Share Email Print

Proceedings Paper

Character recognition using a multistage neural network
Author(s): Ismail I. Jouny; Matthew Sheridan
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

This paper uses two stages of multi-layer neural networks for character recognition. In the first stage, each neural network is trained to recognize a segment of the character image. The responses are then presented to another network where the final decision is made. The proposed method is computationally efficient, fault tolerant, has an associative memory capability, and has some of the merits of multi-decision pattern recognition techniques. The features used are gray-level representations of both typed and hand-written upper case characters. The proposed recognition scheme is tested extensively and its performance is compared with that of other non-parametric recognition methods.

Paper Details

Date Published: 16 September 1992
PDF: 10 pages
Proc. SPIE 1700, Automatic Object Recognition II, (16 September 1992); doi: 10.1117/12.138308
Show Author Affiliations
Ismail I. Jouny, Lafayette College (United States)
Matthew Sheridan, Lafayette College (United States)

Published in SPIE Proceedings Vol. 1700:
Automatic Object Recognition II
Firooz A. Sadjadi, Editor(s)

© SPIE. Terms of Use
Back to Top