Share Email Print

Proceedings Paper

Invariant image recognition by neural networks and modified moment invariants
Author(s): Dayong Wang; Weixing Xie
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

In this paper, a neural networks based approach for distortion invariant image recognition is presented. To reduce the dimension of the required networks, as well as to achieve invariancy, six distortion-invariant feature are extracted from each image and are used as inputs to the neural networks. These six features are derived from the modified geometrical moments of the image, which are calculated through a corrected discrete formula for computing moments more accurately. A multilayer perceptron network trained by the back-propagation algorithm can carry out the classification based on the above features. Experimental results on industrial tools and character recognition are to be given.

Paper Details

Date Published: 30 September 1996
PDF: 7 pages
Proc. SPIE 2898, Electronic Imaging and Multimedia Systems, (30 September 1996); doi: 10.1117/12.253401
Show Author Affiliations
Dayong Wang, Beijing Polytechnic Univ. (China)
Weixing Xie, Xidian Univ. (China)

Published in SPIE Proceedings Vol. 2898:
Electronic Imaging and Multimedia Systems
Chung-Sheng Li; Robert L. Stevenson; LiWei Zhou, Editor(s)

© SPIE. Terms of Use
Back to Top