Share Email Print
cover

Proceedings Paper

Knowledge-assisted evaluation of fringe patterns for automatic fault detection
Author(s): Wolfgang Osten; Werner P. O. Jueptner; Ulrike Mieth
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Automatic pattern recognition methods combined with a knowledge based approach are used for the detection and classification of fault indicating patterns. For this purpose the complex fringe pattern is reduced to a line pattern (fringe skeleton) and this line pattern is approximated by vectors. The new pattern representation is transformed in a data list preserving the topology and metrics of the original pattern. Based on characteristic symptoms within the pattern features for the description of different pattern classes are derived. The knowledge for the hierarchical classification procedure embedded in decision rules for the knowledge assisted system was derived from model based simulation of fringe patterns and preparation of test objects with different flaws.

Paper Details

Date Published: 1 March 1994
PDF: 13 pages
Proc. SPIE 2004, Interferometry VI: Applications, (1 March 1994); doi: 10.1117/12.172599
Show Author Affiliations
Wolfgang Osten, Bremer Institut fuer Angewandte Strahltechnik (Germany)
Werner P. O. Jueptner, Bremer Institut fuer Angewandte Strahltechnik (Germany)
Ulrike Mieth, Bremer Institut fuer Angewandte Strahltechnik (Germany)


Published in SPIE Proceedings Vol. 2004:
Interferometry VI: Applications
Ryszard J. Pryputniewicz; Gordon M. Brown; Werner P. O. Jueptner, Editor(s)

© SPIE. Terms of Use
Back to Top