Invariant pattern recognition: a review
Wood, J. (1996) Invariant pattern recognition: a review. Pattern Recognition, 29, (1), 1-17.
Download
Full text not available from this repository.
Description/Abstract
In this document we review and compare some of the classical and modern techniques for solving the problem of invariant pattern recognition. Such techniques include integral transforms, construction of algebraic moments and the use of structured neural networks. In all cases we assume that the nature of the invariance group is known a priori. Many of the methods described apply to specific geometrical transformation groups; however some of the techniques are highly general and applicable to large classes of invariance groups. We also review some results regarding the existence and structure of invariants under certain kinds of groups.
| Item Type: | Article |
|---|---|
| Divisions: | Faculty of Physical and Applied Science > Electronics and Computer Science |
| Item ID: | 250472 |
| Date Deposited: | 01 Jun 1999 |
| Last Modified: | 01 Mar 2012 10:18 |
| Contributors: | Wood, J. (Author) |
| Date: | January 1996 |
| Status: | Published |
| Further Information: | Google Scholar |
| ISI Citation Count: | 121 |
| URI: | http://eprints.soton.ac.uk/id/eprint/250472 |
Actions (login required)
 |
View Item |
