Linear dimension reduction methods in character recognition systems
Handwritten character recognition systems can be divided into three steps: preprocessing, feature extraction and classification. In the feature extraction process, the representation power of features should be increased while keeping the number of features as small as possible. We project raw chara...
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Tagungsbericht |
| Sprache: | eng ; tur |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 614 |
|---|---|
| container_issue | |
| container_start_page | 611 |
| container_title | |
| container_volume | |
| creator | Capar, A. Ayvaci, A. Kahraman, F. Demirel, H. Gokmen, M. |
| description | Handwritten character recognition systems can be divided into three steps: preprocessing, feature extraction and classification. In the feature extraction process, the representation power of features should be increased while keeping the number of features as small as possible. We project raw character image vectors to lower dimension spaces by different linear transformations and compare their representation and discrimination power. In dimension reduction, principal component analysis (PCA), multiple discriminant analysis (MDA) and independent component analysis (ICA) are compared; the best classification performance is obtained using ICA. A multilayer perceptron, which is trained by a conjugate gradient algorithm, is used for classification. The handwritten character database studied consists of 5000 training patterns and 2500 test patterns. |
| doi_str_mv | 10.1109/SIU.2004.1338603 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_1338603</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>1338603</ieee_id><sourcerecordid>1338603</sourcerecordid><originalsourceid>FETCH-LOGICAL-i105t-b242ea112d402288ff38a2e3f2651e1d24a1b7606769615495960431e3f739c73</originalsourceid><addsrcrecordid>eNotj09LxDAUxAMiqOveBS_9Aq3v5SVpepTin4WCB93zkm1e3YhtJYmH_fZW3bnMwPwYGCFuECpEaO5eN9tKAqgKiawBOhNXUFsgS2jVhVin9AGLlFZS6UvRdmFiFwsfRp5SmKcisv_u828aOR9mn4owFf3BRddnjkvdz-9T-APSMWUe07U4H9xn4vXJV2L7-PDWPpfdy9Omve_KgKBzuZdKskOUXoGU1g4DWSeZBmk0MnqpHO5rA6Y2jUGtGt0YUIQLUVPT17QSt_-7gZl3XzGMLh53p5_0A8x_R7w</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Linear dimension reduction methods in character recognition systems</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Capar, A. ; Ayvaci, A. ; Kahraman, F. ; Demirel, H. ; Gokmen, M.</creator><creatorcontrib>Capar, A. ; Ayvaci, A. ; Kahraman, F. ; Demirel, H. ; Gokmen, M.</creatorcontrib><description>Handwritten character recognition systems can be divided into three steps: preprocessing, feature extraction and classification. In the feature extraction process, the representation power of features should be increased while keeping the number of features as small as possible. We project raw character image vectors to lower dimension spaces by different linear transformations and compare their representation and discrimination power. In dimension reduction, principal component analysis (PCA), multiple discriminant analysis (MDA) and independent component analysis (ICA) are compared; the best classification performance is obtained using ICA. A multilayer perceptron, which is trained by a conjugate gradient algorithm, is used for classification. The handwritten character database studied consists of 5000 training patterns and 2500 test patterns.</description><identifier>ISBN: 0780383184</identifier><identifier>ISBN: 9780780383180</identifier><identifier>DOI: 10.1109/SIU.2004.1338603</identifier><language>eng ; tur</language><publisher>IEEE</publisher><subject>Character recognition ; Computer aided analysis ; Independent component analysis ; Linear discriminant analysis ; Performance analysis ; Principal component analysis ; Solid modeling ; Testing ; Vectors</subject><ispartof>Proceedings of the IEEE 12th Signal Processing and Communications Applications Conference, 2004, 2004, p.611-614</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/1338603$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,2052,4036,4037,27902,54895</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/1338603$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Capar, A.</creatorcontrib><creatorcontrib>Ayvaci, A.</creatorcontrib><creatorcontrib>Kahraman, F.</creatorcontrib><creatorcontrib>Demirel, H.</creatorcontrib><creatorcontrib>Gokmen, M.</creatorcontrib><title>Linear dimension reduction methods in character recognition systems</title><title>Proceedings of the IEEE 12th Signal Processing and Communications Applications Conference, 2004</title><addtitle>SIU</addtitle><description>Handwritten character recognition systems can be divided into three steps: preprocessing, feature extraction and classification. In the feature extraction process, the representation power of features should be increased while keeping the number of features as small as possible. We project raw character image vectors to lower dimension spaces by different linear transformations and compare their representation and discrimination power. In dimension reduction, principal component analysis (PCA), multiple discriminant analysis (MDA) and independent component analysis (ICA) are compared; the best classification performance is obtained using ICA. A multilayer perceptron, which is trained by a conjugate gradient algorithm, is used for classification. The handwritten character database studied consists of 5000 training patterns and 2500 test patterns.