ML Anthology

Object Recognition Using Multidimensional Receptive Field Histograms

Bernt Schiele, James L. Crowley
ECCV 1996 pp. 610-619
doi:10.1007/BFB0015571 /eccv/1996/schiele1996eccv-object/

Abstract

This paper presents a technique to determine the identity of objects in a scene using histograms of the responses of a vector of local linear neighborhood operators (receptive fields). This technique can be used to determine the most probable objects in a scene, independent of the object's position, image-plane orientation and scale. In this paper we describe the mathematical foundations of the technique and present the results of experiments which compare robustness and recognition rates for different local neighborhood operators and histogram similarity measurements.

PDF ECCV Semantic Scholar

Cite

Text

Schiele and Crowley. "Object Recognition Using Multidimensional Receptive Field Histograms." European Conference on Computer Vision, 1996. doi:10.1007/BFB0015571

Markdown

[Schiele and Crowley. "Object Recognition Using Multidimensional Receptive Field Histograms." European Conference on Computer Vision, 1996.](https://mlanthology.org/eccv/1996/schiele1996eccv-object/) doi:10.1007/BFB0015571

BibTeX

@inproceedings{schiele1996eccv-object,
  title     = {{Object Recognition Using Multidimensional Receptive Field Histograms}},
  author    = {Schiele, Bernt and Crowley, James L.},
  booktitle = {European Conference on Computer Vision},
  year      = {1996},
  pages     = {610-619},
  doi       = {10.1007/BFB0015571},
  url       = {https://mlanthology.org/eccv/1996/schiele1996eccv-object/}
}