Neural networks with hybrid morphological/rank/linear nodes and their application to handwritten character recognition

Author

Pessoa, Lucio F. C. ; Maragos, Petros

Author_Institution

Georgia Inst. of Technol., Atlanta, GA, USA

fYear

1998

fDate

8-11 Sept. 1998

Firstpage

1

Lastpage

4

Abstract

We propose a general class of multilayer feed-forward neural networks where the combination of inputs in every node is formed by hybrid linear and nonlinear (of the morphological/rank type) operations. For its design we formulate a methodology using ideas from the back-propagation algorithm and robust techniques to circumvent the non-differentiability of rank functions. Experimental results in a problem of handwritten character recognition are described and illustrate some of the properties of this new type of nonlinear systems.

Keywords

backpropagation; handwritten character recognition; mathematical morphology; multilayer perceptrons; nonlinear systems; backpropagation algorithm; handwritten character recognition; hybrid morphological-rank-linear nodes; multilayer feedforward neural networks; nonlinear operations; nonlinear systems; robust techniques; Algorithm design and analysis; Artificial neural networks; Frequency modulation; Image processing; Nonhomogeneous media; Training;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing Conference (EUSIPCO 1998), 9th European

Conference_Location

Rhodes

Print_ISBN

978-960-7620-06-4

Type

conf

Filename

7089930