Foreground-Background Separation by Feed-forward Neural Networks in Old Manuscripts
Artificial Neural Networks (ANNs) are widely used techniques in image processing and pattern recognition. Despite of their power in classification tasks, for pattern recognition, they show limited applicability in the earlier stages such as the foreground-background separation (FBS). In this paper a...
Gespeichert in:
| Veröffentlicht in: | Informatica (Ljubljana) 2014-12, Vol.38 (4), p.329-329 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 329 |
|---|---|
| container_issue | 4 |
| container_start_page | 329 |
| container_title | Informatica (Ljubljana) |
| container_volume | 38 |
| creator | Kefali, Abderrahmane Sari, Toufik Bahi, Halima |
| description | Artificial Neural Networks (ANNs) are widely used techniques in image processing and pattern recognition. Despite of their power in classification tasks, for pattern recognition, they show limited applicability in the earlier stages such as the foreground-background separation (FBS). In this paper a novel FBS technique based on ANN is applied on old documents with a variety of degradations. The idea is to train the ANN on a set of pairs of original images and their respective ideal black and white ones relying on global and local information. We ran several experiments on benchmark and synthetic data and we obtained better results than state-of-the art methods. |
| format | Article |
| fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_miscellaneous_1709176009</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1709176009</sourcerecordid><originalsourceid>FETCH-LOGICAL-p249t-f89274aeb15313493e3b4f7d5def08a79cfa3e6925483b6998b1d9a7f2ec8b1d3</originalsourceid><addsrcrecordid>eNqFj0FLwzAYhoMoOKf_IeDFSyBpkibfUYdTYbrD9DzS5ot0q01NWob_3g49efH0vIeHB94TMhNWKyatEadkxqXmTGsoz8lFzjvOlRS2mJHNMiZ8T3HsPLtz9f5n0g32LrmhiR2tvugS0bMQ08ElT19wTK6dMBxi2mfadHTdevrsujHXqemHfEnOgmszXv1yTt6W96-LR7ZaPzwtblesLxQMLFgojHJYCS2FVCBRVioYrz0Gbp2BOjiJJRRaWVmVALYSHpwJBdbHKefk5qfbp_g5Yh62H02usW1dh3HMW2E4CFNyDv-r5dTnWqujev1H3cUxddORydIcDFjJ5TeKTWlE</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1650979830</pqid></control><display><type>article</type><title>Foreground-Background Separation by Feed-forward Neural Networks in Old Manuscripts</title><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><creator>Kefali, Abderrahmane ; Sari, Toufik ; Bahi, Halima</creator><creatorcontrib>Kefali, Abderrahmane ; Sari, Toufik ; Bahi, Halima</creatorcontrib><description>Artificial Neural Networks (ANNs) are widely used techniques in image processing and pattern recognition. Despite of their power in classification tasks, for pattern recognition, they show limited applicability in the earlier stages such as the foreground-background separation (FBS). In this paper a novel FBS technique based on ANN is applied on old documents with a variety of degradations. The idea is to train the ANN on a set of pairs of original images and their respective ideal black and white ones relying on global and local information. We ran several experiments on benchmark and synthetic data and we obtained better results than state-of-the art methods.</description><identifier>ISSN: 0350-5596</identifier><identifier>EISSN: 1854-3871</identifier><language>eng</language><publisher>Ljubljana: Slovenian Society Informatika / Slovensko drustvo Informatika</publisher><subject>Benchmarking ; Classification ; Learning theory ; Neural networks ; Pattern recognition ; Separation ; Tasks ; Trains</subject><ispartof>Informatica (Ljubljana), 2014-12, Vol.38 (4), p.329-329</ispartof><rights>Copyright Slovenian Society Informatika / Slovensko drustvo Informatika Dec 2014</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,776,780</link.rule.ids></links><search><creatorcontrib>Kefali, Abderrahmane</creatorcontrib><creatorcontrib>Sari, Toufik</creatorcontrib><creatorcontrib>Bahi, Halima</creatorcontrib><title>Foreground-Background Separation by Feed-forward Neural Networks in Old Manuscripts</title><title>Informatica (Ljubljana)</title><description>Artificial Neural Networks (ANNs) are widely used techniques in image processing and pattern recognition. Despite of their power in classification tasks, for pattern recognition, they show limited applicability in the earlier stages such as the foreground-background separation (FBS). In this paper a novel FBS technique based on ANN is applied on old documents with a variety of degradations. The idea is to train the ANN on a set of pairs of original images and their respective ideal black and white ones relying on global and local information. We ran several experiments on benchmark and synthetic data and we obtained better results than state-of-the art methods.</description><subject>Benchmarking</subject><subject>Classification</subject><subject>Learning theory</subject><subject>Neural networks</subject><subject>Pattern recognition</subject><subject>Separation</subject><subject>Tasks</subject><subject>Trains</subject><issn>0350-5596</issn><issn>1854-3871</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2014</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNqFj0FLwzAYhoMoOKf_IeDFSyBpkibfUYdTYbrD9DzS5ot0q01NWob_3g49efH0vIeHB94TMhNWKyatEadkxqXmTGsoz8lFzjvOlRS2mJHNMiZ8T3HsPLtz9f5n0g32LrmhiR2tvugS0bMQ08ElT19wTK6dMBxi2mfadHTdevrsujHXqemHfEnOgmszXv1yTt6W96-LR7ZaPzwtblesLxQMLFgojHJYCS2FVCBRVioYrz0Gbp2BOjiJJRRaWVmVALYSHpwJBdbHKefk5qfbp_g5Yh62H02usW1dh3HMW2E4CFNyDv-r5dTnWqujev1H3cUxddORydIcDFjJ5TeKTWlE</recordid><startdate>20141201</startdate><enddate>20141201</enddate><creator>Kefali, Abderrahmane</creator><creator>Sari, Toufik</creator><creator>Bahi, Halima</creator><general>Slovenian Society Informatika / Slovensko drustvo Informatika</general><scope>3V.