The past decade has witnessed remarkable advances in digital image processing and computational photography, resulting in sophisticated image-editing software systems. The ease of digital image manipulation has also posed many new challenges. In particular, digital images have become more vulnerable to malicious tampering compared to their non-digital counterparts. This circumstance galvanized rapid developments of research in digital image forensics.
In this talk, I will focus on my recent works in detecting several types of digital image tampering operations, including:
- region duplication, where regions in the same image are copied, transformed, and pasted to new locations to conceal the original image contents;
- image splicing, where regions from an image are pasted into a different image;
- photographic vs. photorealistic detection, where the task is to differentiate a real photograph from an image made from computer graphics software.
The unifying theme of these techniques is to use statistical analysis of normal natural photographic image signals to show abnormalities of tampered images. I will describe the mathematical and algorithmic aspects of these methods, and demonstrate their effectiveness on realistic image forgeries.
Bio: Siwei Lyu is Assistant Professor at the Computer Science Department of University at Albany, State University of New York, Albany, New York, USA. His scientific expertise include natural image statistics, computational visual neural science, digital image forensics, machine learning, and computer vision.
He received his B.S. degree in information science from Peking University, China, in 1997, and his M.S. degree in computer science from Peking University, China, in 2000. He received his Ph.D. degree in computer science from Dartmouth College, Hanover, New Hampshire, USA in 2005. From 1998 to 2000, he worked at the Founder Research and Development Center (Beijing, China) as a Software Engineer. From 2000 to 2001, he worked at Microsoft Research Asia (then Microsoft Research China) as an Assistant Researcher. From 2005 to 2008, he was a Post-Doctoral Research Associate at the Howard Hughes Medical Institute and the Center for Neural Science of New York University.
Prof. Lyu is a member of ACM and IEEE Signal Processing Society. He is the recipient of the Alumni Thesis Award of Dartmouth College in 2005, IEEE Signal Processing Society Best Paper Award in 2010, and the US National Science Foundation Early Faculty CAREER Award in 2010. He has authored and contributed to two books on digital image forensics, and held two U.S. and one E.U. patents. He has published more than 30 conference and journal articles in the research fields of natural image statistics, computational visual neural science, digital image forensics, machine learning and computer vision.