Accession Number : ADA627072


Title :   AMULET: A MUlti-cLuE Approach to Image Forensics


Descriptive Note : Final rept. 1 Oct 2012-31 Dec 2014


Corporate Author : SIENA UNIV (ITALY)


Personal Author(s) : Barni, Mauro ; Fontani, Marco ; Tondi, Benedetta


Full Text : https://apps.dtic.mil/dtic/tr/fulltext/u2/a627072.pdf


Report Date : 31 Dec 2014


Pagination or Media Count : 72


Abstract : The goal of AMULET (A MUlti-cLuE approach To image forensics) was the development of multi-clue forensics techniques that, starting from the indications provided by a pool of forensic tools focusing on specific artifacts, reach a global conclusion about the authenticity of an image. The techniques had to operate in highly nonstructured scenarios characterized by imprecise and incomplete information. The main output of the research activity has been the development of a non-conventional multi-clue inference framework based on Dempster- Shafer (DST) Theory of evidence.


Descriptors :   *FORENSIC ANALYSIS , *IMAGE PROCESSING , *LEARNING MACHINES , *STATISTICAL INFERENCE , ACOUSTIC DETECTION , BAYES THEOREM , DECISION MAKING , EXPERIMENTAL DESIGN , FUZZY LOGIC , GAME THEORY , INFORMATION SECURITY , MATHEMATICAL MODELS , NANOPARTICLES , NEURAL NETS , PATTERN RECOGNITION , PROBABILITY DISTRIBUTION FUNCTIONS , REASONING , SECURITY , SYSTEMS ENGINEERING , UNCERTAINTY , VECTOR ANALYSIS


Subject Categories : Statistics and Probability
      Cybernetics
      Acoustics


Distribution Statement : APPROVED FOR PUBLIC RELEASE