题目:The Image Matting Method with Zero-One Regularization
报告人:Professor Junbin Gao
School of Computing and Mathematics
Charles Sturt University
Bathurst, NSW 2795
时间:2011年1月6日(周四)下午15:00—16:00
地点:南一楼中311
摘要: Image matting refers to the problem of accurately extracting foreground objects in images and video. The most recent work in natural image matting relies on the local and manifold smoothness assumptions on foreground and background colors on which a cost function is established. The closed-form solution has been derived based on certain degree of user inputs. In this work, we present a framework of formulating new regularization for robust solutions under the so-called zero-one regularisers. I also illustrate the new algorithm using the standard benchmark images and very comparable results have been obtained.