Iterative local-global energy minimization for automatic extraction of objects of interest

Gang Hua*, Zicheng Liu, Zhengyou Zhang, Ying Wu

*Corresponding author for this work

Research output: Contribution to journalArticle

20 Scopus citations

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.

Original languageEnglish (US)
Pages (from-to)1701-1706
Number of pages6
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume28
Issue number10
DOIs
StatePublished - Dec 1 2006

Keywords

  • Level set
  • Semisupervised learning
  • Variational energy

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Computational Theory and Mathematics
  • Artificial Intelligence
  • Applied Mathematics

Fingerprint Dive into the research topics of 'Iterative local-global energy minimization for automatic extraction of objects of interest'. Together they form a unique fingerprint.

Cite this