Title :
The Image Matting Method with Regularized Matte
Author :
Gao, Junbin ; Paul, Manoranjan ; Liu, Jun
Author_Institution :
Sch. of Comput. & Math., Charles Sturt Univ., Bathurst, NSW, Australia
Abstract :
Image matting refers to the problem of accurately extracting foreground objects in images and video. The most recent works in natural image matting relies on the local and manifold smoothness assumptions on foreground and background colors on which a cost function is established. In this paper, we present a framework of formulating new regularization for robust solutions and illustrate new algorithms using the standard benchmark images.
Keywords :
feature extraction; image colour analysis; smoothing methods; video signal processing; background color; cost function; foreground color; foreground object extraction; local smoothness assumption; manifold smoothness assumption; natural image matting; regularized matte; video; Cost function; Image color analysis; Laplace equations; Linear programming; Manifolds; Vectors; Image Matting; Laplacian Matrix; Local Tangent Space Alignment; Manifold Learning;
Conference_Titel :
Multimedia and Expo (ICME), 2012 IEEE International Conference on
Conference_Location :
Melbourne, VIC
Print_ISBN :
978-1-4673-1659-0
DOI :
10.1109/ICME.2012.182
