Recognition of facsimile documents using a database of robust features

A method for the recognition of poor quality documents containing touching characters is presented. The method is based on extraction of independent and robust features of each object of a sample word, where objects consist of single letters or of several touching ones. Thus avoiding letter segmenta...

Full description

Saved in:
Bibliographic Details
Main Authors: Raza, G., Hennig, A., Sherkat, N., Whitrow, R.J.
Format: Conference Proceeding
Language:English
Subjects:
Character recognition
Dictionaries
Facsimile
Feature extraction
Humans
Image databases
Image segmentation
Optical character recognition software
Robustness
Spatial databases
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 448 vol.1
container_issue
container_start_page 444
container_title
container_volume 1
creator Raza, G.
Hennig, A.
Sherkat, N.
Whitrow, R.J.
description A method for the recognition of poor quality documents containing touching characters is presented. The method is based on extraction of independent and robust features of each object of a sample word, where objects consist of single letters or of several touching ones. Thus avoiding letter segmentation the method eliminates errors frequently introduced in segmentation based approaches. Features are attributed by their position and extent in order to facilitate discrimination between different classes of objects. A method for automatic construction of a comprehensive database is presented. From a given dictionary every possible letter combination is obtained and the images of the artificially touching letters created. These images are subjected to noise and their features extracted. For recognition, alternatives for each object are found based on the database. Object alternatives are then combined into valid word alternatives using lexicon lookup. It has been observed that the developed method is effective for the recognition of poor quality documents.
doi_str_mv 10.1109/ICDAR.1997.619886
format conference_proceeding
fullrecord <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_619886</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>619886</ieee_id><sourcerecordid>619886</sourcerecordid><originalsourceid>FETCH-LOGICAL-i104t-2800949127c2c1b14187a096f9eea15a45fd4cce00f9978567368deb6aa607703</originalsourceid><addsrcrecordid>eNotj81Kw0AURgdEUGoeQFfzAolz8zNzZ1mi1UKhUHRdbiZ3ykiTSGay8O2t1LP5NocPjhCPoAoAZZ-37cv6UIC1ptBgEfWNyKxBhYDaoEW4E1mMX-pC02BZ4r3YHNhNpzGkMI1y8tKTi2EIZ5b95JaBxxTlEsN4kiR7StRR5D9vnrolJumZ0jJzfBC3ns6Rs_9dic_N60f7nu_2b9t2vcsDqDrlJSplawulcaWDDmpAQ8pqb5kJGqob39fOsVL-EoGNNpXGnjtNpJUxqlqJp-tvYObj9xwGmn-O19jqF2rkSg8</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Recognition of facsimile documents using a database of robust features</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Raza, G. ; Hennig, A. ; Sherkat, N. ; Whitrow, R.J.</creator><creatorcontrib>Raza, G. ; Hennig, A. ; Sherkat, N. ; Whitrow, R.J.</creatorcontrib><description>A method for the recognition of poor quality documents containing touching characters is presented. The method is based on extraction of independent and robust features of each object of a sample word, where objects consist of single letters or of several touching ones. Thus avoiding letter segmentation the method eliminates errors frequently introduced in segmentation based approaches. Features are attributed by their position and extent in order to facilitate discrimination between different classes of objects. A method for automatic construction of a comprehensive database is presented. From a given dictionary every possible letter combination is obtained and the images of the artificially touching letters created. These images are subjected to noise and their features extracted. For recognition, alternatives for each object are found based on the database. Object alternatives are then combined into valid word alternatives using lexicon lookup. It has been observed that the developed method is effective for the recognition of poor quality documents.</description><identifier>ISBN: 9780818678981</identifier><identifier>ISBN: 0818678984</identifier><identifier>DOI: 10.1109/ICDAR.1997.619886</identifier><language>eng</language><publisher>IEEE</publisher><subject>Character recognition ; Dictionaries ; Facsimile ; Feature extraction ; Humans ; Image databases ; Image segmentation ; Optical character recognition software ; Robustness ; Spatial databases</subject><ispartof>Proceedings of the Fourth International Conference on Document Analysis and Recognition, 1997, Vol.1, p.444-448 vol.1</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/619886$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,2052,4036,4037,27902,54895</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/619886$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Raza, G.</creatorcontrib><creatorcontrib>Hennig, A.</creatorcontrib><creatorcontrib>Sherkat, N.</creatorcontrib><creatorcontrib>Whitrow, R.J.