Abstract: We present an efficient technique to detect portions of a digital image that have been modified using textural information from another region of the image, for example Photoshop's healing brush or Poisson cloning. Common uses of these tools include removing damaged areas, blemishes and sometimes larger objects from a scene. We show that the methods are efficient and accurately identify the use of a large class of image manipulation techniques for uncompressed TIFF images and high quality compressed images. When applied to images that have higher compression levels accurate results are also obtained if the region that has been duplicated is sufficiently large.

@inproceedings{Dybala:2007aa,
  publisher    = {ACM Press},
  author       = {Brandon Dybala and Brian Jennings and David Letscher},
  url          = {http://portal.acm.org/ft_gateway.cfm?id=1288877&type=pdf&coll=GUIDE&dl=GUIDE&CFID=4725707&CFTOKEN=57548819},
  year         = {2007},
  booktitle    = {MM\&Sec'07, Proceedings of the Multimedia and Security Workshop 2007, September 20-21, 2007, Dallas, TX, USA},
  address      = {New York, NY, USA},
  title        = {Detecting filtered cloning in digital images},
  pages        = {43--50},
}