High-speed character recognition system based on a complex hierarchical AER architecture

In this paper we briefly summarize the fundamental properties of spikes processing applied to artificial vision systems. This sensing and processing technology is capable of very high speed throughput, because it does not rely on sensing and processing sequences of frames, and because it allows for...

Full description

Saved in:
Bibliographic Details
Main Authors: Perez-Carrasco, J. A., Serrano-Gotarredona, T., Serrano-Gotarredona, C., Acha, B., Linares-Barranco, B.
Format: Conference Proceeding
Language:English
Subjects:
Character recognition
Convolution
Decoding
Feature extraction
Hardware
Kernel
Machine vision
Neurons
Protocols
Retina
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 2153
container_issue
container_start_page 2150
container_title
container_volume
creator Perez-Carrasco, J. A.
Serrano-Gotarredona, T.
Serrano-Gotarredona, C.
Acha, B.
Linares-Barranco, B.
description In this paper we briefly summarize the fundamental properties of spikes processing applied to artificial vision systems. This sensing and processing technology is capable of very high speed throughput, because it does not rely on sensing and processing sequences of frames, and because it allows for complex hierarchically structured cortical-like layers for sophisticated processing. The paper describes briefly cortex-like spiking vision processing principles, and the AER (Address Event Representation) technique used in hardware spiking systems. Afterwards an example application is described, which is a simplification of Fukushima's Neocognitron. Realistic behavioral simulations based on existing AER hardware characteristics, reveal that the simplified neocognitron, although it processes 52 large kernel convolutions, is capable of performing recognition in less than 10μs.
doi_str_mv 10.1109/ISCAS.2008.4541876
format conference_proceeding
fullrecord <record><control><sourceid>proquest_CHZPO</sourceid><recordid>TN_cdi_proquest_miscellaneous_34495929</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>4541876</ieee_id><sourcerecordid>34495929</sourcerecordid><originalsourceid>FETCH-LOGICAL-i206t-3e98a216cb329f220d1a3410ed3b47f7c6f1551268d88fabe068f7adb5be4b743</originalsourceid><addsrcrecordid>eNo1kE1Lw0AYhNePgrH2D-hlT95S93s3x1KqLRQEq-AtbDZvmpWkqbsp2H9vsHUuwzAPcxiE7imZUkqyp9VmPttMGSFmKqSgRqsLdEsFE4IqI-glShiVJqWSySs0ybT577i-RglhmqaCEzZCiSGpEkpycoMmMX6RQUJyJlmCPpd-W6dxD1BiV9tgXQ8BB3Dddud73-1wPMYeWlzYOCBDtth17b6BH1x7CDa42jvb4NniDf-FHlx_CHCHRpVtIkzOPkYfz4v3-TJdv76s5rN16hlRfcohM5ZR5QrOsooxUlLLBSVQ8kLoSjtVUSkpU6Y0prIFEGUqbctCFiAKLfgYPZ5296H7PkDs89ZHB01jd9AdYs6FyGTGsgF8OIEeAPJ98K0Nx_z8LP8FPl9mjQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype><pqid>34495929</pqid></control><display><type>conference_proceeding</type><title>High-speed character recognition system based on a complex hierarchical AER architecture</title><source>IEEE Xplore All Conference Series</source><creator>Perez-Carrasco, J. A. ; Serrano-Gotarredona, T. ; Serrano-Gotarredona, C. ; Acha, B. ; Linares-Barranco, B.</creator><creatorcontrib>Perez-Carrasco, J. A. ; Serrano-Gotarredona, T. ; Serrano-Gotarredona, C. ; Acha, B. ; Linares-Barranco, B.</creatorcontrib><description>In this paper we briefly summarize the fundamental properties of spikes processing applied to artificial vision systems. This sensing and processing technology is capable of very high speed throughput, because it does not rely on sensing and processing sequences of frames, and because it allows for complex hierarchically structured cortical-like layers for sophisticated processing. The paper describes briefly cortex-like spiking vision processing principles, and the AER (Address Event Representation) technique used in hardware spiking systems. Afterwards an example application is described, which is a simplification of Fukushima's Neocognitron. Realistic behavioral simulations based on existing AER hardware characteristics, reveal that the simplified neocognitron, although it processes 52 large kernel convolutions, is capable of performing recognition in less than 10μs.