Artificial neural networks for compression of gray scale images: a benchmark

Detalhes bibliográficos
Autor(a) principal: Souza, Osvaldo de
Data de Publicação: 2013
Outros Autores: Cortez, Paulo Cesar, Silva, Francisco de Assis Tavares Ferreira da
Tipo de documento: Artigo de conferência
Idioma: eng
Título da fonte: Repositório Institucional da Universidade Federal do Ceará (UFC)
Texto Completo: http://www.repositorio.ufc.br/handle/riufc/19036
Resumo: In this paper we present results for an investigation of the use of neural networks for the compression of digital images. The main objective of this investigation is the establishment of a ranking of the performance of neural networks with different architectures and different principles of convergence. The ranking involves backpropagation networks (BPNs), hierarchical back-propagation network (HBPN), adaptive back-propagation network (ABPN), a self-organizing maps (KSOM), hierarchically self-organizing maps (HSOM), radial basis function neural networks (RBF) and a supervised Morphological neural networks (SMNN). For the SMNN, considering that it is a neural network recently introduced, an explanation is presented for use in image compression. Gray scale image of Lena were used as the sample image for all network covered in this research. The best result is compression rate of 195.54 with PSNR = 22.97.
id UFC-7_89a04f7683a53e7236cb2fdafa4130b8
oai_identifier_str oai:repositorio.ufc.br:riufc/19036
network_acronym_str UFC-7
network_name_str Repositório Institucional da Universidade Federal do Ceará (UFC)
repository_id_str
spelling Artificial neural networks for compression of gray scale images: a benchmarkArtificial neural networkDigital image compressionNeural network benchmarkMorphological neural networkVector quantizationMathematical morphologyIn this paper we present results for an investigation of the use of neural networks for the compression of digital images. The main objective of this investigation is the establishment of a ranking of the performance of neural networks with different architectures and different principles of convergence. The ranking involves backpropagation networks (BPNs), hierarchical back-propagation network (HBPN), adaptive back-propagation network (ABPN), a self-organizing maps (KSOM), hierarchically self-organizing maps (HSOM), radial basis function neural networks (RBF) and a supervised Morphological neural networks (SMNN). For the SMNN, considering that it is a neural network recently introduced, an explanation is presented for use in image compression. Gray scale image of Lena were used as the sample image for all network covered in this research. The best result is compression rate of 195.54 with PSNR = 22.97.SBC2016-08-09T18:22:47Z2016-08-09T18:22:47Z2013info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObjectapplication/pdfSOUSA, Osvaldo de; CORTEZ, Paulo Cesar; SILVA, Francisco de Assis Tavares Ferreira da. Artificial neural networks for compression of gray scale images: a benchmark. In: National Meeting on Artificial and Computational Intelligence, 10., 2013, Fortaleza. Anais... Fortaleza: SBC, 2013.http://www.repositorio.ufc.br/handle/riufc/19036Souza, Osvaldo deCortez, Paulo CesarSilva, Francisco de Assis Tavares Ferreira dainfo:eu-repo/semantics/openAccessengreponame:Repositório Institucional da Universidade Federal do Ceará (UFC)instname:Universidade Federal do Ceará (UFC)instacron:UFC2023-10-30T18:22:01Zoai:repositorio.ufc.br:riufc/19036Repositório InstitucionalPUBhttp://www.repositorio.ufc.br/ri-oai/requestbu@ufc.br || repositorio@ufc.bropendoar:2024-09-11T18:27:46.705177Repositório Institucional da Universidade Federal do Ceará (UFC) - Universidade Federal do Ceará (UFC)false
dc.title.none.fl_str_mv Artificial neural networks for compression of gray scale images: a benchmark
title Artificial neural networks for compression of gray scale images: a benchmark
spellingShingle Artificial neural networks for compression of gray scale images: a benchmark
Souza, Osvaldo de
Artificial neural network
Digital image compression
Neural network benchmark
Morphological neural network
Vector quantization
Mathematical morphology
title_short Artificial neural networks for compression of gray scale images: a benchmark
title_full Artificial neural networks for compression of gray scale images: a benchmark
title_fullStr Artificial neural networks for compression of gray scale images: a benchmark
title_full_unstemmed Artificial neural networks for compression of gray scale images: a benchmark
title_sort Artificial neural networks for compression of gray scale images: a benchmark
author Souza, Osvaldo de
author_facet Souza, Osvaldo de
Cortez, Paulo Cesar
Silva, Francisco de Assis Tavares Ferreira da
author_role author
author2 Cortez, Paulo Cesar
Silva, Francisco de Assis Tavares Ferreira da
author2_role author
author
dc.contributor.author.fl_str_mv Souza, Osvaldo de
Cortez, Paulo Cesar
Silva, Francisco de Assis Tavares Ferreira da
dc.subject.por.fl_str_mv Artificial neural network
Digital image compression
Neural network benchmark
Morphological neural network
Vector quantization
Mathematical morphology
topic Artificial neural network
Digital image compression
Neural network benchmark
Morphological neural network
Vector quantization
Mathematical morphology
description In this paper we present results for an investigation of the use of neural networks for the compression of digital images. The main objective of this investigation is the establishment of a ranking of the performance of neural networks with different architectures and different principles of convergence. The ranking involves backpropagation networks (BPNs), hierarchical back-propagation network (HBPN), adaptive back-propagation network (ABPN), a self-organizing maps (KSOM), hierarchically self-organizing maps (HSOM), radial basis function neural networks (RBF) and a supervised Morphological neural networks (SMNN). For the SMNN, considering that it is a neural network recently introduced, an explanation is presented for use in image compression. Gray scale image of Lena were used as the sample image for all network covered in this research. The best result is compression rate of 195.54 with PSNR = 22.97.
publishDate 2013
dc.date.none.fl_str_mv 2013
2016-08-09T18:22:47Z
2016-08-09T18:22:47Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/conferenceObject
format conferenceObject
status_str publishedVersion
dc.identifier.uri.fl_str_mv SOUSA, Osvaldo de; CORTEZ, Paulo Cesar; SILVA, Francisco de Assis Tavares Ferreira da. Artificial neural networks for compression of gray scale images: a benchmark. In: National Meeting on Artificial and Computational Intelligence, 10., 2013, Fortaleza. Anais... Fortaleza: SBC, 2013.
http://www.repositorio.ufc.br/handle/riufc/19036
identifier_str_mv SOUSA, Osvaldo de; CORTEZ, Paulo Cesar; SILVA, Francisco de Assis Tavares Ferreira da. Artificial neural networks for compression of gray scale images: a benchmark. In: National Meeting on Artificial and Computational Intelligence, 10., 2013, Fortaleza. Anais... Fortaleza: SBC, 2013.
url http://www.repositorio.ufc.br/handle/riufc/19036
dc.language.iso.fl_str_mv eng
language eng
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv SBC
publisher.none.fl_str_mv SBC
dc.source.none.fl_str_mv reponame:Repositório Institucional da Universidade Federal do Ceará (UFC)
instname:Universidade Federal do Ceará (UFC)
instacron:UFC
instname_str Universidade Federal do Ceará (UFC)
instacron_str UFC
institution UFC
reponame_str Repositório Institucional da Universidade Federal do Ceará (UFC)
collection Repositório Institucional da Universidade Federal do Ceará (UFC)
repository.name.fl_str_mv Repositório Institucional da Universidade Federal do Ceará (UFC) - Universidade Federal do Ceará (UFC)
repository.mail.fl_str_mv bu@ufc.br || repositorio@ufc.br
_version_ 1813028813999702016