Share Email Print

Proceedings Paper

Pattern Recognition With Multiaperture Optics System
Author(s): Richard T. Schneider; James F. Long; Martin F. Wehling
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

The application of multiaperture optics systems for pattern recognition is discussed. Multiaperture optics systems inherently perform some degree of optical preprocessing which reduces the amount of information offered to the system to a manageable level and so simplifies pattern recognition. The architecture of a typical multiaperture optics system is described and the performance of the system is computed. Due to the large number of lenses, a special detector array is required. Each detector terminates into a memory location which can be randomly accessed. The architecture of the multiaperture system requires special algorithms for pattern recognition. The basic idea is to treat each eyelet as a binary digit. It is shown that only one number is required to describe a given shape. Recognition is accomplished by looking up the stored recognition number.

Paper Details

Date Published: 9 January 1984
PDF: 10 pages
Proc. SPIE 0432, Applications of Digital Image Processing VI, (9 January 1984); doi: 10.1117/12.936686
Show Author Affiliations
Richard T. Schneider, University of Florida (United States)
James F. Long, Eglin AFB (United States)
Martin F. Wehling, Eglin AFB (United States)

Published in SPIE Proceedings Vol. 0432:
Applications of Digital Image Processing VI
Andrew G. Tescher, Editor(s)

© SPIE. Terms of Use
Back to Top