Edge Flow: A Framework of Boundary Detection and Image Segmentation

CVPR 1997 pp. 744-749

doi:10.1109/CVPR.1997.609409 /cvpr/1997/ma1997cvpr-edge/

Abstract

A novel boundary detection scheme based on "edge flow" is proposed in this paper. This scheme utilizes a predictive coding model to identify the direction of change in color and texture at each image location at a given scale, and constructs an edge flow vector. By iteratively propagating the edge flow, the boundaries can be detected at image locations which encounter two opposite directions of flow in the stable state. A user defined image scale is the only significant control parameter that is needed by the algorithm. The scheme facilitates integration of color and texture into a single framework for boundary detection.

CVPR Semantic Scholar

Cite

Text

Ma and Manjunath. "Edge Flow: A Framework of Boundary Detection and Image Segmentation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1997. doi:10.1109/CVPR.1997.609409

Markdown

[Ma and Manjunath. "Edge Flow: A Framework of Boundary Detection and Image Segmentation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1997.](https://mlanthology.org/cvpr/1997/ma1997cvpr-edge/) doi:10.1109/CVPR.1997.609409

BibTeX

@inproceedings{ma1997cvpr-edge,
  title     = {{Edge Flow: A Framework of Boundary Detection and Image Segmentation}},
  author    = {Ma, Wei-Ying and Manjunath, B. S.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1997},
  pages     = {744-749},
  doi       = {10.1109/CVPR.1997.609409},
  url       = {https://mlanthology.org/cvpr/1997/ma1997cvpr-edge/}
}