Close
Metadata

Identity statement area
Reference TypeConference Paper (Conference Proceedings)
Sitesibgrapi.sid.inpe.br
Identifier6qtX3pFwXQZeBBx/w4RP9
Repositorysid.inpe.br/banon/2002/11.05.11.03
Last Update2002:11.04.02.00.00 administrator
Metadatasid.inpe.br/banon/2002/11.05.11.03.13
Metadata Last Update2020:02.19.02.58.51 administrator
Citation KeyOliveiraLethBortSabo:2000:HaDiSe
TitleHandwritten digits segmentation based on structural approach
Year2000
DateOctober
Access Date2021, Jan. 19
Number of Files1
Size455 KiB
Context area
Author1 Oliveira, Luiz E. Soares
2 Lethelier, Edouard
3 Bortolozzi, Flávio
4 Sabourin, Robert
EditorCarvalho, Paulo Cezar Pinto
Walter, Marcelo
Conference NameBrazilian Symposium on Computer Graphics and Image Processing, 13 (SIBGRAPI)
Conference LocationGramado, RS, Brazil
Pages67-73
PublisherIEEE Computer Society
Publisher CityLos Alamitos
Tertiary TypeFull Paper
OrganizationSBC - Brazilian Computer Society
History2008-07-17 14:10:49 :: administrator -> banon ::
2008-08-26 15:23:01 :: banon -> administrator ::
2009-08-13 20:36:52 :: administrator -> banon ::
2010-08-28 20:00:09 :: banon -> administrator ::
2020-02-19 02:58:51 :: administrator -> :: 2000
Content and structure area
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
Content TypeExternal Contribution
Keywordshandwritten character recognition, handwritten digit segmentation, structural approach, segmentation-based recognition system, heuristic rules, graphs.
AbstractWe deal with a new segmentation approach applied to unconstrained handwritten digits. The novelty of the proposed algorithm is based on the combination of two types of structural features in order to provide the best segmentation path between connected entities. This method was developed to be applied in a segmentation-based recognition system. We first present the features used to generate our basic segmentation points, and we define our segmentation paths depending on the encountered configurations with only few heuristic rules. Then, we present a strategy based on graphs in order to manage the segmentation. Finally, we evaluate the output of our segmenter using a integrated classifier with three different combination methods.
source Directory Contentthere are no files
agreement Directory Contentthere are no files
Conditions of access and use area
data URLhttp://urlib.net/rep/6qtX3pFwXQZeBBx/w4RP9
zipped data URLhttp://urlib.net/zip/6qtX3pFwXQZeBBx/w4RP9
Target File67-73.pdf
User Groupadministrator
Visibilityshown
Allied materials area
Host Collectionsid.inpe.br/banon/2001/03.30.15.38
Notes area
NotesThe conference was held in Gramado, RS, Brazil, from October 17 to 20.
Empty Fieldsaccessionnumber affiliation archivingpolicy archivist area booktitle callnumber copyholder copyright creatorhistory descriptionlevel dissemination documentstage doi e-mailaddress edition electronicmailaddress format group holdercode isbn issn label language lineage mark mirrorrepository nextedition nexthigherunit numberofvolumes orcid parameterlist parentrepositories previousedition previouslowerunit progress project readergroup readpermission resumeid rightsholder secondarydate secondarykey secondarymark secondarytype serieseditor session shorttitle sponsor subject tertiarymark type url versiontype volume

Close