Handwritten character recognition based on moment features derived from image partition

In this work we present a novel approach to handwritten character recognition which is based on the intuitive way in which characters are written as one or a few continuous lines. Therefore we calculate the zeroth, first and second radial moment as a function of the angle. In practice this is done b...

Full description

Saved in:
Bibliographic Details
Main Authors: Tsang, I.J., Tsang, I.R., Van Dyck, D.
Format: Conference Proceeding
Language:English
Subjects:
Character recognition
Feature extraction
Fingerprint recognition
Handwriting recognition
Image recognition
Image segmentation
Partitioning algorithms
Pattern recognition
Physics
Testing
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 942 vol.2
container_issue
container_start_page 939
container_title
container_volume 2
creator Tsang, I.J.
Tsang, I.R.
Van Dyck, D.
description In this work we present a novel approach to handwritten character recognition which is based on the intuitive way in which characters are written as one or a few continuous lines. Therefore we calculate the zeroth, first and second radial moment as a function of the angle. In practice this is done by dividing the character into 32 angular sections. The three obtained curves can be used for pattern recognition using statistical analysis. The method has been evaluated using the NIST handwritten character data set. At first, a simple chi-square test gave a result of 80.81% recognition rate at zero rejection rate for digits. Using a back-propagation algorithm the recognition rate obtained was 87.54% also at zero rejection rate, showing that the features are sufficient to discriminate the characters.
doi_str_mv 10.1109/ICIP.1998.723709
format conference_proceeding
fullrecord <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_723709</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>723709</ieee_id><sourcerecordid>723709</sourcerecordid><originalsourceid>FETCH-LOGICAL-i104t-31c97c401a638187ccda02abfb99d0c0e9dfb3f127069e91472fb0c2b041a633</originalsourceid><addsrcrecordid>eNotT01LAzEUDIig1t7FU_7Aru8lyyY5SlG7UNBDwWPJx0uNuLslGxX_vavtXGZgmGGGsRuEGhHMXbfqXmo0RtdKSAXmjF2BRt1qLRAv2HKa3mGGFkoZdcle13YI3zmVQgP3bzZbXyjzTH7cD6mkceDOThT4LPqxp6HwSLZ8Zpp4oJy-Zivmseept3viB5vLf-qanUf7MdHyxAu2fXzYrtbV5vmpW91vqoTQlEqiN8o3gLaV80rlfbAgrIvOmAAeyIToZEShoDVksFEiOvDCQfMXkQt2e6xNRLQ75HlF_tkdn8tfw6VQWg</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Handwritten character recognition based on moment features derived from image partition</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Tsang, I.J. ; Tsang, I.R. ; Van Dyck, D.</creator><creatorcontrib>Tsang, I.J. ; Tsang, I.R. ; Van Dyck, D.</creatorcontrib><description>In this work we present a novel approach to handwritten character recognition which is based on the intuitive way in which characters are written as one or a few continuous lines. Therefore we calculate the zeroth, first and second radial moment as a function of the angle. In practice this is done by dividing the character into 32 angular sections. The three obtained curves can be used for pattern recognition using statistical analysis. The method has been evaluated using the NIST handwritten character data set. At first, a simple chi-square test gave a result of 80.81% recognition rate at zero rejection rate for digits. Using a back-propagation algorithm the recognition rate obtained was 87.54% also at zero rejection rate, showing that the features are sufficient to discriminate the characters.</description><identifier>ISBN: 0818688211</identifier><identifier>ISBN: 9780818688218</identifier><identifier>DOI: 10.1109/ICIP.1998.723709</identifier><language>eng</language><publisher>IEEE</publisher><subject>Character recognition ; Feature extraction ; Fingerprint recognition ; Handwriting recognition ; Image recognition ; Image segmentation ; Partitioning algorithms ; Pattern recognition ; Physics ; Testing</subject><ispartof>Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269), 1998, Vol.2, p.939-942 vol.2</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/723709$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,2052,4036,4037,27902,54895</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/723709$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Tsang, I.J.</creatorcontrib><creatorcontrib>Tsang, I.R.</creatorcontrib><creatorcontrib>Van Dyck, D.</creatorcontrib><title>Handwritten character recognition based on moment features derived from image partition</title><title>Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269)</title><addtitle>ICIP</addtitle><description>In this work we present a novel approach to handwritten character recognition which is based on the intuitive way in which characters are written as one or a few continuous lines. Therefore we calculate the zeroth, first and second radial moment as a function of the angle. In practice this is done by dividing the character into 32 angular sections. The three obtained curves can be used for pattern recognition using statistical analysis. The method has been evaluated using the NIST handwritten character data set. At first, a simple chi-square test gave a result of 80.81% recognition rate at zero rejection rate for digits. Using a back-propagation algorithm the recognition rate obtained was 87.54% also at zero rejection rate, showing that the features are sufficient to discriminate the characters.