Iterative Local-Global Energy Minimization for Automatic Extraction of Objects of Interest.
Lists
Only you see this
Abstract
We propose a novel global-local variational energy to automatically extract objects of interest from images. Previous formulations only incorporate local region potentials, which are sensitive to incorrectly classified pixels during iteration. We introduce a global likelihood potential to achieve better estimation of the foreground and background models and, thus, better extraction results. Extensive experiments demonstrate its efficacy
BibTeX
@article{hua2006iterative,
author = {Gang Hua and Zicheng Liu and Zhengyou Zhang and Ying Wu},
title = {{Iterative Local-Global Energy Minimization for Automatic Extraction of Objects of Interest.}},
journal = {IEEE Trans. Pattern Anal. Mach. Intell.},
year = {2006},
doi = {10.1109/tpami.2006.209},
}Loading related content...