Half-integrality based algorithms for cosegmentation of images

We study the cosegmentation problem where the objective is to segment the same object (i.e., region) from a pair of images. The segmentation for each image can be cast using a partitioning/segmentation function with an additional constraint that seeks to make the histograms of the segmented regions...

Full description

Saved in:
Bibliographic Details
Published in2009 IEEE Conference on Computer Vision and Pattern Recognition pp. 2028 - 2035
Main Authors Mukherjee, Lopamudra, Singh, Vikas, Dyer, Charles R.
Format Conference Proceeding Journal Article
LanguageEnglish
Published United States IEEE 01.01.2009
Subjects
Biomedical imaging
Brain
Computer science
Computer vision
Histograms
Image segmentation
Markov random fields
Mathematics
Pathology
Videos
Online AccessGet full text

Cover

More Information
Summary:We study the cosegmentation problem where the objective is to segment the same object (i.e., region) from a pair of images. The segmentation for each image can be cast using a partitioning/segmentation function with an additional constraint that seeks to make the histograms of the segmented regions (based on intensity and texture features) similar. Using Markov random field (MRF) energy terms for the simultaneous segmentation of the images together with histogram consistency requirements using the squared L 2 (rather than L 1 ) distance, after linearization and adjustments, yields an optimization model with some interesting combinatorial properties. We discuss these properties which are closely related to certain relaxation strategies recently introduced in computer vision. Finally, we show experimental results of the proposed approach.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISBN:1424439922
9781424439928
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2009.5206652