</description><subject>Character recognition</subject><subject>Feature extraction</subject><subject>Fingerprint recognition</subject><subject>Handwriting recognition</subject><subject>Image recognition</subject><subject>Image segmentation</subject><subject>Partitioning algorithms</subject><subject>Pattern recognition</subject><subject>Physics</subject><subject>Testing</subject><isbn>0818688211</isbn><isbn>9780818688218</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>1998</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotT01LAzEUDIig1t7FU_7Aru8lyyY5SlG7UNBDwWPJx0uNuLslGxX_vavtXGZgmGGGsRuEGhHMXbfqXmo0RtdKSAXmjF2BRt1qLRAv2HKa3mGGFkoZdcle13YI3zmVQgP3bzZbXyjzTH7cD6mkceDOThT4LPqxp6HwSLZ8Zpp4oJy-Zivmseept3viB5vLf-qanUf7MdHyxAu2fXzYrtbV5vmpW91vqoTQlEqiN8o3gLaV80rlfbAgrIvOmAAeyIToZEShoDVksFEiOvDCQfMXkQt2e6xNRLQ75HlF_tkdn8tfw6VQWg</recordid><startdate>1998</startdate><enddate>1998</enddate><creator>Tsang, I.J.</creator><creator>Tsang, I.R.</creator><creator>Van Dyck, D.</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>1998</creationdate><title>Handwritten character recognition based on moment features derived from image partition</title><author>Tsang, I.J. ; Tsang, I.R. ; Van Dyck, D.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i104t-31c97c401a638187ccda02abfb99d0c0e9dfb3f127069e91472fb0c2b041a633</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>1998</creationdate><topic>Character recognition</topic><topic>Feature extraction</topic><topic>Fingerprint recognition</topic><topic>Handwriting recognition</topic><topic>Image recognition</topic><topic>Image segmentation</topic><topic>Partitioning algorithms</topic><topic>Pattern recognition</topic><topic>Physics</topic><topic>Testing</topic><toplevel>online_resources</toplevel><creatorcontrib>Tsang, I.J.</creatorcontrib><creatorcontrib>Tsang, I.R.</creatorcontrib><creatorcontrib>Van Dyck, D.</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 Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Tsang, I.J.</au><au>Tsang, I.R.</au><au>Van Dyck, D.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Handwritten character recognition based on moment features derived from image partition</atitle><btitle>Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269)</btitle><stitle>ICIP</stitle><date>1998</date><risdate>1998</risdate><volume>2</volume><spage>939</spage><epage>942 vol.2</epage><pages>939-942 vol.2</pages><isbn>0818688211</isbn><isbn>9780818688218</isbn><abstract>In this work we present a novel approach to handwritten character recognition which is based on the intuitive way in which characters are written as one or a few continuous lines. Therefore we calculate the zeroth, first and second radial moment as a function of the angle. In practice this is done by dividing the character into 32 angular sections. The three obtained curves can be used for pattern recognition using statistical analysis. The method has been evaluated using the NIST handwritten character data set. At first, a simple chi-square test gave a result of 80.81% recognition rate at zero rejection rate for digits. Using a back-propagation algorithm the recognition rate obtained was 87.54% also at zero rejection rate, showing that the features are sufficient to discriminate the characters.</abstract><pub>IEEE</pub><doi>10.1109/ICIP.1998.723709</doi></addata></record>
fulltext fulltext_linktorsrc
identifier ISBN: 0818688211
ispartof Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269), 1998, Vol.2, p.939-942 vol.2
issn
language eng
recordid cdi_ieee_primary_723709
source IEEE Electronic Library (IEL) Conference Proceedings
subjects Character recognition
Feature extraction
Fingerprint recognition
Handwriting recognition
Image recognition
Image segmentation
Partitioning algorithms
Pattern recognition
Physics
Testing
title Handwritten character recognition based on moment features derived from image partition
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-13T23%3A19%3A09IST&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=Handwritten%20character%20recognition%20based%20on%20moment%20features%20derived%20from%20image%20partition&rft.btitle=Proceedings%201998%20International%20Conference%20on%20Image%20Processing.%20ICIP98%20(Cat.%20No.98CB36269)&rft.au=Tsang,%20I.J.&rft.date=1998&rft.volume=2&rft.spage=939&rft.epage=942%20vol.2&rft.pages=939-942%20vol.2&rft.isbn=0818688211&rft.isbn_list=9780818688218&rft_id=info:doi/10.1109/ICIP.1998.723709&rft_dat=%3Cieee_6IE%3E723709%3C/ieee_6IE%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i104t-31c97c401a638187ccda02abfb99d0c0e9dfb3f127069e91472fb0c2b041a633%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=723709&rfr_iscdi=true