ML Anthology

OTC: A Novel Local Descriptor for Scene Classification

Ran Margolin, Lihi Zelnik-Manor, Ayellet Tal
ECCV 2014 pp. 377-391
doi:10.1007/978-3-319-10584-0_25 /eccv/2014/margolin2014eccv-otc/

Abstract

Scene classification is the task of determining the scene type in which a photograph was taken. In this paper we present a novel local descriptor suited for such a task: Oriented Texture Curves (OTC). Our descriptor captures the texture of a patch along multiple orientations, while maintaining robustness to illumination changes, geometric distortions and local contrast differences. We show that our descriptor outperforms all state-of-the-art descriptors for scene classification algorithms on the most extensive scene classification benchmark to-date.

PDF ECCV Semantic Scholar

Cite

Text

Margolin et al. "OTC: A Novel Local Descriptor for Scene Classification." European Conference on Computer Vision, 2014. doi:10.1007/978-3-319-10584-0_25

Markdown

[Margolin et al. "OTC: A Novel Local Descriptor for Scene Classification." European Conference on Computer Vision, 2014.](https://mlanthology.org/eccv/2014/margolin2014eccv-otc/) doi:10.1007/978-3-319-10584-0_25

BibTeX

@inproceedings{margolin2014eccv-otc,
  title     = {{OTC: A Novel Local Descriptor for Scene Classification}},
  author    = {Margolin, Ran and Zelnik-Manor, Lihi and Tal, Ayellet},
  booktitle = {European Conference on Computer Vision},
  year      = {2014},
  pages     = {377-391},
  doi       = {10.1007/978-3-319-10584-0_25},
  url       = {https://mlanthology.org/eccv/2014/margolin2014eccv-otc/}
}