Towards Fast and Accurate Segmentation

CVPR 2013

doi:10.1109/CVPR.2013.250 /cvpr/2013/taylor2013cvpr-fast/

Abstract

In this paper we explore approaches to accelerating segmentation and edge detection algorithms based on the gPb framework. The paper characterizes the performance of a simple but effective edge detection scheme which can be computed rapidly and offers performance that is competitive with the pB detector. The paper also describes an approach for computing a reduced order normalized cut that captures the essential features of the original problem but can be computed in less than half a second on a standard computing platform.

PDF CVPR Semantic Scholar

Cite

Text

Taylor. "Towards Fast and Accurate Segmentation." Conference on Computer Vision and Pattern Recognition, 2013. doi:10.1109/CVPR.2013.250

Markdown

[Taylor. "Towards Fast and Accurate Segmentation." Conference on Computer Vision and Pattern Recognition, 2013.](https://mlanthology.org/cvpr/2013/taylor2013cvpr-fast/) doi:10.1109/CVPR.2013.250

BibTeX

@inproceedings{taylor2013cvpr-fast,
  title     = {{Towards Fast and Accurate Segmentation}},
  author    = {Taylor, Camillo J.},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2013},
  doi       = {10.1109/CVPR.2013.250},
  url       = {https://mlanthology.org/cvpr/2013/taylor2013cvpr-fast/}
}