Presentation is loading. Please wait.

Presentation is loading. Please wait.

Detect Digital Image Forgeries Ting-Wei Hsu. History of photo manipulation 1860 the portrait of Lincoln is a composite of Lincoln ’ s head and John Calhoun.

Similar presentations


Presentation on theme: "Detect Digital Image Forgeries Ting-Wei Hsu. History of photo manipulation 1860 the portrait of Lincoln is a composite of Lincoln ’ s head and John Calhoun."— Presentation transcript:

1 Detect Digital Image Forgeries Ting-Wei Hsu

2 History of photo manipulation 1860 the portrait of Lincoln is a composite of Lincoln ’ s head and John Calhoun ’ s body

3 History of photo manipulation 1917: “ Cottingley fairies

4 History of photo manipulation 1930s: Stalin had disgraced comrades airbrushed out of his pictures

5 History of photo manipulation 1936: same story with Mao

6 History of photo manipulation 1936: same story with Mao

7 History of photo manipulation Oprah Winfrey head on Ann-Margret

8 History of photo manipulation 1994: O.J. Simpson ’ s mug shot modified to appear more menacing

9 History of photo manipulation

10 April 2003: This digital composite of a British soldier in Basra, gesturing to Iraqi civilians urging them to seek cover,

11 History of photo manipulation

12 February 2004: Senator John Kerry and Jane Fonda sharing a stage at an anti- war rally emerged during the 2004 Presidential primaries as Senator Kerry was campaigning for the Democratic nomination.

13 History of photo manipulation

14 March 2004

15 History of photo manipulation February 2008:

16 History of photo manipulation August 2007

17 History of photo manipulation November 2007

18 Cue in Forgeries Detection Light Transport Difference Acquisition Difference Model Detect

19 Detect inconsistencies in Lighting If the photo was composited, it ’ s often difficult to match the lighting conditions from individual photographs.

20 Detect inconsistencies in Lighting

21

22 Color Model Assumption: –the surface of interest is Lambertian –the surface has a constant reflectance value –the surface is illuminated by a point light source infinitely far away

23 Image Intensity Model R : constant reflectance value N(x,y) : 3 vector representing the surface normal at (x,y) A : constant ambient light L : surface normal

24 Image Intensity Model

25 Results

26

27 Using in Forgeries Detection

28 Detect Duplicated Image Region A common manipulation in tampering with an image is to copy and paste portions of the image to conceal a person or object in the scene.

29 Forgeries Using Duplicated Image

30 Applying PCA on small fixed size image block. –Reduce dimension representation –This representation is robust to minor variations in the image due to additive noise or lossy compression Do lexicographic sorting

31 Results Take 10 seconds in 512*512 image using 3 GHz processor

32 Results

33 Detect by Tracking Re- sample Processing in making forgeries often necessary to resize or rotate. Assume resizing by linear or cubic interpolation method.

34 Resample Resample by factor of 4/3

35 Resample

36

37 Use EM algorithm to estimate

38 Resized Estimate

39 Rotated Estimate

40 Rotated and Resized Upsampled by 15% and rotated by 5% Rotated by 5% and upsampled by 15%

41 Forgery Detect

42 PATTERN NOISE & DETECTION OF ITS PRESENCE Detection of digitally manipulated images based on the sensor pattern noise. Detection whether image take from same camera or from another region.

43 Image Fetch Processing

44 PATTERN NOISE & DETECTION OF ITS PRESENCE Most digital camera with CCD or CMOS use color filter array (CFA)

45 PRNU Photo-response non-uniformity noise Dominate part of the pattern noise in nature images. PNU – pixel non-uniformity : different sensitivity of pixel to light Caused by stochastic inhomogenities present in silicon wafer

46 Noise Model x ij : signal from light η ij : random shot noise c ij : dark current ε ij : read-out noise

47 Learn PNU F : denoising filtering Training by more than 50 picture

48 Detect Random select n region with m masks Estimate

49 Forgery Detection Mask

50 Forgery Detection

51

52

53

54 Reference Luk?, J., J. Fridrich, et al. "Detecting digital image forgeries using sensor pattern noise." Proc. SPIE, Electronic Imaging, Security, Steganography, and Watermarking of Multimedia Contents VIII 6072: 16?9. Lyu, S. and H. Farid (2005). "How realistic is photorealistic?" IEEE Transactions on Signal Processing 53(2 Part 2): 845-850. Ng, T., S. Chang, et al. (2005). Physics-motivated features for distinguishing photographic images and computer graphics, ACM New York, NY, USA. Popescu, A. and H. Farid "Exposing digital forgeries by detecting duplicated image regions." Department of Computer Science, Dartmouth College. Popescu, A. and H. Farid (2005). "Exposing digital forgeries by detecting traces of resampling." IEEE Transactions on Signal Processing 53(2 Part 2): 758-767. Popescu, A. and H. Farid (2005). "Exposing digital forgeries in color filter array interpolated images." IEEE Transactions on Signal Processing 53(10 Part 2): 3948- 3959.

55 Reference http://www.cs.dartmouth.edu/farid/r esearch/digitaltampering/http://www.cs.dartmouth.edu/farid/r esearch/digitaltampering/ http://www.newseum.org/berlinwall/c ommissar_vanishes/vanishes.htmhttp://www.newseum.org/berlinwall/c ommissar_vanishes/vanishes.htm http://www.cs.unc.edu/~lazebnik/res earch/fall08/http://www.cs.unc.edu/~lazebnik/res earch/fall08/


Download ppt "Detect Digital Image Forgeries Ting-Wei Hsu. History of photo manipulation 1860 the portrait of Lincoln is a composite of Lincoln ’ s head and John Calhoun."

Similar presentations


Ads by Google