Half-Integrality Based Algorithms for Cosegmentation of Images
Abstract
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.
Cite
Text
Mukherjee et al. "Half-Integrality Based Algorithms for Cosegmentation of Images." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2009. doi:10.1109/CVPR.2009.5206652Markdown
[Mukherjee et al. "Half-Integrality Based Algorithms for Cosegmentation of Images." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2009.](https://mlanthology.org/cvpr/2009/mukherjee2009cvpr-half/) doi:10.1109/CVPR.2009.5206652BibTeX
@inproceedings{mukherjee2009cvpr-half,
title = {{Half-Integrality Based Algorithms for Cosegmentation of Images}},
author = {Mukherjee, Lopamudra and Singh, Vikas and Dyer, Charles R.},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2009},
pages = {2028-2035},
doi = {10.1109/CVPR.2009.5206652},
url = {https://mlanthology.org/cvpr/2009/mukherjee2009cvpr-half/}
}