Detecting photographic composites using two-view geometrical constraints

In this work, we describe a new technique for detecting image composites by enforcing two-view geometrical constrains: H and F constraints on image pairs, where H denotes the planar homography matrix and F the fundamental matrix. Our approach detects fake regions efficiently on pictures taken at the same scene but with different camera configurations. Performance of this approach is demonstrated on real image pairs with visually plausible composites.

[1]  Weihong Wang,et al.  Exposing digital forgeries in video by detecting duplication , 2007, MM&Sec.

[2]  Weihong Wang,et al.  Detecting Re-projected Video , 2008, Information Hiding.

[3]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

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

[5]  Zhengyou Zhang,et al.  Determining the Epipolar Geometry and its Uncertainty: A Review , 1998, International Journal of Computer Vision.

[6]  Ingemar J. Cox,et al.  Digital Watermarking , 2003, Lecture Notes in Computer Science.

[7]  Xiaochun Cao,et al.  Single view compositing with shadows , 2005, The Visual Computer.

[8]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[9]  Micah K. Johnson,et al.  Metric Measurements on a Plane from a Single Image , 2006 .

[10]  Andrew Zisserman,et al.  Multiple view geometry in computer visiond , 2001 .

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

[12]  Hongmei Liu,et al.  Feature based watermarking scheme for image authentication , 2008, 2008 IEEE International Conference on Multimedia and Expo.