ML Anthology

Learning Good Features for Active Shape Models

Nuria Brunet, Francisco Perez, Fernando De la Torre
ICCVW 2009 pp. 206-211
doi:10.1109/ICCVW.2009.5457699 /iccvw/2009/brunet2009iccvw-learning/

Abstract

Active Shape Models (ASMs) are commonly used to model the appearance and shape variation of objects in images. This paper proposes two strategies to improve speed and accuracy in ASMs fitting. First, we define a new criterion to select landmarks that have good generalization properties. Second, for each landmark we learn a subspace with improved facial feature response effectively avoiding local minima in the ASM fitting. Experimental results show the effectiveness and robustness of the approach.

PDF ICCVW Semantic Scholar

Cite

Text

Brunet et al. "Learning Good Features for Active Shape Models." IEEE/CVF International Conference on Computer Vision Workshops, 2009. doi:10.1109/ICCVW.2009.5457699

Markdown

[Brunet et al. "Learning Good Features for Active Shape Models." IEEE/CVF International Conference on Computer Vision Workshops, 2009.](https://mlanthology.org/iccvw/2009/brunet2009iccvw-learning/) doi:10.1109/ICCVW.2009.5457699

BibTeX

@inproceedings{brunet2009iccvw-learning,
  title     = {{Learning Good Features for Active Shape Models}},
  author    = {Brunet, Nuria and Perez, Francisco and De la Torre, Fernando},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2009},
  pages     = {206-211},
  doi       = {10.1109/ICCVW.2009.5457699},
  url       = {https://mlanthology.org/iccvw/2009/brunet2009iccvw-learning/}
}