Share Email Print

Proceedings Paper

Rotation Invariant Pattern Recognition
Author(s): H. H. Arsenault; Y. N. Hsu; K. Chalasinska-Macukow; Y. Yang
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Conventional matched filtering is sensitive to rotation of the object to be detected. If the target object is rotated, the signal to noise ratio of the output correlation is reduced with the result that the object may not be detected. Efforts have been made towards developing matched filters with signal to noise ratios that are space invariant and rotation invariant with respect to the target. Our latest approach has been to extract from the target some circular harmonic component, and to use a filter matched to this component. A complete digital simulation using simple two-dimensional objects has resulted in the successful detection of rotated target objects in a field of different objects. The same technique has also been implemented in an optical processor using computer generated holograms. To discriminate between objects that are almost similar, a pseudo-object is used to generate the matched filter.

Paper Details

Date Published: 17 March 1983
PDF: 7 pages
Proc. SPIE 0359, Applications of Digital Image Processing IV, (17 March 1983); doi: 10.1117/12.965974
Show Author Affiliations
H. H. Arsenault, Universite Laval (Canada)
Y. N. Hsu, Sian Research Institute of Radio Technology (China)
K. Chalasinska-Macukow, University of Warsaw (Poland)
Y. Yang, Northwestern University (China)

Published in SPIE Proceedings Vol. 0359:
Applications of Digital Image Processing IV
Andrew G. Tescher, Editor(s)

© SPIE. Terms of Use
Back to Top