A new interactive pattern recognition approach by multilayer neural networks and mathematical morphology

Author

Daoudi, Mohamed ; Benslimane, Rachid ; Hamad, Denis ; Postaire, Jack-Gerard

Author_Institution

Centre d´´Autom., Univ. des Sci. et Tech. de Lille Flandres Artois, Villeneuve d´´Ascq, France

fYear

1993

fDate

17-20 Oct 1993

Firstpage

125

Abstract

We describe an online interactive graphic system which has been designed to separate a set of multidimensional multivariate observations into groups or clusters. A neural network allows one to map the data onto a two dimensional display. We propose a new clustering approach based on the so called “watershed” algorithm which takes advantage of the two dimensional display

Keywords

feedforward neural nets; interactive systems; mathematical morphology; multilayer perceptrons; pattern classification; clustering approach; interactive pattern recognition approach; mathematical morphology; multidimensional multivariate observations; multilayer neural networks; online interactive graphic system; two dimensional display; watershed algorithm; Clustering algorithms; Graphics; Humans; Morphology; Multi-layer neural network; Multidimensional systems; Neural networks; Pattern classification; Pattern recognition; Two dimensional displays;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man and Cybernetics, 1993. 'Systems Engineering in the Service of Humans', Conference Proceedings., International Conference on

Conference_Location

Le Touquet

Print_ISBN

0-7803-0911-1

Type

conf

DOI

10.1109/ICSMC.1993.390695

Filename

390695