Share Email Print

Proceedings Paper

Syntactic neural network for character recognition
Author(s): Viktor A. Jaravine
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

This article presents a synergism of syntactic 2-D parsing of images and multilayered, feed- forward network techniques. This approach makes it possible to build a written text reading system with absolute recognition rate for unambiguous text strings. The Syntactic Neural Network (SNN) is created during image parsing process by capturing the higher order statistical structure in the ensemble of input image examples. Acquired knowledge is stored in the form of hierarchical image elements dictionary and syntactic network. The number of hidden layers and neuron units is not fixed and is determined by the structural complexity of the teaching set. A proposed syntactic neuron differs from conventional numerical neuron by its symbolic input/output and usage of the dictionary for determining the output. This approach guarantees exact recognition of an image that is a combinatorial variation of the images from the training set. The system is taught to generalize and to make stochastic parsing of distorted and shifted patterns. The generalizations enables the system to perform continuous incremental optimization of its work. New image data learned by SNN doesn''t interfere with previously stored knowledge, thus leading to unlimited storage capacity of the network.

Paper Details

Date Published: 1 August 1992
PDF: 9 pages
Proc. SPIE 1661, Machine Vision Applications in Character Recognition and Industrial Inspection, (1 August 1992); doi: 10.1117/12.130289
Show Author Affiliations
Viktor A. Jaravine, Kingston Polytechnic (United Kingdom)

Published in SPIE Proceedings Vol. 1661:
Machine Vision Applications in Character Recognition and Industrial Inspection
Donald P. D'Amato; Wolf-Ekkehard Blanz; Byron E. Dom; Sargur N. Srihari, Editor(s)

© SPIE. Terms of Use
Back to Top