A practical use of cellular neural networks: the stereo-vision problem as an optimisation

A variational way of deriving the relevant parameters of a cellular neural network (CNN) is introduced. The approach exploits the CNN spontaneous internal-energy decrease and is applicable when a given problem can be expressed in terms of an optimisation task. The presented approach is fully mathema...

Full description

Saved in:
Bibliographic Details
Published in:Machine vision and applications 2000-02, Vol.11 (5), p.242-251
Main Authors: Taraglio, Sergio, Zanela, Andrea
Format: Article
Language:English
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c266t-1ac91635d4b29313dbe7e990ed6f824bc0217cb8bcd7416625d82bac75def76e3
cites
container_end_page 251
container_issue 5
container_start_page 242
container_title Machine vision and applications
container_volume 11
creator Taraglio, Sergio
Zanela, Andrea
description A variational way of deriving the relevant parameters of a cellular neural network (CNN) is introduced. The approach exploits the CNN spontaneous internal-energy decrease and is applicable when a given problem can be expressed in terms of an optimisation task. The presented approach is fully mathematical as compared with the typical heuristic search for the correct parameters in the literature on CNNs. This method is practically employed in recovering information on the three-dimensional structure of the environment, through the stereo vision problem. A CNN able to find the conjugate points in a stereogram is fully derived in the proposed framework. Results of computer simulations on several test cases are provided.
doi_str_mv 10.1007/s001380050107
format article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_27656441</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>27656441</sourcerecordid><originalsourceid>FETCH-LOGICAL-c266t-1ac91635d4b29313dbe7e990ed6f824bc0217cb8bcd7416625d82bac75def76e3</originalsourceid><addsrcrecordid>eNpVULtOxDAQtBBIHAclvSu6wPoRO6Y7nXhJJ9FAQRXZzkYEcvFhOyD-HqOjoZrVzOxqdgg5Z3DJAPRVAmCiAaiBgT4gCyYFr5hW5pAswJS5AcOPyUlKbwAgtZYL8rKiu2h9Hrwd6ZyQhp56HMd5tJFOOMdCT5i_QnxP1zS_Ik0ZI4bqc0hDmMpycCNuqU3UTjTs8rAdks1FOiVHvR0Tnv3hkjzf3jyt76vN493DerWpPFcqV8x6w5SoO-m4EUx0DjUaA9ipvuHSeeBMe9c432nJlOJ113Bnva477LVCsSQX-7slyseMKbclwe8LdsIwp5ZrVSspWTFWe6OPIaWIfbuLw9bG75ZB-1tg-69A8QMmv2QC</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>27656441</pqid></control><display><type>article</type><title>A practical use of cellular neural networks: the stereo-vision problem as an optimisation</title><source>Springer Link</source><creator>Taraglio, Sergio ; Zanela, Andrea</creator><creatorcontrib>Taraglio, Sergio ; Zanela, Andrea</creatorcontrib><description>A variational way of deriving the relevant parameters of a cellular neural network (CNN) is introduced. The approach exploits the CNN spontaneous internal-energy decrease and is applicable when a given problem can be expressed in terms of an optimisation task. The presented approach is fully mathematical as compared with the typical heuristic search for the correct parameters in the literature on CNNs. This method is practically employed in recovering information on the three-dimensional structure of the environment, through the stereo vision problem. A CNN able to find the conjugate points in a stereogram is fully derived in the proposed framework. Results of computer simulations on several test cases are provided.</description><identifier>ISSN: 0932-8092</identifier><identifier>EISSN: 1432-1769</identifier><identifier>DOI: 10.1007/s001380050107</identifier><language>eng</language><ispartof>Machine vision and applications, 2000-02, Vol.11 (5), p.242-251</ispartof><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c266t-1ac91635d4b29313dbe7e990ed6f824bc0217cb8bcd7416625d82bac75def76e3</citedby></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids></links><search><creatorcontrib>Taraglio, Sergio</creatorcontrib><creatorcontrib>Zanela, Andrea</creatorcontrib><title>A practical use of cellular neural networks: the stereo-vision problem as an optimisation</title><title>Machine vision and applications</title><description>A variational way of deriving the relevant parameters of a cellular neural network (CNN) is introduced. The approach exploits the CNN spontaneous internal-energy decrease and is applicable when a given problem can be expressed in terms of an optimisation task. The presented approach is fully mathematical as compared with the typical heuristic search for the correct parameters in the literature on CNNs. This method is practically employed in recovering information on the three-dimensional structure of the environment, through the stereo vision problem. A CNN able to find the conjugate points in a stereogram is fully derived in the proposed framework. Results of computer simulations on several test cases are provided.