Implementation and design of a new model of neural network with application to typographical character recognition

Author

Gómez, J.M. ; López, O. ; Montes, M. ; Bota, S.A. ; Juvells, I. ; Herms, A.

Author_Institution

Fac. de Fisica, Barcelona Univ., Spain

Volume

1

fYear

1996

fDate

16-19 Sep 1996

Firstpage

201

Abstract

Neural networks have received considerable attention during the lasts years, specially in the field of image recognition. On the other hand, error correcting codes are widely applied to the sampling system, transmission and storage of digital data. A new model of neural network has been developed, considering that a group of images can define a code. Also, an ASIC that is suitable for recognising a set or typographical characters has been designed. A description of the model, the basic architecture and the working modes of the designed circuit is presented

Keywords

CMOS digital integrated circuits; application specific integrated circuits; character recognition; digital signal processing chips; error correction codes; image recognition; learning (artificial intelligence); neural chips; ASIC; CMOS technology; circuit architecture; data transmission; digital data storage; error correcting codes; image recognition; neural networks; sampling system; supervised learning; typographical character recognition; Application specific integrated circuits; Character recognition; Error correction; Error correction codes; Image recognition; Laboratories; Neural networks; Optical character recognition software; Optical computing; Optical materials;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing, 1996. Proceedings., International Conference on

Conference_Location

Lausanne

Print_ISBN

0-7803-3259-8

Type

conf

DOI

10.1109/ICIP.1996.560658

Filename

560658