Share Email Print

Proceedings Paper

Recognition of handwritten katakana in a frame using moment invariants based on neural network
Author(s): Takeshi Agui; Hiroki Takahashi; Masayuki Nakajima; Hiroshi Nagahashi
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

A method of pattern recognition using a three layered feedforward neural network is described. Experiments were carried out for handwritten katakana in a frame using neural network. Handwritten characters have varieties of scales, positions, and orientations. In a neural network, however, if the input patterns are shifted in position, rotated, and varied in scales, it does not function well. So we describe a method to solve the problems of these variations using three layered feedforward neural network. We used two kinds of moment values that are invariant for these variations. One is regular moments and the other is Zernike moment, which gives a set of orthogonal complex moments of an image known as Zernike moments. We also describe the problem of the structure of neural networks and the relation between the recognition rate and data sets for similar and different patterns.

Paper Details

Date Published: 1 November 1991
PDF: 10 pages
Proc. SPIE 1606, Visual Communications and Image Processing '91: Image Processing, (1 November 1991); doi: 10.1117/12.50373
Show Author Affiliations
Takeshi Agui, Tokyo Institute of Technology (Japan)
Hiroki Takahashi, Tokyo Institute of Technology (Japan)
Masayuki Nakajima, Tokyo Institute of Technology (Japan)
Hiroshi Nagahashi, Tokyo Institute of Technology (Japan)

Published in SPIE Proceedings Vol. 1606:
Visual Communications and Image Processing '91: Image Processing
Kou-Hu Tzou; Toshio Koga, Editor(s)

© SPIE. Terms of Use
Back to Top