ML Anthology

Object-Specific Figure-Ground Segregation

Stella X. Yu, Jianbo Shi
CVPR 2003 pp. 39-45
doi:10.1109/CVPR.2003.10006 /cvpr/2003/yu2003cvpr-object/

Abstract

We consider the problem of segmenting an image into foreground and background, with foreground containing solely objects of interest known a priori. We propose an integration model that incorporates both edge detection and object part detection results. It consists of two parallel processes: low-level pixel grouping and high-level patch grouping. We seek a solution that optimizes a joint grouping criterion in a reduced space enforced by grouping correspondence between pixels and patches. Using spectral graph partitioning, we show that a near global optimum can be found by solving a constrained eigenvalue problem. We report promising experimental results on a dataset of 15 objects under clutter and occlusion.

CVPR Semantic Scholar

Cite

Text

Yu and Shi. "Object-Specific Figure-Ground Segregation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2003. doi:10.1109/CVPR.2003.10006

Markdown

[Yu and Shi. "Object-Specific Figure-Ground Segregation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2003.](https://mlanthology.org/cvpr/2003/yu2003cvpr-object/) doi:10.1109/CVPR.2003.10006

BibTeX

@inproceedings{yu2003cvpr-object,
  title     = {{Object-Specific Figure-Ground Segregation}},
  author    = {Yu, Stella X. and Shi, Jianbo},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2003},
  pages     = {39-45},
  doi       = {10.1109/CVPR.2003.10006},
  url       = {https://mlanthology.org/cvpr/2003/yu2003cvpr-object/}
}