Iterative Local-Global Energy Minimization for Automatic Extraction of Objects of Interest

Author

Gang Hua ; Zicheng Liu ; Zhengyou Zhang ; Ying Wu

Author_Institution

Microsoft Live Labs, One Microsoft Way, Redmond, WA

Volume

28

Issue

10

fYear

2006

Firstpage

1701

Lastpage

1706

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

Keywords

feature extraction; iterative methods; object detection; automatic object extraction; global likelihood potential; global-local variational energy; iterative local-global energy minimization; Active contours; Finite difference methods; Image analysis; Image segmentation; Level set; Object recognition; Painting; Pixel; Robustness; Semisupervised learning; Variational energy; level set; semisupervised learning.; Algorithms; Artificial Intelligence; Image Enhancement; Image Interpretation, Computer-Assisted; Information Storage and Retrieval; Pattern Recognition, Automated; Reproducibility of Results; Sensitivity and Specificity;

fLanguage

English

Journal_Title

Pattern Analysis and Machine Intelligence, IEEE Transactions on

Publisher

ieee

ISSN

0162-8828

Type

jour

DOI

10.1109/TPAMI.2006.209

Filename

1677525