ML Anthology

Quantitative Evaluation of a Novel Image Segmentation Algorithm

Francisco J. Estrada, Allan D. Jepson
CVPR 2005 pp. 1132-1139
doi:10.1109/CVPR.2005.284 /cvpr/2005/estrada2005cvpr-quantitative/

Abstract

We present a quantitative evaluation of SE-MinCut, a novel segmentation algorithm based on spectral embedding and minimum cut. We use human segmentations from the Berkeley segmentation database as ground truth and propose suitable measures to evaluate segmentation quality. With these measures we generate precision/recall curves for SE-MinCut and three of the leading segmentation algorithms: mean-shift, normalized Cuts, and the local variation algorithm. These curves characterize the performance of each algorithm over a range of input parameters. We compare the precision/recall curves for the four algorithms and show segmented images that support the conclusions obtained from the quantitative evaluation.

PDF CVPR Semantic Scholar

Cite

Text

Estrada and Jepson. "Quantitative Evaluation of a Novel Image Segmentation Algorithm." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2005. doi:10.1109/CVPR.2005.284

Markdown

[Estrada and Jepson. "Quantitative Evaluation of a Novel Image Segmentation Algorithm." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2005.](https://mlanthology.org/cvpr/2005/estrada2005cvpr-quantitative/) doi:10.1109/CVPR.2005.284

BibTeX

@inproceedings{estrada2005cvpr-quantitative,
  title     = {{Quantitative Evaluation of a Novel Image Segmentation Algorithm}},
  author    = {Estrada, Francisco J. and Jepson, Allan D.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2005},
  pages     = {1132-1139},
  doi       = {10.1109/CVPR.2005.284},
  url       = {https://mlanthology.org/cvpr/2005/estrada2005cvpr-quantitative/}
}