Handwritten character recognition using steerable filters and neural networks

Author

Talleux, Samuel ; Tavsanoglu, Vedat ; Tufan, Emir

Author_Institution

Sch. of Electr., Electron. & Inf. Eng., South Bank Univ., London, UK

Volume

5

fYear

1998

fDate

31 May-3 Jun 1998

Firstpage

341

Abstract

In this paper a system for handwritten character recognition has been developed using a steerable filter and a neural network where the former yields the local direction of dominant orientation while the latter, using this feature, recognises the character. Two different models of neural networks have been tested: (i) the single layer perceptron with error correction and (ii) multilayer perceptron with backpropagation algorithm. The pre-processing consists of several stages

Keywords

backpropagation; character recognition; error correction; neural nets; perceptrons; backpropagation algorithm; dominant orientation; error correction; handwritten character recognition; local direction; multilayer perceptron; neural networks; single layer perceptron; steerable filters; Band pass filters; Character recognition; Gaussian processes; Handwriting recognition; Information filtering; Information filters; Multilayer perceptrons; Neural networks; Noise reduction; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 1998. ISCAS '98. Proceedings of the 1998 IEEE International Symposium on

Conference_Location

Monterey, CA

Print_ISBN

0-7803-4455-3

Type

conf

DOI

10.1109/ISCAS.1998.694486

Filename

694486