ML Anthology

Random Subwindows for Robust Image Classification

Raphaël Marée, Pierre Geurts, Justus H. Piater, Louis Wehenkel
CVPR 2005 pp. 34-40
doi:10.1109/CVPR.2005.287 /cvpr/2005/maree2005cvpr-random/

Abstract

We present a novel, generic image classification method based on a recent machine learning algorithm (ensembles of extremely randomized decision trees). Images are classified using randomly extracted subwindows that are suitably normalized to yield robustness to certain image transformations. Our method is evaluated on four very different, publicly available datasets (COIL-100, ZuBuD, ETH-80, WANG). Our results show that our automatic approach is generic and robust to illumination, scale, and viewpoint changes. An extension of the method is proposed to improve its robustness with respect to rotation changes.

PDF CVPR Semantic Scholar

Cite

Text

Marée et al. "Random Subwindows for Robust Image Classification." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2005. doi:10.1109/CVPR.2005.287

Markdown

[Marée et al. "Random Subwindows for Robust Image Classification." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2005.](https://mlanthology.org/cvpr/2005/maree2005cvpr-random/) doi:10.1109/CVPR.2005.287

BibTeX

@inproceedings{maree2005cvpr-random,
  title     = {{Random Subwindows for Robust Image Classification}},
  author    = {Marée, Raphaël and Geurts, Pierre and Piater, Justus H. and Wehenkel, Louis},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2005},
  pages     = {34-40},
  doi       = {10.1109/CVPR.2005.287},
  url       = {https://mlanthology.org/cvpr/2005/maree2005cvpr-random/}
}