ML Anthology

Discriminative Training for Object Recognition Using Image Patches

Thomas Deselaers, Daniel Keysers, Hermann Ney
CVPR 2005 pp. 157-162
doi:10.1109/CVPR.2005.134 /cvpr/2005/deselaers2005cvpr-discriminative/

Abstract

We present a method for automatically learning discriminative image patches for the recognition of given object classes. The approach applies discriminative training of log-linear models to image patch histograms. We show that it works well on three tasks and performs significantly better than other methods using the same features. For example, the method decides that patches containing an eye are most important for distinguishing face from background images. The recognition performance is very competitive with error rates presented in other publications. In particular, a new best error rate for the Caltech motorbikes data of 1.5% is achieved.

CVPR Semantic Scholar

Cite

Text

Deselaers et al. "Discriminative Training for Object Recognition Using Image Patches." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2005. doi:10.1109/CVPR.2005.134

Markdown

[Deselaers et al. "Discriminative Training for Object Recognition Using Image Patches." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2005.](https://mlanthology.org/cvpr/2005/deselaers2005cvpr-discriminative/) doi:10.1109/CVPR.2005.134

BibTeX

@inproceedings{deselaers2005cvpr-discriminative,
  title     = {{Discriminative Training for Object Recognition Using Image Patches}},
  author    = {Deselaers, Thomas and Keysers, Daniel and Ney, Hermann},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2005},
  pages     = {157-162},
  doi       = {10.1109/CVPR.2005.134},
  url       = {https://mlanthology.org/cvpr/2005/deselaers2005cvpr-discriminative/}
}