<?xml version="1.0" encoding="ISO-8859-1"?>
<metadatalist>
	<metadata ReferenceType="Conference Proceedings">
		<site>sibgrapi.sid.inpe.br 802</site>
		<holdercode>{ibi 8JMKD3MGPEW34M/46T9EHH}</holdercode>
		<identifier>6qtX3pFwXQZeBBx/vRT7J</identifier>
		<repository>sid.inpe.br/banon/2002/10.24.10.32</repository>
		<lastupdate>2002:09.10.03.00.00 sid.inpe.br/banon/2001/03.30.15.38 administrator</lastupdate>
		<metadatarepository>sid.inpe.br/banon/2002/10.24.10.32.25</metadatarepository>
		<metadatalastupdate>2022:06.14.00.11.51 sid.inpe.br/banon/2001/03.30.15.38 administrator {D 2002}</metadatalastupdate>
		<doi>10.1109/SIBGRA.2002.1167145</doi>
		<citationkey>OliveiraJrCarvFreiSabo:2002:EvNNHM</citationkey>
		<title>Evaluating NN and HMM classifiers for handwritten word recognition</title>
		<year>2002</year>
		<numberoffiles>1</numberoffiles>
		<size>150 KiB</size>
		<author>Oliveira Junior, Jose Josemar de,</author>
		<author>Carvalho, Joao Marques de,</author>
		<author>Freitas, Cinthia Obladen de Almendra,</author>
		<author>Sabourin, Robert,</author>
		<editor>Gonçalves, Luiz Marcos Garcia,</editor>
		<editor>Musse, Soraia Raupp,</editor>
		<editor>Comba, João Luiz Dihl,</editor>
		<editor>Giraldi, Gilson,</editor>
		<editor>Dreux, Marcelo,</editor>
		<conferencename>Brazilian Symposium on Computer Graphics and Image Processing, 15 (SIBGRAPI)</conferencename>
		<conferencelocation>Fortaleza, CE, Brazil</conferencelocation>
		<date>10-10 Oct. 2002</date>
		<publisher>IEEE Computer Society</publisher>
		<publisheraddress>Los Alamitos</publisheraddress>
		<booktitle>Proceedings</booktitle>
		<tertiarytype>Full Paper</tertiarytype>
		<organization>SBC - Brazilian Computer Society</organization>
		<transferableflag>1</transferableflag>
		<versiontype>finaldraft</versiontype>
		<abstract>This paper evaluates NN and HMM classifiers applied to the handwritten word recognition problem. The goal is analyse the individual and combined performance of these classifiers. They are evaluated considering two different combination strategies and the experiments are performed with the same database and similar feature sets. The strategy proposed takes advantage of the different but complementary mechanisms of NN and HMM to obtain a more efficient hybrid classifier. The recognition rates obtained vary from 75.9% using the HMM classifier alone to 90.4% considering the NN and HMM combination.</abstract>
		<language>en</language>
		<targetfile>79.pdf</targetfile>
		<usergroup>administrator</usergroup>
		<visibility>shown</visibility>
		<nexthigherunit>8JMKD3MGPEW34M/46QCSHP</nexthigherunit>
		<nexthigherunit>8JMKD3MGPEW34M/4742MCS</nexthigherunit>
		<citingitemlist>sid.inpe.br/sibgrapi/2022/05.01.04.11 6</citingitemlist>
		<citingitemlist>sid.inpe.br/sibgrapi/2022/06.10.21.49 1</citingitemlist>
		<hostcollection>sid.inpe.br/banon/2001/03.30.15.38</hostcollection>
		<notes>The conference was held in Fortaleza, CE, Brazil, from October 7 to 10.</notes>
		<lasthostcollection>sid.inpe.br/banon/2001/03.30.15.38</lasthostcollection>
		<url>http://sibgrapi.sid.inpe.br/rep-/sid.inpe.br/banon/2002/10.24.10.32</url>
	</metadata>
</metadatalist>