Discriminative k metrics and the Chan-Vese model for object detection and segmentation

Arthur Szlam, Guillermo SapiroProceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE 2009 · DOI

Abstract

In this work, a modification of the <i>k</i> <i>q</i>-flats framework for pattern classification introduced in [9] is used for pixelwise object detection. We include a preliminary discussion of augmenting this method is with a Chan-Vese-like geometric regularization.
BibTeX
@inproceedings{szlam2009discriminative,
  author = {Arthur Szlam and Guillermo Sapiro},
  title = {{Discriminative k metrics and the Chan-Vese model for object detection and segmentation}},
  booktitle = {Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE},
  year = {2009},
  doi = {10.1117/12.825800},
}

Loading related content...

Figure