ML Anthology

Image Segmentation Using Local Variation

Pedro F. Felzenszwalb, Daniel P. Huttenlocher
CVPR 1998 pp. 98-104
doi:10.1109/CVPR.1998.698594 /cvpr/1998/felzenszwalb1998cvpr-image/

Abstract

We present a new graph-theoretic approach to the problem of image segmentation. Our method uses local criteria and yet produces results that reflect global properties of the image. We develop a framework that provides specific definitions of what it means for an image to be under- or over-segmented. We then present an efficient algorithm for computing a segmentation that is neither under- nor over-segmented according to these definitions. Our segmentation criterion is based on intensity differences between neighboring pixels. An important characteristic of the approach is that it is able to preserve detail in low-variability regions while ignoring detail in high-variability regions, which we illustrate with several examples on both real and synthetic images.

CVPR Semantic Scholar

Cite

Text

Felzenszwalb and Huttenlocher. "Image Segmentation Using Local Variation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1998. doi:10.1109/CVPR.1998.698594

Markdown

[Felzenszwalb and Huttenlocher. "Image Segmentation Using Local Variation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1998.](https://mlanthology.org/cvpr/1998/felzenszwalb1998cvpr-image/) doi:10.1109/CVPR.1998.698594

BibTeX

@inproceedings{felzenszwalb1998cvpr-image,
  title     = {{Image Segmentation Using Local Variation}},
  author    = {Felzenszwalb, Pedro F. and Huttenlocher, Daniel P.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1998},
  pages     = {98-104},
  doi       = {10.1109/CVPR.1998.698594},
  url       = {https://mlanthology.org/cvpr/1998/felzenszwalb1998cvpr-image/}
}