Discriminative Learning for Deformable Shape Segmentation: A Comparative Study

Abstract

We present a comparative study on how to use discriminative learning methods such as classification, regression, and ranking to address deformable shape segmentation. Traditional generative models and energy minimization methods suffer from local minima. By casting the segmentation into a discriminative framework, the target fitting function can be steered to possess a desired shape for ease of optimization yet better characterize the relationship between shape and appearance. To address the high-dimensional learning challenge present in the learning framework, we use a multi-level approach to learning discriminative models. Our experimental results on left ventricle segmentation from ultrasound images and facial feature point localization demonstrate that the discriminative models outperform generative models and energy minimization methods by a large margin.

Cite

Text

Zhang et al. "Discriminative Learning for Deformable Shape Segmentation: A Comparative Study." European Conference on Computer Vision, 2008. doi:10.1007/978-3-540-88682-2_54

Markdown

[Zhang et al. "Discriminative Learning for Deformable Shape Segmentation: A Comparative Study." European Conference on Computer Vision, 2008.](https://mlanthology.org/eccv/2008/zhang2008eccv-discriminative-a/) doi:10.1007/978-3-540-88682-2_54

BibTeX

@inproceedings{zhang2008eccv-discriminative-a,
  title     = {{Discriminative Learning for Deformable Shape Segmentation: A Comparative Study}},
  author    = {Zhang, Jingdan and Zhou, Shaohua Kevin and Comaniciu, Dorin and McMillan, Leonard},
  booktitle = {European Conference on Computer Vision},
  year      = {2008},
  pages     = {711-724},
  doi       = {10.1007/978-3-540-88682-2_54},
  url       = {https://mlanthology.org/eccv/2008/zhang2008eccv-discriminative-a/}
}