Close
Metadata

%0 Conference Proceedings
%4 sid.inpe.br/sibgrapi/2012/12.17.13.52
%2 sid.inpe.br/sibgrapi/2012/12.17.13.52.37
%@isbn 978-85-7669-271-3
%A Costa, Luciano da Fontoura,
%A Joo, Javier Montenegro,
%A Köberle, Roland,
%@affiliation Instituto de Física e Química de São Carlos (IFQSC) da Universidade de São Paulo (USP)
%@affiliation Instituto de Física e Química de São Carlos (IFQSC) da Universidade de São Paulo (USP)
%@affiliation Instituto de Física e Química de São Carlos (IFQSC) da Universidade de São Paulo (USP)
%T Distance-discriminator neural networks for classification and pattern recognition
%B Simpósio Brasileiro de Computação Gráfica e Processamento de Imagens, 6 (SIBGRAPI)
%D 1993
%E Figueiredo, Luiz Henrique de,
%E Gomes, Jonas de Miranda,
%V 1
%S Anais
%8 19 - 22 out. 1993
%J Porto Alegre
%I Sociedade Brasileira de Computação
%C Recife
%K discriminator neural, Distance-discriminator neurons, Distance-discriminator Neural Networks, interfaces.
%X Distance-discriminator neurons DDNs and their combination in Distance-discriminator Neural Networks DDNNs are proposed and discussed. DDNs, based on distance metric concepts, are able to discriminate whether a given point (x,y) belongs to a closed region such as diamond-, rectangle and ellipse-bound regions, which are tasks traditionally performed by perceptrons. DDNs can also be straightforwardly modified in order to discriminate hollow regions having as outer boundaries the above mentioned geometrical figures or even combinations of them. The principal advantage of DDNNs over perceptrons is a substantial reduction of execution time and/or the amount of required hardware operators: many polygonal classification regions which would otherwise demand large perceptron structures can be discriminated with only a few DDNNs. DDNNs can also be easily programmed by design or automatically with the help of the hough transform. Such issues as well as the relative advantages of DDNNs and perceptrons and a complete application example are presented and discussed in the present paper.
%P 221-229
%@language en
%9 Visão por Computador
%3 26 Distance discriminator neural networks.pdf


Close