Skip to main navigation Skip to search Skip to main content

Local reinforcement learning for object recognition

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Current computer vision systems, whose basic methodology is open-loop or filter type, typically use image segmentation followed by object recognition algorithms. These systems are not robust for most real-world applications. In contrast, the system presented here achieves robust performance by using local reinforcement learning to induce a highly adaptive mapping from input images to segmentation strategies. This is accomplished by using the confidence level of model matching as reinforcement to drive learning. The system is verified through experiments on a large set of real images.

Original languageEnglish
Title of host publicationProceedings - 14th International Conference on Pattern Recognition, ICPR 1998
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages272-274
Number of pages3
ISBN (Print)0818685123, 9780818685125
DOIs
StatePublished - 1998
Event14th International Conference on Pattern Recognition, ICPR 1998 - Brisbane, QLD, Australia
Duration: 16 Aug 199820 Aug 1998

Publication series

NameProceedings - International Conference on Pattern Recognition
Volume1
ISSN (Print)1051-4651

Conference

Conference14th International Conference on Pattern Recognition, ICPR 1998
Country/TerritoryAustralia
CityBrisbane, QLD
Period16/08/9820/08/98

Fingerprint

Dive into the research topics of 'Local reinforcement learning for object recognition'. Together they form a unique fingerprint.

Cite this