Image segmentation plays very important role in digital image processing, pattern recognition and computer vision. Although image segmentation has been studied for decades, it is still being regarded as one of the most difficult problems in image processing, especially on achieving general object-level image segmentation. Here, we focus on the problem of cutting out foreground object-of-interest from an image, where one major question we need to answer is where the object-of-interest is. In the recent years, we do see many interesting solutions that figure out where the object-of-interest is through training, user interactions, saliency detection, etc. In this talk, I will share with you a series of my group''s works on cutting out foreground object-of-interest from an image through user interactions, Internet images as well as the shadows in Kinect data and show the comparisons with the state-of-the-art.
Jianfei Cai received his PhD degree from the University of Missouri-Columbia. Currently, he is the Head of Visual & Interactive Computing Division at the School of Computer Engineering, Nanyang Technological University, Singapore. His major research interests include visual information processing and multimedia networking. He has published over 100 technical papers in international conferences and journals. He has been actively participating in program committees of various conferences. He had served as the leading Technical Program Chair for IEEE International Conference on Multimedia & Expo (ICME) 2012 and he currently sits on the steering committee of ICME. He was an invited speaker for the first IEEE Signal Processing Society Summer School on 3D and high definition/high contrast video process systems in 2011. He is also an Associate Editor for IEEE Transactions on Circuits and Systems for video Technology (T-CSVT), and a senior member of IEEE.