</description><identifier>ISSN: 0271-4302</identifier><identifier>ISBN: 9781424416837</identifier><identifier>ISBN: 1424416833</identifier><identifier>EISSN: 2158-1525</identifier><identifier>EISBN: 1424416841</identifier><identifier>EISBN: 9781424416844</identifier><identifier>DOI: 10.1109/ISCAS.2008.4541876</identifier><identifier>LCCN: 80-646530</identifier><language>eng</language><publisher>IEEE</publisher><subject>Character recognition ; Convolution ; Decoding ; Feature extraction ; Hardware ; Kernel ; Machine vision ; Neurons ; Protocols ; Retina</subject><ispartof>2008 IEEE International Symposium on Circuits and Systems, 2008, p.2150-2153</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/4541876$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,314,780,784,789,790,2056,27922,27923,54553,54918,54930</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/4541876$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Perez-Carrasco, J. A.</creatorcontrib><creatorcontrib>Serrano-Gotarredona, T.</creatorcontrib><creatorcontrib>Serrano-Gotarredona, C.</creatorcontrib><creatorcontrib>Acha, B.</creatorcontrib><creatorcontrib>Linares-Barranco, B.</creatorcontrib><title>High-speed character recognition system based on a complex hierarchical AER architecture</title><title>2008 IEEE International Symposium on Circuits and Systems</title><addtitle>ISCAS</addtitle><description>In this paper we briefly summarize the fundamental properties of spikes processing applied to artificial vision systems. This sensing and processing technology is capable of very high speed throughput, because it does not rely on sensing and processing sequences of frames, and because it allows for complex hierarchically structured cortical-like layers for sophisticated processing. The paper describes briefly cortex-like spiking vision processing principles, and the AER (Address Event Representation) technique used in hardware spiking systems. Afterwards an example application is described, which is a simplification of Fukushima's Neocognitron. Realistic behavioral simulations based on existing AER hardware characteristics, reveal that the simplified neocognitron, although it processes 52 large kernel convolutions, is capable of performing recognition in less than 10μs.</description><subject>Character recognition</subject><subject>Convolution</subject><subject>Decoding</subject><subject>Feature extraction</subject><subject>Hardware</subject><subject>Kernel</subject><subject>Machine vision</subject><subject>Neurons</subject><subject>Protocols</subject><subject>Retina</subject><issn>0271-4302</issn><issn>2158-1525</issn><isbn>9781424416837</isbn><isbn>1424416833</isbn><isbn>1424416841</isbn><isbn>9781424416844</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2008</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNo1kE1Lw0AYhNePgrH2D-hlT95S93s3x1KqLRQEq-AtbDZvmpWkqbsp2H9vsHUuwzAPcxiE7imZUkqyp9VmPttMGSFmKqSgRqsLdEsFE4IqI-glShiVJqWSySs0ybT577i-RglhmqaCEzZCiSGpEkpycoMmMX6RQUJyJlmCPpd-W6dxD1BiV9tgXQ8BB3Dddud73-1wPMYeWlzYOCBDtth17b6BH1x7CDa42jvb4NniDf-FHlx_CHCHRpVtIkzOPkYfz4v3-TJdv76s5rN16hlRfcohM5ZR5QrOsooxUlLLBSVQ8kLoSjtVUSkpU6Y0prIFEGUqbctCFiAKLfgYPZ5296H7PkDs89ZHB01jd9AdYs6FyGTGsgF8OIEeAPJ98K0Nx_z8LP8FPl9mjQ</recordid><startdate>20080101</startdate><enddate>20080101</enddate><creator>Perez-Carrasco, J. A.</creator><creator>Serrano-Gotarredona, T.</creator><creator>Serrano-Gotarredona, C.</creator><creator>Acha, B.</creator><creator>Linares-Barranco, B.</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope></search><sort><creationdate>20080101</creationdate><title>High-speed character recognition system based on a complex hierarchical AER architecture</title><author>Perez-Carrasco, J. A. ; Serrano-Gotarredona, T. ; Serrano-Gotarredona, C. ; Acha, B. ; Linares-Barranco, B.