ML Anthology

Sparse Representations for Image Decomposition with Occlusions

Michael J. Donahue, Davi Geiger, Tyng-Luh Liu, Robert A. Hummel
CVPR 1996 pp. 7-12
doi:10.1109/CVPR.1996.517046 /cvpr/1996/donahue1996cvpr-sparse/

Abstract

We study the problem of how to detect "interesting objects" appeared in a given image, I. Our approach is to treat it as a function approximation problem based on an over-redundant basis, and also account for occlusions, where the basis superposition principle is no longer valid. Since the basis (a library of image templates) is over-redundant, there are infinitely many ways to decompose I. We are motivated to select a sparse/compact representation of I, and to account for occlusions and noise. We then study a greedy and iterative "weighted L/sup p/ Matching Pursuit" strategy, with O<p<1. We use an L/sup p/ result to compute a solution, select the best template, at each stage of the pursuit.

CVPR Semantic Scholar

Cite

Text

Donahue et al. "Sparse Representations for Image Decomposition with Occlusions." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1996. doi:10.1109/CVPR.1996.517046

Markdown

[Donahue et al. "Sparse Representations for Image Decomposition with Occlusions." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1996.](https://mlanthology.org/cvpr/1996/donahue1996cvpr-sparse/) doi:10.1109/CVPR.1996.517046

BibTeX

@inproceedings{donahue1996cvpr-sparse,
  title     = {{Sparse Representations for Image Decomposition with Occlusions}},
  author    = {Donahue, Michael J. and Geiger, Davi and Liu, Tyng-Luh and Hummel, Robert A.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1996},
  pages     = {7-12},
  doi       = {10.1109/CVPR.1996.517046},
  url       = {https://mlanthology.org/cvpr/1996/donahue1996cvpr-sparse/}
}