</scope><scope>7SC</scope><scope>7XB</scope><scope>8AL</scope><scope>8FD</scope><scope>8FE</scope><scope>8FG</scope><scope>8FK</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>ARAPS</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>BYOGL</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>GNUQQ</scope><scope>HCIFZ</scope><scope>JQ2</scope><scope>K7-</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>M0N</scope><scope>P5Z</scope><scope>P62</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>Q9U</scope><scope>7QO</scope><scope>FR3</scope><scope>P64</scope></search><sort><creationdate>20141201</creationdate><title>Foreground-Background Separation by Feed-forward Neural Networks in Old Manuscripts</title><author>Kefali, Abderrahmane ; Sari, Toufik ; Bahi, Halima</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-p249t-f89274aeb15313493e3b4f7d5def08a79cfa3e6925483b6998b1d9a7f2ec8b1d3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2014</creationdate><topic>Benchmarking</topic><topic>Classification</topic><topic>Learning theory</topic><topic>Neural networks</topic><topic>Pattern recognition</topic><topic>Separation</topic><topic>Tasks</topic><topic>Trains</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Kefali, Abderrahmane</creatorcontrib><creatorcontrib>Sari, Toufik</creatorcontrib><creatorcontrib>Bahi, Halima</creatorcontrib><collection>ProQuest Central (Corporate)</collection><collection>Computer and Information Systems Abstracts</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>Computing Database (Alumni Edition)</collection><collection>Technology Research Database</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>Advanced Technologies & Aerospace Collection</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>East Europe, Central Europe Database</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>ProQuest Central Student</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Computer Science Collection</collection><collection>Computer Science Database</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>Computing Database</collection><collection>Advanced Technologies & Aerospace Database</collection><collection>ProQuest Advanced Technologies & Aerospace Collection</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>ProQuest Central Basic</collection><collection>Biotechnology Research Abstracts</collection><collection>Engineering Research Database</collection><collection>Biotechnology and BioEngineering Abstracts</collection><jtitle>Informatica (Ljubljana)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Kefali, Abderrahmane</au><au>Sari, Toufik</au><au>Bahi, Halima</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Foreground-Background Separation by Feed-forward Neural Networks in Old Manuscripts</atitle><jtitle>Informatica (Ljubljana)</jtitle><date>2014-12-01</date><risdate>2014</risdate><volume>38</volume><issue>4</issue><spage>329</spage><epage>329</epage><pages>329-329</pages><issn>0350-5596</issn><eissn>1854-3871</eissn><abstract>Artificial Neural Networks (ANNs) are widely used techniques in image processing and pattern recognition. Despite of their power in classification tasks, for pattern recognition, they show limited applicability in the earlier stages such as the foreground-background separation (FBS). In this paper a novel FBS technique based on ANN is applied on old documents with a variety of degradations. The idea is to train the ANN on a set of pairs of original images and their respective ideal black and white ones relying on global and local information. We ran several experiments on benchmark and synthetic data and we obtained better results than state-of-the art methods.</abstract><cop>Ljubljana</cop><pub>Slovenian Society Informatika / Slovensko drustvo Informatika</pub><tpages>1</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0350-5596 |
| ispartof | Informatica (Ljubljana), 2014-12, Vol.38 (4), p.329-329 |
| issn | 0350-5596 1854-3871 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_1709176009 |
| source | Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals |
| subjects | Benchmarking Classification Learning theory Neural networks Pattern recognition Separation Tasks Trains |
| title | Foreground-Background Separation by Feed-forward Neural Networks in Old Manuscripts |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-09T04%3A01%3A48IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Foreground-Background%20Separation%20by%20Feed-forward%20Neural%20Networks%20in%20Old%20Manuscripts&rft.jtitle=Informatica%20(Ljubljana)&rft.au=Kefali,%20Abderrahmane&rft.date=2014-12-01&rft.volume=38&rft.issue=4&rft.spage=329&rft.epage=329&rft.pages=329-329&rft.issn=0350-5596&rft.eissn=1854-3871&rft_id=info:doi/&rft_dat=%3Cproquest%3E1709176009%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=1650979830&rft_id=info:pmid/&rfr_iscdi=true |