</description><subject>Character recognition</subject><subject>Computer aided analysis</subject><subject>Independent component analysis</subject><subject>Linear discriminant analysis</subject><subject>Performance analysis</subject><subject>Principal component analysis</subject><subject>Solid modeling</subject><subject>Testing</subject><subject>Vectors</subject><isbn>0780383184</isbn><isbn>9780780383180</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2004</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNotj09LxDAUxAMiqOveBS_9Aq3v5SVpepTin4WCB93zkm1e3YhtJYmH_fZW3bnMwPwYGCFuECpEaO5eN9tKAqgKiawBOhNXUFsgS2jVhVin9AGLlFZS6UvRdmFiFwsfRp5SmKcisv_u828aOR9mn4owFf3BRddnjkvdz-9T-APSMWUe07U4H9xn4vXJV2L7-PDWPpfdy9Omve_KgKBzuZdKskOUXoGU1g4DWSeZBmk0MnqpHO5rA6Y2jUGtGt0YUIQLUVPT17QSt_-7gZl3XzGMLh53p5_0A8x_R7w</recordid><startdate>2004</startdate><enddate>2004</enddate><creator>Capar, A.</creator><creator>Ayvaci, A.</creator><creator>Kahraman, F.</creator><creator>Demirel, H.</creator><creator>Gokmen, M.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>2004</creationdate><title>Linear dimension reduction methods in character recognition systems</title><author>Capar, A. ; Ayvaci, A. ; Kahraman, F. ; Demirel, H. ; Gokmen, M.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i105t-b242ea112d402288ff38a2e3f2651e1d24a1b7606769615495960431e3f739c73</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng ; tur</language><creationdate>2004</creationdate><topic>Character recognition</topic><topic>Computer aided analysis</topic><topic>Independent component analysis</topic><topic>Linear discriminant analysis</topic><topic>Performance analysis</topic><topic>Principal component analysis</topic><topic>Solid modeling</topic><topic>Testing</topic><topic>Vectors</topic><toplevel>online_resources</toplevel><creatorcontrib>Capar, A.</creatorcontrib><creatorcontrib>Ayvaci, A.</creatorcontrib><creatorcontrib>Kahraman, F.</creatorcontrib><creatorcontrib>Demirel, H.</creatorcontrib><creatorcontrib>Gokmen, M.</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/IET Electronic Library</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>Capar, A.</au><au>Ayvaci, A.</au><au>Kahraman, F.</au><au>Demirel, H.</au><au>Gokmen, M.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Linear dimension reduction methods in character recognition systems</atitle><btitle>Proceedings of the IEEE 12th Signal Processing and Communications Applications Conference, 2004</btitle><stitle>SIU</stitle><date>2004</date><risdate>2004</risdate><spage>611</spage><epage>614</epage><pages>611-614</pages><isbn>0780383184</isbn><isbn>9780780383180</isbn><abstract>Handwritten character recognition systems can be divided into three steps: preprocessing, feature extraction and classification. In the feature extraction process, the representation power of features should be increased while keeping the number of features as small as possible. We project raw character image vectors to lower dimension spaces by different linear transformations and compare their representation and discrimination power. In dimension reduction, principal component analysis (PCA), multiple discriminant analysis (MDA) and independent component analysis (ICA) are compared; the best classification performance is obtained using ICA. A multilayer perceptron, which is trained by a conjugate gradient algorithm, is used for classification. The handwritten character database studied consists of 5000 training patterns and 2500 test patterns.</abstract><pub>IEEE</pub><doi>10.1109/SIU.2004.1338603</doi><tpages>4</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISBN: 0780383184 |
| ispartof | Proceedings of the IEEE 12th Signal Processing and Communications Applications Conference, 2004, 2004, p.611-614 |
| issn | |
| language | eng ; tur |
| recordid | cdi_ieee_primary_1338603 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Character recognition Computer aided analysis Independent component analysis Linear discriminant analysis Performance analysis Principal component analysis Solid modeling Testing Vectors |
| title | Linear dimension reduction methods in character recognition systems |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-07T14%3A43%3A49IST&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=Linear%20dimension%20reduction%20methods%20in%20character%20recognition%20systems&rft.btitle=Proceedings%20of%20the%20IEEE%2012th%20Signal%20Processing%20and%20Communications%20Applications%20Conference,%202004&rft.au=Capar,%20A.&rft.date=2004&rft.spage=611&rft.epage=614&rft.pages=611-614&rft.isbn=0780383184&rft.isbn_list=9780780383180&rft_id=info:doi/10.1109/SIU.2004.1338603&rft_dat=%3Cieee_6IE%3E1338603%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=1338603&rfr_iscdi=true |