</description><issn>0932-8092</issn><issn>1432-1769</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2000</creationdate><recordtype>article</recordtype><recordid>eNpVULtOxDAQtBBIHAclvSu6wPoRO6Y7nXhJJ9FAQRXZzkYEcvFhOyD-HqOjoZrVzOxqdgg5Z3DJAPRVAmCiAaiBgT4gCyYFr5hW5pAswJS5AcOPyUlKbwAgtZYL8rKiu2h9Hrwd6ZyQhp56HMd5tJFOOMdCT5i_QnxP1zS_Ik0ZI4bqc0hDmMpycCNuqU3UTjTs8rAdks1FOiVHvR0Tnv3hkjzf3jyt76vN493DerWpPFcqV8x6w5SoO-m4EUx0DjUaA9ipvuHSeeBMe9c432nJlOJ113Bnva477LVCsSQX-7slyseMKbclwe8LdsIwp5ZrVSspWTFWe6OPIaWIfbuLw9bG75ZB-1tg-69A8QMmv2QC</recordid><startdate>20000201</startdate><enddate>20000201</enddate><creator>Taraglio, Sergio</creator><creator>Zanela, Andrea</creator><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope></search><sort><creationdate>20000201</creationdate><title>A practical use of cellular neural networks: the stereo-vision problem as an optimisation</title><author>Taraglio, Sergio ; Zanela, Andrea</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c266t-1ac91635d4b29313dbe7e990ed6f824bc0217cb8bcd7416625d82bac75def76e3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2000</creationdate><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Taraglio, Sergio</creatorcontrib><creatorcontrib>Zanela, Andrea</creatorcontrib><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>Machine vision and applications</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Taraglio, Sergio</au><au>Zanela, Andrea</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A practical use of cellular neural networks: the stereo-vision problem as an optimisation</atitle><jtitle>Machine vision and applications</jtitle><date>2000-02-01</date><risdate>2000</risdate><volume>11</volume><issue>5</issue><spage>242</spage><epage>251</epage><pages>242-251</pages><issn>0932-8092</issn><eissn>1432-1769</eissn><abstract>A variational way of deriving the relevant parameters of a cellular neural network (CNN) is introduced. The approach exploits the CNN spontaneous internal-energy decrease and is applicable when a given problem can be expressed in terms of an optimisation task. The presented approach is fully mathematical as compared with the typical heuristic search for the correct parameters in the literature on CNNs. This method is practically employed in recovering information on the three-dimensional structure of the environment, through the stereo vision problem. A CNN able to find the conjugate points in a stereogram is fully derived in the proposed framework. Results of computer simulations on several test cases are provided.</abstract><doi>10.1007/s001380050107</doi><tpages>10</tpages></addata></record>
fulltext fulltext
identifier ISSN: 0932-8092
ispartof Machine vision and applications, 2000-02, Vol.11 (5), p.242-251
issn 0932-8092
1432-1769
language eng
recordid cdi_proquest_miscellaneous_27656441
source Springer Link
title A practical use of cellular neural networks: the stereo-vision problem as an optimisation
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T11%3A02%3A03IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20practical%20use%20of%20cellular%20neural%20networks:%20the%20stereo-vision%20problem%20as%20an%20optimisation&rft.jtitle=Machine%20vision%20and%20applications&rft.au=Taraglio,%20Sergio&rft.date=2000-02-01&rft.volume=11&rft.issue=5&rft.spage=242&rft.epage=251&rft.pages=242-251&rft.issn=0932-8092&rft.eissn=1432-1769&rft_id=info:doi/10.1007/s001380050107&rft_dat=%3Cproquest_cross%3E27656441%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c266t-1ac91635d4b29313dbe7e990ed6f824bc0217cb8bcd7416625d82bac75def76e3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=27656441&rft_id=info:pmid/&rfr_iscdi=true