Integrating recognition paradigms in a multiple-path architecture

DOI10.1007/3-540-44732-6_21MaRDI QIDQ2763422zbMATH OpenFDO

Authors Gerhard Sagerer, Christian Bauckhage, Gunther Heidemann, Franz Kummert, Edward L. Braun

Publication date 15 January 2002

Published in Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL http://link.springer.de/link/service/series/0558/bibs/2013/20130202

zbMATH Keywords

architecture, votinglocalizationobject recognitionvarious classifiers

Mathematics Subject Classification ID

Pattern recognition, speech recognition (68T10) Computing methodologies and applications (68U99)

Review text

Four decades of intensive research in computer vision have lead to numerous computational paradigms. This fact is comprehensible since problems like object recognition or scene descriptions are of high complexity, have different aspects and can be attacked by processing various features. In this paper we propose an architecture that combines the advantages of different paradigms in pattern recognition. Voting and Bayesian networks provide a computational framework to integrate approaches to knowledge based and probabilistic reasoning as well as neural computations. For the entire collection see [Zbl 0977.68799].

Recommendations

• scientific article; zbMATH DE number 978198
• scientific article; zbMATH DE number 4119685
• scientific article; zbMATH DE number 1860779
• scientific article; zbMATH DE number 4060761
• Parallel Integration of Vision Modules

Cited in

(3)

• Integrated architectures for machine learning
• scientific article; zbMATH DE number 5592466 (Why is no real title available?)
• scientific article; zbMATH DE number 3253169 (Why is no real title available?)

This page was built for publication: Integrating recognition paradigms in a multiple-path architecture

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2763422)