Fechar
Metadados

1. Identificação
Tipo de ReferênciaArtigo em Evento (Conference Proceedings)
Sitemtc-m16b.sid.inpe.br
Código do Detentorisadg {BR SPINPE} ibi 8JMKD3MGPCW/3DT298S
Repositóriosid.inpe.br/mtc-m17@80/2007/06.05.18.57
Última Atualização2007:06.05.18.57.07 (UTC) administrator
Repositório de Metadadossid.inpe.br/mtc-m17@80/2007/06.05.18.57.08
Última Atualização dos Metadados2018:06.05.03.34.14 (UTC) administrator
Chave SecundáriaINPE--PRE/
Chave de CitaçãoCastroSilv:2007:NeNeBa
TítuloNeural network based multiscale image restoration approach
Ano2007
Data de Acesso18 maio 2024
Tipo SecundárioPRE CI
Número de Arquivos1
Tamanho13 KiB
2. Contextualização
Autor1 Castro, Ana Paula Abrantes de
2 Silva, José Demísio Simões da
Grupo1 LAC-INPE-MCT-BR
2 LAC-INPE-MCT-BR
Afiliação1 Instituto Nacional de Pesquisas Espaciais (INPE)
2 Instituto Nacional de Pesquisas Espaciais (INPE)
Nome do EventoProceedings of SPIE.
Volume6497
PáginasDOI 10.1117/12.703468
Título do LivroProceedings
Histórico (UTC)2007-06-29 19:12:14 :: rosemary -> administrator ::
2012-10-23 23:53:21 :: administrator -> simone :: 2007
2013-02-20 15:19:57 :: simone -> administrator :: 2007
2018-06-05 03:34:14 :: administrator -> marciana :: 2007
3. Conteúdo e estrutura
É a matriz ou uma cópia?é a matriz
Estágio do Conteúdoconcluido
Transferível1
Tipo do ConteúdoExternal Contribution
Palavras-ChaveNeural networks
image restoration
COMPUTAÇÂO APLICADA
ResumoThis paper describes a neural network based multiscale image restoration approach. Multilayer perceptrons are trained with artificial images of degraded gray level circles, in an attempt to make the neural network learn inherent space relations of the degraded pixels. The present approach simulates the degradation by a low pass Gaussian filter blurring operation and the addition of noise to the pixels at pre-established rates. The training process considers the degraded image as input and the non-degraded image as output for the supervised learning process. The neural network thus performs an inverse operation by recovering a quasi non-degraded image in terms of least squared. The main difference of the approach to existing ones relies on the fact that the space relations are taken from different scales, thus providing relational space data to the neural network. The approach is an attempt to come up with a simple method that leads to an optimum solution to the problem. Considering different window sizes around a pixel simulates the multiscale operation. In the generalization phase the neural network is exposed to indoor, outdoor, and satellite degraded images following the same steps use for the artificial circle image.
ÁreaCOMP
Arranjourlib.net > BDMCI > Fonds > Produção anterior à 2021 > LABAC > Neural network based...
Conteúdo da Pasta docacessar
Conteúdo da Pasta sourcenão têm arquivos
Conteúdo da Pasta agreementnão têm arquivos
4. Condições de acesso e uso
URL dos dadoshttp://mtc-m16b.sid.inpe.br/ibi/sid.inpe.br/mtc-m17@80/2007/06.05.18.57
URL dos dados zipadoshttp://mtc-m16b.sid.inpe.br/zip/sid.inpe.br/mtc-m17@80/2007/06.05.18.57
Idiomaen
Arquivo Alvo2007SPIE.6497E..24D.html
Grupo de Usuáriosadministrator
rosemary
Visibilidadeshown
5. Fontes relacionadas
Unidades Imediatamente Superiores8JMKD3MGPCW/3ESGTTP
Acervo Hospedeirolcp.inpe.br/ignes/2004/02.12.18.39
cptec.inpe.br/walmeida/2003/04.25.17.12
6. Notas
Campos Vaziosarchivingpolicy archivist callnumber conferencelocation copyholder copyright creatorhistory date descriptionlevel dissemination documentstage doi e-mailaddress edition editor electronicmailaddress format identifier isbn issn label lineage mark mirrorrepository nextedition notes numberofvolumes orcid organization parameterlist parentrepositories previousedition previouslowerunit progress project publisher publisheraddress readergroup readpermission resumeid rightsholder schedulinginformation secondarydate secondarymark serieseditor session shorttitle sponsor subject tertiarymark tertiarytype type url versiontype
7. Controle da descrição
e-Mail (login)marciana
atualizar 


Fechar