1 November 1991 Recognition of handwritten katakana in a frame using moment invariants based on neural network
Author Affiliations +
Proceedings Volume 1606, Visual Communications and Image Processing '91: Image Processing; (1991); doi: 10.1117/12.50373
Event: Visual Communications, '91, 1991, Boston, MA, United States
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.
© (1991) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Takeshi Agui, Hiroki Takahashi, Masayuki Nakajima, Hiroshi Nagahashi, "Recognition of handwritten katakana in a frame using moment invariants based on neural network", Proc. SPIE 1606, Visual Communications and Image Processing '91: Image Processing, (1 November 1991); doi: 10.1117/12.50373; https://doi.org/10.1117/12.50373
PROCEEDINGS
10 PAGES


SHARE
KEYWORDS
Neural networks

Image processing

Visual communications

Digital imaging

Optical character recognition

Binary data

Image classification

Back to Top