Active Detection and Classsification of Junctions by Foveation with a Head-Eye System Guided by the Scale-Space Primal Sketch
Abstract
We consider how junction detection and classification can be performed in an active visual system. This is to exemplify that feature de-tection and classification in general can be done by both simple and robust methods, if the vision system is allowed to look at the world rather than at prerecorded images. We address issues on how to attract the attention to salient local image structures, as well as on how to characterize those .
Cite
Text
Brunnström et al. "Active Detection and Classsification of Junctions by Foveation with a Head-Eye System Guided by the Scale-Space Primal Sketch." European Conference on Computer Vision, 1992. doi:10.1007/3-540-55426-2_77Markdown
[Brunnström et al. "Active Detection and Classsification of Junctions by Foveation with a Head-Eye System Guided by the Scale-Space Primal Sketch." European Conference on Computer Vision, 1992.](https://mlanthology.org/eccv/1992/brunnstrom1992eccv-active/) doi:10.1007/3-540-55426-2_77BibTeX
@inproceedings{brunnstrom1992eccv-active,
title = {{Active Detection and Classsification of Junctions by Foveation with a Head-Eye System Guided by the Scale-Space Primal Sketch}},
author = {Brunnström, Kjell and Lindeberg, Tony and Eklundh, Jan-Olof},
booktitle = {European Conference on Computer Vision},
year = {1992},
pages = {701-709},
doi = {10.1007/3-540-55426-2_77},
url = {https://mlanthology.org/eccv/1992/brunnstrom1992eccv-active/}
}