Share Email Print
cover

Proceedings Paper

Multistaged neural network architecture for position invariant shape recognition
Author(s): Jay I. Minnix; Eugene S. McVey; Rafael M. Inigo
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

This paper presents a pattern recognition system that self-organizes to recognize objects by shape as part of an Integrated Visual Network (IVN) for autonomous flight control. The system uses a multistaged hierarchical neural network that exhibits insensitivity to the location of the object in the visual field. The network''s three layers perform the functionally disjoint tasks of preprocessing (dynamic thresholding) invariance (position normalization) and recognition (identification of the shape). The Preprocessing stage uses a single layer of elements to dynamically threshold the grey level input image into a binary image. The Invariance stage is a multilayered neural network implementation of a modified Waish-Hadamard transform that generates a representation of the object that is invariant with respect to the object''s position. The Recognition stage is a modified version of Fukushima''s Neocognitron that identifies the position normalized representation by shape. The inclusion of the Preprocessing and Invariance stages allows reduction of the massively replicated processing structures used for translation invariance in the Neocognitron. This system offers roughly the same translation invariance capabilities as the Neocognitron with a dramatic reduction in the number of elements and the network''s interconnection complexity.

Paper Details

Date Published: 1 September 1990
PDF: 11 pages
Proc. SPIE 1360, Visual Communications and Image Processing '90: Fifth in a Series, (1 September 1990); doi: 10.1117/12.24106
Show Author Affiliations
Jay I. Minnix, Stanford Telcommunications Inc (United States)
Eugene S. McVey, Univ. of Virginia (United States)
Rafael M. Inigo, Univ. of Virginia (United States)


Published in SPIE Proceedings Vol. 1360:
Visual Communications and Image Processing '90: Fifth in a Series
Murat Kunt, Editor(s)

© SPIE. Terms of Use
Back to Top