</creatorcontrib><title>Recognition of facsimile documents using a database of robust features</title><title>Proceedings of the Fourth International Conference on Document Analysis and Recognition</title><addtitle>ICDAR</addtitle><description>A method for the recognition of poor quality documents containing touching characters is presented. The method is based on extraction of independent and robust features of each object of a sample word, where objects consist of single letters or of several touching ones. Thus avoiding letter segmentation the method eliminates errors frequently introduced in segmentation based approaches. Features are attributed by their position and extent in order to facilitate discrimination between different classes of objects. A method for automatic construction of a comprehensive database is presented. From a given dictionary every possible letter combination is obtained and the images of the artificially touching letters created. These images are subjected to noise and their features extracted. For recognition, alternatives for each object are found based on the database. Object alternatives are then combined into valid word alternatives using lexicon lookup. It has been observed that the developed method is effective for the recognition of poor quality documents.</description><subject>Character recognition</subject><subject>Dictionaries</subject><subject>Facsimile</subject><subject>Feature extraction</subject><subject>Humans</subject><subject>Image databases</subject><subject>Image segmentation</subject><subject>Optical character recognition software</subject><subject>Robustness</subject><subject>Spatial databases</subject><isbn>9780818678981</isbn><isbn>0818678984</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>1997</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotj81Kw0AURgdEUGoeQFfzAolz8zNzZ1mi1UKhUHRdbiZ3ykiTSGay8O2t1LP5NocPjhCPoAoAZZ-37cv6UIC1ptBgEfWNyKxBhYDaoEW4E1mMX-pC02BZ4r3YHNhNpzGkMI1y8tKTi2EIZ5b95JaBxxTlEsN4kiR7StRR5D9vnrolJumZ0jJzfBC3ns6Rs_9dic_N60f7nu_2b9t2vcsDqDrlJSplawulcaWDDmpAQ8pqb5kJGqob39fOsVL-EoGNNpXGnjtNpJUxqlqJp-tvYObj9xwGmn-O19jqF2rkSg8</recordid><startdate>1997</startdate><enddate>1997</enddate><creator>Raza, G.</creator><creator>Hennig, A.</creator><creator>Sherkat, N.</creator><creator>Whitrow, R.J.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>1997</creationdate><title>Recognition of facsimile documents using a database of robust features</title><author>Raza, G. ; Hennig, A. ; Sherkat, N. ; Whitrow, R.J.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i104t-2800949127c2c1b14187a096f9eea15a45fd4cce00f9978567368deb6aa607703</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>1997</creationdate><topic>Character recognition</topic><topic>Dictionaries</topic><topic>Facsimile</topic><topic>Feature extraction</topic><topic>Humans</topic><topic>Image databases</topic><topic>Image segmentation</topic><topic>Optical character recognition software</topic><topic>Robustness</topic><topic>Spatial databases</topic><toplevel>online_resources</toplevel><creatorcontrib>Raza, G.</creatorcontrib><creatorcontrib>Hennig, A.</creatorcontrib><creatorcontrib>Sherkat, N.</creatorcontrib><creatorcontrib>Whitrow, R.J.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Raza, G.</au><au>Hennig, A.</au><au>Sherkat, N.</au><au>Whitrow, R.J.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Recognition of facsimile documents using a database of robust features</atitle><btitle>Proceedings of the Fourth International Conference on Document Analysis and Recognition</btitle><stitle>ICDAR</stitle><date>1997</date><risdate>1997</risdate><volume>1</volume><spage>444</spage><epage>448 vol.1</epage><pages>444-448 vol.1</pages><isbn>9780818678981</isbn><isbn>0818678984</isbn><abstract>A method for the recognition of poor quality documents containing touching characters is presented. The method is based on extraction of independent and robust features of each object of a sample word, where objects consist of single letters or of several touching ones. Thus avoiding letter segmentation the method eliminates errors frequently introduced in segmentation based approaches. Features are attributed by their position and extent in order to facilitate discrimination between different classes of objects. A method for automatic construction of a comprehensive database is presented. From a given dictionary every possible letter combination is obtained and the images of the artificially touching letters created. These images are subjected to noise and their features extracted. For recognition, alternatives for each object are found based on the database. Object alternatives are then combined into valid word alternatives using lexicon lookup. It has been observed that the developed method is effective for the recognition of poor quality documents.</abstract><pub>IEEE</pub><doi>10.1109/ICDAR.1997.619886</doi></addata></record>
fulltext fulltext_linktorsrc
identifier ISBN: 9780818678981
ispartof Proceedings of the Fourth International Conference on Document Analysis and Recognition, 1997, Vol.1, p.444-448 vol.1
issn
language eng
recordid cdi_ieee_primary_619886
source IEEE Electronic Library (IEL) Conference Proceedings
subjects Character recognition
Dictionaries
Facsimile
Feature extraction
Humans
Image databases
Image segmentation
Optical character recognition software
Robustness
Spatial databases
title Recognition of facsimile documents using a database of robust features
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-12T20%3A09%3A27IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Recognition%20of%20facsimile%20documents%20using%20a%20database%20of%20robust%20features&rft.btitle=Proceedings%20of%20the%20Fourth%20International%20Conference%20on%20Document%20Analysis%20and%20Recognition&rft.au=Raza,%20G.&rft.date=1997&rft.volume=1&rft.spage=444&rft.epage=448%20vol.1&rft.pages=444-448%20vol.1&rft.isbn=9780818678981&rft.isbn_list=0818678984&rft_id=info:doi/10.1109/ICDAR.1997.619886&rft_dat=%3Cieee_6IE%3E619886%3C/ieee_6IE%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i104t-2800949127c2c1b14187a096f9eea15a45fd4cce00f9978567368deb6aa607703%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=619886&rfr_iscdi=true