Please use this identifier to cite or link to this item:
Full metadata record
DC FieldValueLanguage
dc.contributor.CRUESPUniversidade Estadual de Campinaspt_BR
dc.typeArtigo de periódicopt_BR
dc.titleSnooperText: A text detection system for automatic scenes indexing of urban scenespt_BR
dc.contributor.authorMinetto, Rpt_BR
dc.contributor.authorThome, Npt_BR
dc.contributor.authorCord, Mpt_BR
dc.contributor.authorLeite, NJpt_BR
dc.contributor.authorStolfi, Jpt_BR
unicamp.authorMinetto, Rodrigo Univ Fed Parana, DAINF, BR-80060000 Curitiba, Parana, Brazilpt_BR
unicamp.authorThome, Nicolas Cord, Matthieu Univ Paris 06, Lab Informat Paris 6 LIP6, Paris, Francept_BR
unicamp.authorLeite, Neucimar J. Stolfi, Jorge Univ Estadual Campinas, Inst Comp, Campinas, SP, Brazilpt_BR
dc.subjectText detectionpt_BR
dc.subjectText region classificationpt_BR
dc.subjectHistogram of oriented gradients for textpt_BR
dc.subjectText descriptorpt_BR
dc.subjectTextual indexing in urban scene imagespt_BR
dc.description.abstractWe describe SNOOPERTEXT, an original detector for textual information embedded in photos of building facades (such as names of stores, products and services) that we developed for the iTowns urban geographic information project. SNOOPERTEXT locates candidate characters by using toggle-mapping image segmentation and character/non-character classification based on shape descriptors. The candidate characters are then grouped to form either candidate words or candidate text lines. These candidate regions are then validated by a text/non-text classifier using a HOG-based descriptor specifically tuned to single-line text regions. These operations are applied at multiple image scales in order to suppress irrelevant detail in character shapes and to avoid the use of overly large kernels in the segmentation. We show that SNOOPERTEXT outperforms other published state-of-the-art text detection algorithms on standard image benchmarks. We also describe two metrics to evaluate the end-to-end performance of text extraction systems, and show that the use of SNOOPERTEXT as a pre-filter significantly improves the performance of a general-purpose OCR algorithm when applied to photos of urban scenes. (C) 2013 Elsevier Inc. All rights
dc.relation.ispartofComputer Vision And Image Understandingpt_BR
dc.relation.ispartofabbreviationComput. Vis. Image Underst.pt_BR
dc.publisher.citySan Diegopt_BR
dc.publisherAcademic Press Inc Elsevier Sciencept_BR
dc.identifier.citationComputer Vision And Image Understanding. Academic Press Inc Elsevier Science, v. 122, n. 92, n. 104, 2014.pt_BR
dc.sourceWeb of Sciencept_BR
dc.description.sponsorshipFundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)pt_BR
dc.description.sponsorshipConselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)pt_BR
dc.description.sponsorshipCoordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)pt_BR
dc.description.sponsorshipANR [07-MDC0-007-03]pt_BR
dc.description.sponsorship1Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)pt_BR
dc.description.sponsorship1Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)pt_BR
dc.description.sponsorship1Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)pt_BR
dc.description.sponsordocumentnumberFAPESP [07/54201-6, 07/52015-0]pt
dc.description.sponsordocumentnumberCNPq [301016/92-5]pt
dc.description.sponsordocumentnumberCAPES [592/08]pt
dc.description.sponsordocumentnumberANR [07-MDC0-007-03]pt
dc.description.provenanceMade available in DSpace on 2014-07-30T18:42:59Z (GMT). No. of bitstreams: 0 Previous issue date: 2014en
dc.description.provenanceMade available in DSpace on 2015-11-26T17:39:54Z (GMT). No. of bitstreams: 0 Previous issue date: 2014en
Appears in Collections:Unicamp - Artigos e Outros Documentos

Files in This Item:
There are no files associated with this item.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.