ML Anthology

Connectionist Networks for Feature Indexing and Object Recognition

Clark F. Olson
CVPR 1996 pp. 907-912
doi:10.1109/CVPR.1996.517179 /cvpr/1996/olson1996cvpr-connectionist/

Abstract

Feature indexing techniques are promising for object recognition since they can quickly reduce the set of possible matches for a set of image features. This work exploits another property of such techniques. They have inherently parallel structure and connectionist network formulations are easy to develop. Once indexing has been performed, a voting scheme such as geometric hashing can be used to generate object hypotheses in parallel. We describe a framework for the connectionist implementation of such indexing and recognition techniques. With sufficient processing elements, recognition can be performed in a small number of time steps. The number of processing elements necessary to achieve peak performance and the fan-in/fan-out required for the processing elements is examined. These techniques have been simulated on a conventional architecture with good results.

CVPR Semantic Scholar

Cite

Text

Olson. "Connectionist Networks for Feature Indexing and Object Recognition." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1996. doi:10.1109/CVPR.1996.517179

Markdown

[Olson. "Connectionist Networks for Feature Indexing and Object Recognition." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1996.](https://mlanthology.org/cvpr/1996/olson1996cvpr-connectionist/) doi:10.1109/CVPR.1996.517179

BibTeX

@inproceedings{olson1996cvpr-connectionist,
  title     = {{Connectionist Networks for Feature Indexing and Object Recognition}},
  author    = {Olson, Clark F.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1996},
  pages     = {907-912},
  doi       = {10.1109/CVPR.1996.517179},
  url       = {https://mlanthology.org/cvpr/1996/olson1996cvpr-connectionist/}
}