Projects‎ > ‎Projects Archive‎ > ‎

Multimedia Forensics

Multimedia Forensics

In the analog world, an image (specifically a photograph) has generally been accepted as a "proof of occurrence" of the event it depicts. In today's digital age, however, the creation and manipulation of digital images and videos are made simple through digital processing tools that are easily and widely available. As a consequence, we can no longer take the authenticity of images and videos for granted, be they analog or digital. This is especially true when it comes to legal evidence. Image and video forensics, in this context, is concerned with uncovering some underlying fact about an image or video.

The past few years have seen a growth of research on image forensics. The work has come to focus mainly on three types of problems:

  1. Image origin/type identification. The goal is to determine through what means a given digital image was originally generated, e.g., digital camera, scanner, computer graphics software, etc. The most immediate challenge in this area is to discriminate computer generated images, which do not depict real-life occurrences, from real images.
  2. Image source identification. Given the type of an image, this research area aims at identifying the class and/or individual characterisctics of the mechanism that generated the digital image. This essentially entails associating the image with a class of sources that have common characteristics (e.g., device model) and matching the image to an individual source device.

  3. Image forgery detection. In this field of research, the objective is to determine whether a given digital image has undergone any form of modification or processing after it was initially captured. Determining the processing history of an image and identification of tampered image parts are the foremost research goals.
Research at ISIS has developed many techniques that address the three dimensions of the digital image forensics.

Sponsors:

  • AFOSR
  • NIJ

Participants:

Baris Coskun
Taha Sencar
Nasir Memon
Emir Dirik
Sevinc Bayram
Yagiz Sutcu
Kurt Rosenfeld

Resources: ISIS in the NEWS


Data Sets and Codes
Book Chapter

Journal
Conference