Share Email Print
cover

Proceedings Paper

Rotation invariant object classification using fast Fourier transform features
Author(s): Mehmet Celenk; Srinivasa Rao Datari
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

This paper describes a position and rotation invariant fast object classification scheme. A parallel region growing technique is used to detect objects in binary images. 2D fast Fourier transform (FFT) is applied to each object region after translating the origin of the image coordinate system to the object center and aligning the image coordinate axes with the object's principal axes. The first five components from the principal lobe of the Fourier spectrum of each object are selected as characteristic features for minimum-distance classification. For time efficiency, region growing and 2D FFT computations were performed on a 16-node hypercube processor.

Paper Details

Date Published: 1 March 1991
PDF: 12 pages
Proc. SPIE 1468, Applications of Artificial Intelligence IX, (1 March 1991); doi: 10.1117/12.45514
Show Author Affiliations
Mehmet Celenk, Ohio Univ. (United States)
Srinivasa Rao Datari, Simco/Ramic Co. (United States)


Published in SPIE Proceedings Vol. 1468:
Applications of Artificial Intelligence IX
Mohan M. Trivedi, Editor(s)

© SPIE. Terms of Use
Back to Top