ML Anthology

Autonomous Recognition: Driven by Ambiguit

Franco Callari, Frank P. Ferrie
CVPR 1996 pp. 701-707
doi:10.1109/CVPR.1996.517149 /cvpr/1996/callari1996cvpr-autonomous/

Abstract

Recognition ambiguity, due to noisy measurements and uncertain object models, can be quantified and actively used by an autonomous agent to efficiently gather new data and improve its information about the environment. In this work an information-based utility measure is used to derive from a learned classification of shape models an efficient data collection strategy, specifically aimed at increasing classification confidence when recognizing uncertain shapes. Promising simulation results are presented and discussed.

CVPR Semantic Scholar

Cite

Text

Callari and Ferrie. "Autonomous Recognition: Driven by Ambiguit." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1996. doi:10.1109/CVPR.1996.517149

Markdown

[Callari and Ferrie. "Autonomous Recognition: Driven by Ambiguit." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1996.](https://mlanthology.org/cvpr/1996/callari1996cvpr-autonomous/) doi:10.1109/CVPR.1996.517149

BibTeX

@inproceedings{callari1996cvpr-autonomous,
  title     = {{Autonomous Recognition: Driven by Ambiguit}},
  author    = {Callari, Franco and Ferrie, Frank P.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1996},
  pages     = {701-707},
  doi       = {10.1109/CVPR.1996.517149},
  url       = {https://mlanthology.org/cvpr/1996/callari1996cvpr-autonomous/}
}