Automated image splicing detection from noise estimation in raw images

Splicing is a common image manipulation technique in which a region from a first image is pasted onto a second image to alter its content. In this paper, we use the fact that different images have different noise characteristics, according to the camera and lighting conditions during the image acquisition. The proposed method automatically detects image splicing in raw images by highlighting local noise inconsistencies within a quadtree scan of the image. The image noise is modelized by both Gaussian and Poisson noise components. We demonstrate the efficiency and robustness of our method on several images generated with an automated image splicing.

[1]  Xing Zhang,et al.  Exposing image forgery with blind noise estimation , 2011, MM&Sec '11.

[2]  Hugues Talbot,et al.  An EM approach for Poisson-Gaussian noise modeling , 2011, 2011 19th European Signal Processing Conference.

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

[4]  Junfeng He,et al.  Detecting Doctored JPEG Images Via DCT Coefficient Analysis , 2006, ECCV.

[5]  Jan Lukás,et al.  Detecting digital image forgeries using sensor pattern noise , 2006, Electronic Imaging.

[6]  Babak Mahdian,et al.  Detection of Resampling Supplemented with Noise Inconsistencies Analysis for Image Forensics , 2008, 2008 International Conference on Computational Sciences and Its Applications.

[7]  Xing Zhang,et al.  Exposing image splicing with inconsistent local noise variances , 2012, 2012 IEEE International Conference on Computational Photography (ICCP).

[8]  Babak Mahdian,et al.  Using noise inconsistencies for blind image forensics , 2009, Image Vis. Comput..

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

[10]  Alessandro Foi,et al.  Image Denoising by Sparse 3-D Transform-Domain Collaborative Filtering , 2007, IEEE Transactions on Image Processing.

[11]  Chi-Keung Tang,et al.  Fast, automatic and fine-grained tampered JPEG image detection via DCT coefficient analysis , 2009, Pattern Recognit..

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

[13]  Wei Su,et al.  Image splicing detection using 2-D phase congruency and statistical moments of characteristic function , 2007, Electronic Imaging.

[14]  Hany Farid,et al.  Exposing Digital Forgeries From JPEG Ghosts , 2009, IEEE Transactions on Information Forensics and Security.

[15]  Hany Farid,et al.  Statistical Tools for Digital Forensics , 2004, Information Hiding.

[16]  Karen O. Egiazarian,et al.  Practical Poissonian-Gaussian Noise Modeling and Fitting for Single-Image Raw-Data , 2008, IEEE Transactions on Image Processing.

[17]  Jean-Michel Morel,et al.  Non-Local Means Denoising , 2011, Image Process. Line.

[18]  Hugues Talbot,et al.  A primal-dual proximal splitting approach for restoring data corrupted with poisson-gaussian noise , 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).