Please use this identifier to cite or link to this item:
Full metadata record
DC FieldValueLanguage
dc.contributor.authorSouza, Osvaldo de-
dc.contributor.authorCortez, Paulo Cesar-
dc.contributor.authorSilva, Francisco de Assis Tavares Ferreira da-
dc.identifier.citationSOUSA, 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.pt_BR
dc.description.abstractIn 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.pt_BR
dc.rightsAcesso Abertopt_BR
dc.subjectArtificial neural networkpt_BR
dc.subjectDigital image compressionpt_BR
dc.subjectNeural network benchmarkpt_BR
dc.subjectMorphological neural networkpt_BR
dc.subjectVector quantizationpt_BR
dc.subjectMathematical morphologypt_BR
dc.titleArtificial neural networks for compression of gray scale images: a benchmarkpt_BR
dc.typeArtigo de Eventopt_BR
Appears in Collections:DCINF - Trabalhos apresentados em eventos

Files in This Item:
File Description SizeFormat 
2013_eve_osouza.pdf1,31 MBAdobe PDFView/Open

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