Please use this identifier to cite or link to this item: http://repositorio.unicamp.br/jspui/handle/REPOSIP/342755
Full metadata record
DC FieldValueLanguage
dc.contributor.CRUESPUNIVERSIDADE ESTADUAL DE CAMPINASpt_BR
dc.identifier.isbn978-1-7281-4569-3; 978-1-7281-4570-9pt_BR
dc.contributor.authorunicampGalindo, Eldrey Seolin-
dc.contributor.authorunicampPedrini, Hélio-
dc.typeArtigopt_BR
dc.titleImage super-resolution improved by edge informationpt_BR
dc.contributor.authorGalindo, E.-
dc.contributor.authorPedrini, H.-
dc.subjectAprendizado profundopt_BR
dc.subjectImagenspt_BR
dc.subject.otherlanguageDeep learningpt_BR
dc.subject.otherlanguagePicturespt_BR
dc.description.abstractAs well as in other knowledge domains, deep learning techniques have revolutionized the development of image super-resolution approaches. State-of-the-art algorithms for this problem have employed convolutional neural networks in residual architectures with a number of layers and generic loss functions, such as L1 and Peak Signal-to-Noise Ratio (PSNR). These frameworks (architectures + loss functions) are generic and do not address the main characteristics of an image for human visual perception (luminance, contrast, and structure) resulting in better images, however, with noise mainly at the edges. In this work, we present an edge enhanced super-resolution (EESR) method using a novel residual neural network with focus on image edges and a mix of loss functions that use PSNR, L1, Multiple-Scale Structural Similarity (MS-SSIM), and a new loss function based on the pencil sketch technique. As main contribution, the proposed framework aims to leverage the limits of image super-resolution and presents an improvement of the results in terms of the SSIM metric and achieving competitive results for the PSNR metric.pt_BR
dc.relation.ispartofIEEE international conference on systems, man, and cybernetics. Conference proceedingspt_BR
dc.publisher.cityNew York, NYpt_BR
dc.publisher.countryEstados Unidospt_BR
dc.publisherInstitute of Electrical and Electronics Engineerspt_BR
dc.date.issued2019-
dc.date.monthofcirculationNov.pt_BR
dc.language.isoengpt_BR
dc.description.firstpage3383pt_BR
dc.description.lastpage3389pt_BR
dc.rightsFechadopt_BR
dc.sourceScopuspt_BR
dc.identifier.issn1062-922Xpt_BR
dc.identifier.eissn2577-1655pt_BR
dc.identifier.doi10.1109/SMC.2019.8914550pt_BR
dc.identifier.urlhttps://ieeexplore.ieee.org/document/8914550pt_BR
dc.description.sponsorshipCONSELHO NACIONAL DE DESENVOLVIMENTO CIENTÍFICO E TECNOLÓGICO - CNPQpt_BR
dc.description.sponsorshipCOORDENAÇÃO DE APERFEIÇOAMENTO DE PESSOAL DE NÍVEL SUPERIOR - CAPESpt_BR
dc.description.sponsorshipFUNDAÇÃO DE AMPARO À PESQUISA DO ESTADO DE SÃO PAULO - FAPESPpt_BR
dc.description.sponsordocumentnumber309330/2018-7pt_BR
dc.description.sponsordocumentnumberSem informaçãopt_BR
dc.description.sponsordocumentnumber2017/12646-3pt_BR
dc.date.available2020-06-05T14:02:48Z-
dc.date.accessioned2020-06-05T14:02:48Z-
dc.description.provenanceSubmitted by Bruna Maria Campos da Cunha (bcampos@unicamp.br) on 2020-06-05T14:02:48Z No. of bitstreams: 0. Added 1 bitstream(s) on 2020-09-03T11:55:48Z : No. of bitstreams: 1 2-s2.0-85076731471.pdf: 3845414 bytes, checksum: 4bba82d0bf0b4769288eb488191bab02 (MD5)en
dc.description.provenanceMade available in DSpace on 2020-06-05T14:02:48Z (GMT). No. of bitstreams: 0 Previous issue date: 2019en
dc.identifier.urihttp://repositorio.unicamp.br/jspui/handle/REPOSIP/342755-
dc.description.conferencenomeIEEE International Conference on Systems, Man and Cyberneticspt_BR
dc.contributor.departmentSem informaçãopt_BR
dc.contributor.departmentDepartamento de Sistemas da Informaçãopt_BR
dc.contributor.unidadeInstituto de Computaçãopt_BR
dc.contributor.unidadeInstituto de Computaçãopt_BR
dc.subject.keywordEdge detectionpt_BR
dc.subject.keywordImage resolutionpt_BR
dc.subject.keywordMultilayer neural networkspt_BR
dc.subject.keywordNetwork architecturept_BR
dc.subject.keywordOptical resolving powerpt_BR
dc.subject.keywordSignal to noise ratiopt_BR
dc.subject.keywordConvolutional neural networkpt_BR
dc.subject.keywordHuman visual perceptionpt_BR
dc.subject.keywordImage super resolutionspt_BR
dc.subject.keywordLoss functionspt_BR
dc.subject.keywordPeak signal to noise ratiopt_BR
dc.subject.keywordState-of-the-art algorithmspt_BR
dc.subject.keywordStructural similaritypt_BR
dc.subject.keywordSuper resolutionpt_BR
dc.subject.keywordImage enhancementpt_BR
dc.identifier.source2-s2.0-85076731471pt_BR
dc.creator.orcidorcid.org/0000-0001-6396-4761pt_BR
dc.creator.orcidorcid.org/0000-0003-0125-630Xpt_BR
dc.type.formArtigo de eventopt_BR
dc.identifier.articleid8914550pt_BR
Appears in Collections:IC - Artigos e Outros Documentos

Files in This Item:
File Description SizeFormat 
2-s2.0-85076731471.pdf3.76 MBAdobe PDFView/Open


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