IATH NEWS
Forensic methods for detecting fake digital images
April 25, 2016
James F. O'Brien, Professor of Computer Science at the University of California, Berkeley, and Chief Scientist at Avametric, will speak on techniques for detecting whether or not a digital image has been tampered with. He will be speaking as part of the UVA Computer Science Department's Distinguished Speaker Series, on Friday, April 29, at 10:45am in Rice 242.
Prof. O'Brien's research interests include graphics, computer animation, simulations of physical systems, and the forensic analysis of images and video. He has authored numerous papers on these topics. In addition to his research pursuits, Prof. O'Brien has worked with film and game companies on integrating advanced simulation physics into games and special effects. His methods for destruction modeling have been used in over 100 feature films and AAA game titles. In 2015 the Academy of Motion Picture Arts and Sciences recognized his work in destruction modeling with an Academy Award for Technical Achievement. He received his doctorate from the Georgia Institute of Technology in 2000, the same year he joined the faculty at U.C. Berkeley. Professor O'Brien is a Sloan Fellow and ACM Distinguished Scientist, has been selected as one of Technology Review's TR-100, and has been awarded research fellowships from the Okawa and Hellman Foundations. He is currently serving as ACM SIGGRAPH Director at Large.
Abstract
Advances in computational photography, computer vision, and computer graphics allow for the creation of visually compelling photographic forgeries. Forged images have appeared in tabloid magazines, main-stream media outlets, political attacks, scientific journals, and the hoaxes that land in our email in-boxes. These doctored photographs are appearing with growing frequency and sophistication, and even experts cannot rely on visual inspection to distinguish authentic images from forgeries.
Techniques in image forensics operate on the assumption that photo-tampering will measurably disturb an image. In a well-executed forgery these disturbances will either be perceptibly insignificant, or they may be noticeable but subjectively plausible. Methods for forensic analysis provide a means to detect and quantify specific types of tampering. To the extent that these perturbations can be quantified and detected, they can be used to objectively invalidate a photo.
This talk will focus on forensic methods based on geometric content analysis. These methods work by finding inconsistencies in the geometric relationships among objects depicted in a photograph. The geometric relationships in the 2D image correspond to the projection of the relations that exist in the 3D scene. If a scene is known to contain a given relationship but the projected relation does not hold in the photograph, then one may conclude that the photograph is not a true projective image of the scene. The goal is to build a set of hard constraints that must be satisfied or else the image must be fake.
