Active Perception Using DAM and Estimation Techniques
Abstract
The Distributed Associative Memory (DAM) has been described previously as a powerful method for pattern recognition. We show that it also can be used for preattentive and attentive vision. The basis for the preattentive system is that both the visual input features as well as the memory are arranged in a pyramid. This enables the system to provide fast preselection of regions of visual interest. The selected areas of interest are used in an attentive recognition stage, where the memory and the features work at full resolution. The reason for application of DAM is based on a statistical theory of rejection. The availability of a reject option in the DAM is the prerequisite for novelty detection and preattentive selection. We demonstrate the performance of the method on two diverse applications.
Cite
Text
Pölzleitner and Wechsler. "Active Perception Using DAM and Estimation Techniques." European Conference on Computer Vision, 1992. doi:10.1007/3-540-55426-2_56Markdown
[Pölzleitner and Wechsler. "Active Perception Using DAM and Estimation Techniques." European Conference on Computer Vision, 1992.](https://mlanthology.org/eccv/1992/polzleitner1992eccv-active/) doi:10.1007/3-540-55426-2_56BibTeX
@inproceedings{polzleitner1992eccv-active,
title = {{Active Perception Using DAM and Estimation Techniques}},
author = {Pölzleitner, Wolfgang and Wechsler, Harry},
booktitle = {European Conference on Computer Vision},
year = {1992},
pages = {511-515},
doi = {10.1007/3-540-55426-2_56},
url = {https://mlanthology.org/eccv/1992/polzleitner1992eccv-active/}
}