Share Email Print
cover

Proceedings Paper

Layered object recognition system using a hierarchical hybrid neural network architecture
Author(s): Srinivasan Raghavan; Naresh Gupta; Barbara A. Lambird; David Lavine; Laveen N. Kanall
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

A layered object recognition paradigm is described in this paper. The lower layers of the proposed system extracts rich feature information in the sense of a primal sketch including oriented edges, blobs, corners, and texture primitives from a raw image. The middle layers of the system extracts object parts such as faces, sides and adjacency relationships between them. The highest layers of the system use the information obtained beneath them to recognize the objects. The system consists of a combination of different types of neural networks making appropriate use of their different capabilities. That is, a collection of unsupervised neural networks are employed for generic feature extraction, while a similar collection of supervised networks are employed for learning object-specific shape information. We present some results of a partial implementation of this system.

Paper Details

Date Published: 1 February 1992
PDF: 12 pages
Proc. SPIE 1609, Model-Based Vision Development and Tools, (1 February 1992); doi: 10.1117/12.57112
Show Author Affiliations
Srinivasan Raghavan, LNK Corp. (United States)
Naresh Gupta, LNK Corp. (United States)
Barbara A. Lambird, LNK Corp. (United States)
David Lavine, LNK Corp. (United States)
Laveen N. Kanall, LNK Corp. (United States)


Published in SPIE Proceedings Vol. 1609:
Model-Based Vision Development and Tools
Rodney M. Larson; Hatem N. Nasr, Editor(s)

© SPIE. Terms of Use
Back to Top