Time：9:30 am, July 9, 2011
Venue: Conference Room of Optical Image Analysis and Learning Center (OPTIMAL)
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. The performance of the existing automatic segmentation approaches is far from satisfactory. In the past few years, users are being included into the processing loop, i.e. interactive image segmentation, which involves minimal user interaction to incorporate user intention in the segmentation process. One weakness in the existing interactive image segmentation algorithms is the lack of more intelligent ways to understand the intention of user inputs. In this talk, I will present our recent work on interactive image segmentation, where we advocate the use of multiple intuitive user inputs to better reflect user's intention. Experimental results on the benchmark datasets show that the proposed framework is highly effective and can quickly and accurately segment a wide variety of natural images with ease.
Jianfei Cai received his PhD degree from University of Missouri-Columbia in 2002. Currently, he is the Head of Computer Communications Division at the School of Computer Engineering, Nanyang Technological University, Singapore. His major research interests include visual signal processing and multimedia networking. He has published over 100 technical papers in international conferences and journals. He has been actively participated in program committees of various conferences. He will serve as a technical program co-chair for IEEE ICME 2012 and general chair for PCM 2012. He is also an Associate Editor for IEEE Transactions on Circuits and Systems for Video Technology (T-CSVT). He is a senior member of IEEE.