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i206t-3e98a216cb329f220d1a3410ed3b47f7c6f1551268d88fabe068f7adb5be4b743</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2008</creationdate><topic>Character recognition</topic><topic>Convolution</topic><topic>Decoding</topic><topic>Feature extraction</topic><topic>Hardware</topic><topic>Kernel</topic><topic>Machine vision</topic><topic>Neurons</topic><topic>Protocols</topic><topic>Retina</topic><toplevel>online_resources</toplevel><creatorcontrib>Perez-Carrasco, J. A.</creatorcontrib><creatorcontrib>Serrano-Gotarredona, T.</creatorcontrib><creatorcontrib>Serrano-Gotarredona, C.</creatorcontrib><creatorcontrib>Acha, B.</creatorcontrib><creatorcontrib>Linares-Barranco, B.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE/IET Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics &amp; Communications 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></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Perez-Carrasco, J. A.</au><au>Serrano-Gotarredona, T.</au><au>Serrano-Gotarredona, C.</au><au>Acha, B.</au><au>Linares-Barranco, B.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>High-speed character recognition system based on a complex hierarchical AER architecture</atitle><btitle>2008 IEEE International Symposium on Circuits and Systems</btitle><stitle>ISCAS</stitle><date>2008-01-01</date><risdate>2008</risdate><spage>2150</spage><epage>2153</epage><pages>2150-2153</pages><issn>0271-4302</issn><eissn>2158-1525</eissn><isbn>9781424416837</isbn><isbn>1424416833</isbn><eisbn>1424416841</eisbn><eisbn>9781424416844</eisbn><abstract>In this paper we briefly summarize the fundamental properties of spikes processing applied to artificial vision systems. This sensing and processing technology is capable of very high speed throughput, because it does not rely on sensing and processing sequences of frames, and because it allows for complex hierarchically structured cortical-like layers for sophisticated processing. The paper describes briefly cortex-like spiking vision processing principles, and the AER (Address Event Representation) technique used in hardware spiking systems. Afterwards an example application is described, which is a simplification of Fukushima's Neocognitron. Realistic behavioral simulations based on existing AER hardware characteristics, reveal that the simplified neocognitron, although it processes 52 large kernel convolutions, is capable of performing recognition in less than 10μs.</abstract><pub>IEEE</pub><doi>10.1109/ISCAS.2008.4541876</doi><tpages>4</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 0271-4302
ispartof 2008 IEEE International Symposium on Circuits and Systems, 2008, p.2150-2153
issn 0271-4302
2158-1525
language eng
recordid cdi_proquest_miscellaneous_34495929
source IEEE Xplore All Conference Series
subjects Character recognition
Convolution
Decoding
Feature extraction
Hardware
Kernel
Machine vision
Neurons
Protocols
Retina
title High-speed character recognition system based on a complex hierarchical AER architecture
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-14T12%3A42%3A04IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=High-speed%20character%20recognition%20system%20based%20on%20a%20complex%20hierarchical%20AER%20architecture&rft.btitle=2008%20IEEE%20International%20Symposium%20on%20Circuits%20and%20Systems&rft.au=Perez-Carrasco,%20J.%20A.&rft.date=2008-01-01&rft.spage=2150&rft.epage=2153&rft.pages=2150-2153&rft.issn=0271-4302&rft.eissn=2158-1525&rft.isbn=9781424416837&rft.isbn_list=1424416833&rft_id=info:doi/10.1109/ISCAS.2008.4541876&rft.eisbn=1424416841&rft.eisbn_list=9781424416844&rft_dat=%3Cproquest_CHZPO%3E34495929%3C/proquest_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i206t-3e98a216cb329f220d1a3410ed3b47f7c6f1551268d88fabe068f7adb5be4b743%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=34495929&rft_id=info:pmid/&rft_ieee_id=4541876&rfr_iscdi=true