Skip to main content
MSU CSE Colloquium Series 2015-2016: Siwei Lyu Digital Image Forensics: There is More to a Picture Than Meets the Eye

Dr. Siwei Lyu
Associate Professor
University at Albany, State University of New York

Time: Friday, Oct 23, 2015, 2pm
Location: Anthony Hall 1257

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 galvanize 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:
- image splicing, where regions from an image is pasted into a different image;
- region duplication, where regions in the same image is copied, transformed, and pasted to new locations to conceal the original image contents;
- photographic or photorealistic, 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.

Siwei Lyu is an Associate Professor at the Computer Science Department of University at Albany, State University of New York. Prior to joining University at Albany, he was a Post-Doctoral Research Associate at the Howard Hughes Medical Institute and the Center for Neural Science of New York University, and an Assistant Researcher at Microsoft Research Asia. He graduated from Dartmouth College with Ph.D. degree in Computer Science in 2005, and from Beijing University with M.S. degree in Computer Science and B.S. degree in Information Science in 2000 and 1997, respectively. His main research interests include digital image/video forensics, computer vision, machine learning and computational neural science. He has authored one book, one book chapter and more than 60 refereed technical papers. He is the recipient of the IEEE Signal Processing Society Best Paper Award in 2011, and the National Science Foundation CAREER Award in 2010.

Dr. Xiaoming Liu