Learning to Detect Natural Image Boundaries Using Brightness and Texture

David R. Martin, Charless C. Fowlkes, Jitendra Malik

NeurIPS 2002 pp. 1279-1286

/neurips/2002/martin2002neurips-learning/

Abstract

The goal of this work is to accurately detect and localize boundaries in natural scenes using local image measurements. We formulate features that respond to characteristic changes in brightness and texture associated with natural boundaries. In order to combine the information from these features in an optimal way, a classiﬁer is trained using human labeled images as ground truth. We present precision-recall curves showing that the resulting detector outperforms existing approaches.

PDF NeurIPS Semantic Scholar

Cite

Text

Martin et al. "Learning to Detect Natural Image Boundaries Using Brightness and Texture." Neural Information Processing Systems, 2002.

Markdown

[Martin et al. "Learning to Detect Natural Image Boundaries Using Brightness and Texture." Neural Information Processing Systems, 2002.](https://mlanthology.org/neurips/2002/martin2002neurips-learning/)

BibTeX

@inproceedings{martin2002neurips-learning,
  title     = {{Learning to Detect Natural Image Boundaries Using Brightness and Texture}},
  author    = {Martin, David R. and Fowlkes, Charless C. and Malik, Jitendra},
  booktitle = {Neural Information Processing Systems},
  year      = {2002},
  pages     = {1279-1286},
  url       = {https://mlanthology.org/neurips/2002/martin2002neurips-learning/}
}