ML Anthology

Multiple Class Segmentation Using a Unified Framework over Mean-Shift Patches

Lin Yang, Peter Meer, David J. Foran
CVPR 2007
doi:10.1109/CVPR.2007.383229 /cvpr/2007/yang2007cvpr-multiple/

Abstract

Object-based segmentation is a challenging topic. Most of the previous algorithms focused on segmenting a single or a small set of objects. In this paper, the multiple class object-based segmentation is achieved using the appearance and bag of keypoints models integrated over mean-shift patches. We also propose a novel affine invariant descriptor to model the spatial relationship of keypoints and apply the Elliptical Fourier Descriptor to describe the global shapes. The algorithm is computationally efficient and has been tested for three real datasets using less training samples. Our algorithm provides better results than other studies reported in the literature.

PDF CVPR Semantic Scholar

Cite

Text

Yang et al. "Multiple Class Segmentation Using a Unified Framework over Mean-Shift Patches." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2007. doi:10.1109/CVPR.2007.383229

Markdown

[Yang et al. "Multiple Class Segmentation Using a Unified Framework over Mean-Shift Patches." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2007.](https://mlanthology.org/cvpr/2007/yang2007cvpr-multiple/) doi:10.1109/CVPR.2007.383229

BibTeX

@inproceedings{yang2007cvpr-multiple,
  title     = {{Multiple Class Segmentation Using a Unified Framework over Mean-Shift Patches}},
  author    = {Yang, Lin and Meer, Peter and Foran, David J.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2007},
  doi       = {10.1109/CVPR.2007.383229},
  url       = {https://mlanthology.org/cvpr/2007/yang2007cvpr-multiple/}
}