%0 Conference Proceedings
%4 sid.inpe.br/sibgrapi/2013/01.21.16.33
%2 sid.inpe.br/sibgrapi/2013/01.21.16.33.42
%@isbn 978-85-7669-272-0
%T A radial basis function neural network for parts identification of three dimensional shapes
%D 1994
%A Borges, Díbio Leandro,
%A Orr, Mark J.,
%A Fisher, Robert B.,
%@affiliation Department of Artificial Intelligence of Edinburgh University
%@affiliation Centre for Cognitive Science of Edinburgh University
%@affiliation Centre for Cognitive Science of Edinburgh University
%E Freitas, Carla dal Sasso,
%E Geus, Klaus de,
%E Scheer, Sérgio,
%B Simpósio Brasileiro de Computação Gráfica e Processamento de Imagens, 7 (SIBGRAPI)
%C Curitiba, PR, Brazil
%8 9-11 Nov. 1994
%I Sociedade Brasileira de Computação
%J Porto Alegre
%V 1
%P 77-84
%S Anais
%K function neural, function neural, image understanding.
%X This discrimination of volumetric pieces or parts of objects from range data is one key element for achieving 3-D object recognition. In this paper it is shown that previously segmented and acquired super quadrics from range data can be reliably mapped into a set of qualitative volumetric shapes (geons) by means of an RBF (Radial Basis Function) neural network classifier. We use a regularized RBF classifier and the results are shown to be both reliable and efficient in the context of range image understanding.
%9 Visão Computacional
%@language en
%3 11 A radial basis function neural network.pdf