Lecture Series in Pattern Recognition
题 目（TITLE）：Digital Image forensics using physical and geometric constraints
讲 座 人（SPEAKER）: Prof. XiaoChun Cao，the Tianjing University
主 持人 (CHAIR)： Dr. Ran He
时 间 (TIME)： 15:00PM, Sep. 21 (Friday), 2012
地 点 (VENUE)： 1115 Meeting Room
Photographs or paintings lost their innocent many years ago. With the advent of high-resolution digital cameras, powerful personal computers and sophisticated photo-editing software, the manipulation of photos is becoming more common. This talk will first show some interesting examples of famous fake images, followed by our three recent works on this area. The first work is to use an automatic fake region detection method based on the planar homography constraint, and an automatic extraction method using graph cut with online feature/parameter selection. The second work presents a framework for detecting tampered digital images based on photometric consistency of illumination in shadows. In particular, we formulate color characteristics of shadows measured by the shadow matte value. The shadow boundaries and the penumbra shadow region in an image are first extracted. Then a simple and efficient method is used to estimate shadow matte values of shadows. Our approach efficiently extracts these constraints from a single view of a target scene and makes use of them for the digital forgery detection. The last work considers the fact that distortion is often considered as an unfavorable factor in most image analysis. However, it is undeniable that the distortion reflects the intrinsic property of the lens, especially, the extreme wide-angle lens, which has a significant distortion. We show how explicitly employing the distortion cues can detect the forgery object in distortion image.
Xiaochun Cao received the B.E. and M.E. degrees both in computer science from Beihang University (BUAA), Beijing, China. He received the Ph.D. degree in computer science from the University of Central Florida, Orlando, USA, with his dissertation nominated for the university-level award for Outstanding Dissertation. After graduation, he spent about two and half years at ObjectVideo Inc. as a Research Scientist. Since August 2008, he has been with Tianjin University, China, where he is currently Professor of Computer Science. He has authored and coauthored over 60 peer-reviewed journal and conference papers, and has been in the organizing and the technical committees of several international colloquia. In 2004 and 2010, Dr. Cao was the recipients of the Piero Zamperoni best student paper award at the International Conference on Pattern Recognition.