Share Email Print

Journal of Electronic Imaging

Hardware-implementable neural network for rotation-scaling invariant pattern classification
Author(s): Rafael M. Inigo; Catherine Q. Xu; Begona C. Arrue; Eugene S. McVey
Format Member Price Non-Member Price
PDF $20.00 $25.00

Paper Abstract

The design, hardware implementation, and simulation of a shift invariant pattern recognizer based on a modified higher order neural network (MHONN) is presented. When the MHONN is integrated with centroid calculation and logarithmic spiral mapping subsystems, translation, rotation around the optical axis, and scaling invariant pattern recognition can be achieved. The design objective is to deal with large-scale images with possible pattern deformation, noise, and highly textured backgrounds. Images are acquired with a 256 x 256 infrared sensor. We describe the theory of the MHONN, its hardware implementation, and simulation results.

Paper Details

Date Published: 1 July 1992
PDF: 20 pages
J. Electron. Imag. 1(3) doi: 10.1117/12.60033
Published in: Journal of Electronic Imaging Volume 1, Issue 3
Show Author Affiliations
Rafael M. Inigo, Univ. of Virginia (United States)
Catherine Q. Xu, ARIC (United States)
Begona C. Arrue, Univ. of Virginia (United States)
Eugene S. McVey, Univ. of Virginia (United States)

© SPIE. Terms of Use
Back to Top