Share Email Print

Proceedings Paper

Training of object classes using mathematical morphology
Author(s): Stephen S. Wilson
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

In some industrial optical character recognition applications, the background of the image surrounding the characters is very confusing and contains clutter that often overlays and connects the characters. Characters are found amidst the clutter by applying a number of morphological structuring elements to the image. Each structuring element is responsible for locating a specific class of characters where all characters in that class are similar to each other. The set of all structuring elements efficiently covers the entire character set. To further reduce noise, other checks such as colinearity and equidistance of the characters in the string are applied. This paper describes an automatic training method for defining efficient classes of structuring elements.

Paper Details

Date Published: 1 April 1992
PDF: 9 pages
Proc. SPIE 1658, Nonlinear Image Processing III, (1 April 1992); doi: 10.1117/12.58383
Show Author Affiliations
Stephen S. Wilson, Applied Intelligent Systems, Inc. (United States)

Published in SPIE Proceedings Vol. 1658:
Nonlinear Image Processing III
Edward R. Dougherty; Jaakko T. Astola; Charles G. Boncelet, Editor(s)

© SPIE. Terms of Use
Back to Top