthias Kirchner,et al.  Fast and reliable resampling detection by spectral analysis of fixed linear predictor residue , 2008, MM&Sec '08.

[4]  Yizhen Huang,et al.  Image Based Source Camera Identification using Demosaicking , 2006, 2006 IEEE Workshop on Multimedia Signal Processing.

[5]  Yizhen Huang,et al.  A pixel-based digital photo authentication framework via demosaicking inter-pixel correlation , 2009, MM&Sec '09.

[6]  Martin Vetterli,et al.  Demosaicking by Alternating Projections: Theory and Fast One-Step Implementation , 2010, IEEE Transactions on Image Processing.

[7]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[8]  Ron Kimmel,et al.  Demosaicing: Image Reconstruction from Color CCD Samples , 1998, ECCV.

[9]  L. Zhaoxiang,et al.  Sex Preference, Fertility, and Family Planning in China , 1986 .

[10]  Norbert Wiener,et al.  Extrapolation, Interpolation, and Smoothing of Stationary Time Series , 1964 .

[11]  Yizhen Huang Can digital image forgery detection be unevadable? A case study: color filter array interpolation statistical feature recovery , 2005, Visual Communications and Image Processing.

[12]  Amparo Alonso-Betanzos,et al.  A Very Fast Learning Method for Neural Networks Based on Sensitivity Analysis , 2006, J. Mach. Learn. Res..

[13]  Mohan S. Kankanhalli,et al.  A Survey on Digital Camera Image Forensic Methods , 2007, 2007 IEEE International Conference on Multimedia and Expo.

[14]  Sviatoslav Voloshynovskiy,et al.  Watermark copy attack , 2000, Electronic Imaging.

[15]  V. Tikhomirov On the Representation of Continuous Functions of Several Variables as Superpositions of Continuous Functions of one Variable and Addition , 1991 .

[16]  Yizhen Huang,et al.  Demosaicking recognition with applications in digital photo authentication based on a quadratic pixel correlation model , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[17]  H. Farid A Survey of Image Forgery Detection , 2008 .

[18]  Alin C. Popescu,et al.  Exposing digital forgeries in color filter array interpolated images , 2005, IEEE Transactions on Signal Processing.

[19]  R. Schafer,et al.  Demosaicking: Color Filter Array Interpolation in Single-Chip Digital Cameras , 2003 .

[20]  Ron Kimmel,et al.  Demosaicing: Image Reconstruction from Color CCD Samples , 1998, ECCV.

[21]  B. Silver,et al.  Fertility and sex ratios at birth in China: the effects of parity and the sex composition of previous children based on ethnic comparisons in Xinjiang. , 1994 .

[22]  R.W. Schafer,et al.  Demosaicking: color filter array interpolation , 2005, IEEE Signal Processing Magazine.

[23]  Min Wu,et al.  Image acquisition forensics: Forensic analysis to identify imaging source , 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

[24]  Jian Sun,et al.  Lazy snapping , 2004, SIGGRAPH 2004.

[25]  J. Kahane Sur le théorème de superposition de Kolmogorov , 1975 .

[26]  Sushil K. Bhattacharjee,et al.  Towards second generation watermarking schemes , 1999, Proceedings 1999 International Conference on Image Processing (Cat. 99CH36348).

[27]  Edward Y. Chang,et al.  Color filter array recovery using a threshold-based variable number of gradients , 1999, Electronic Imaging.

[28]  Yizhen Huang,et al.  Learning from interpolated images using neural networks for digital forensics , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[29]  Tsuhan Chen,et al.  Image authentication by detecting traces of demosaicing , 2008, 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[30]  E. Loftus,et al.  Changing history: doctored photographs affect memory for past public events , 2007 .

[31]  Kenneth O. Stanley,et al.  Compositional Pattern Producing Networks : A Novel Abstraction of Development , 2007 .

[32]  Martin Fodslette Meiller A Scaled Conjugate Gradient Algorithm for Fast Supervised Learning , 1993 .

[33]  Hany Farid,et al.  Exposing digital forgeries by detecting inconsistencies in lighting , 2005, MM&Sec '05.

[34]  Yücel Altunbasak,et al.  Color plane interpolation using alternating projections , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[35]  Jan-Olof Eklundh,et al.  Automatic estimation of the projected light source direction , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[36]  Yizhen Huang,et al.  Adaptive Demosaicking using Multiple Neural Networks , 2006, 2006 16th IEEE Signal Processing Society Workshop on Machine Learning for Signal Processing.

[37]  Nasir D. Memon,et al.  Blind source camera identification , 2004, 2004 International Conference on Image Processing, 2004. ICIP '04..

[38]  Bülent Sankur,et al.  Blind Identification of Source Cell-Phone Model , 2008, IEEE Transactions on Information Forensics and Security.

[39]  Hany Farid,et al.  Exposing digital forgeries by detecting traces of resampling , 2005 .

[40]  H. Farid,et al.  Image forgery detection , 2009, IEEE Signal Processing Magazine.

[41]  Nasir D. Memon,et al.  Image manipulation detection , 2006, J. Electronic Imaging.

[42]  Nasir D. Memon,et al.  Classification of digital camera-models based on demosaicing artifacts , 2008, Digit. Investig..

[43]  Min Wu,et al.  Nonintrusive component forensics of visual sensors using output images , 2007, IEEE Transactions on Information Forensics and Security.

[44]  Ching Y. Suen,et al.  Application of majority voting to pattern recognition: an analysis of its behavior and performance , 1997, IEEE Trans. Syst. Man Cybern. Part A.

[45]  Chu Junhong,et al.  Prenatal Sex Determination and Sex‐Selective Abortion in Rural Central China , 2001 .

[46]  Vera Kurková,et al.  Kolmogorov's theorem and multilayer neural networks , 1992, Neural Networks.

[47]  Alex ChiChung Kot,et al.  A generalized model for detection of demosaicing characteristics , 2008, 2008 IEEE International Conference on Multimedia and Expo.

[48]  Siwei Lyu,et al.  How realistic is photorealistic , 2005 .

[49]  Kwanghoon Sohn,et al.  Interpolation using neural networks for digital still cameras , 2000, IEEE Trans. Consumer Electron..

[50]  Yizhen Huang,et al.  Super-resolution using neural networks based on the optimal recovery theory , 2006, 2006 16th IEEE Signal Processing Society Workshop on Machine Learning for Signal Processing.

[51]  Chih-Jen Lin,et al.  A comparison of methods for multiclass support vector machines , 2002, IEEE Trans. Neural Networks.