Share Email Print

Proceedings Paper

Object classification by using textural and geometric classificators
Author(s): Dirk Foertsch; Uwe Weller
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

This paper presents a typical industrial application of machine vision in order to classify and select different types of cylindrical steel bars in combination with direct process control. The main classification algorithm consists of a combination of several routines, using different image processing methods. On the one hand a textural approach, using first and second order statistics, is used. Typical histogram data in addition with gray level dependence matrices give some textural classification criteria. On the other hand the search and utilization of geometric criteria supply additional features for classification. Several contour measurement routines deliver a set of additional information about the examined bar. The paper offers details about the used classification algorithms. Furthermore it deals with experimental results such as velocity and rate of selection success.

Paper Details

Date Published: 3 October 1995
PDF: 10 pages
Proc. SPIE 2597, Machine Vision Applications, Architectures, and Systems Integration IV, (3 October 1995); doi: 10.1117/12.223969
Show Author Affiliations
Dirk Foertsch, VITRONIC GmbH (Germany)
Uwe Weller, Univ. Siegen (Germany)

Published in SPIE Proceedings Vol. 2597:
Machine Vision Applications, Architectures, and Systems Integration IV
Bruce G. Batchelor; Susan Snell Solomon; Frederick M. Waltz, Editor(s)

© SPIE. Terms of Use
Back to Top