Abstract: The many images deriving from the Web have a pronounced effect on opinions and bias of every person exploiting it. Technological means for image analysis would be extremely useful for the evaluation, understanding and validation of pictures used in the communication process. Though the current state of the art of image forensics permits to acquire very interesting information about image history, all the instruments developed so far focus on the analysis of single images. It is the aim of this paper to propose a new approach which moves the forensics analysis further, by considering groups of images instead of single images. The idea is to discover dependencies among a group of images representing similar or equal contents in order to construct a graph describing image histories and relationships. We propose a theoretical framework for image dependency analysis, resulting in a dependency test and a dependency graph. To demonstrate how the proposed formalization could be implemented in practice, we consider two practical examples where a set of images represents a given subject: by applying the proposed dependency test we are able to build the graph where the directed links indicate the dependency, with related direction, among the considered images.

  url          = {http://link.aip.org/link/?PSISDG/7541/75410X/1},
  booktitle    = {SPIE Conference on Media Forensics and Security},
  author       = {Alessia De Rosa and Francesca Uccheddu and Alessandro Piva and Mauro Barni and Andrea Costanzo},
  location     = {San Jose, CA},
  year         = {2010},
  title        = {Exploring image dependencies: a new challenge in image forensics},