Pattern recognition properties of various feature spaces for higherorder neural networks
Schmidt, W.A.C.
Davis, J.P.
US Naval Air Dev. Center, Warminster, PA;
This paper appears in: Pattern Analysis and Machine Intelligence, IEEE Transactions on
Publication Date: Aug 1993
Volume: 15,
Issue: 8
On page(s): 795-801
ISSN: 0162-8828
References Cited: 8
CODEN: ITPIDJ
INSPEC Accession Number: 4500754
Digital Object Identifier: 10.1109/34.236250
Current Version Published: 2002-08-06
Abstract
The authors explore alternatives that reduce the number of network
weights while maintaining geometric invariant properties for recognizing
patterns in real-time processing applications. This study is limited to
translation and rotation invariance. The primary interest is in
examining the properties of various feature spaces for higher-order
neural networks (HONNs), in correlated and uncorrelated noise, such as
the effect of various types of input features, feature size and number
of feature pixels, and effect of scene size. The robustness of HONN
training is considered in terms of target detectability. The
experimental setup consists of a 15×20 pixel scene possibly
containing a 3×10 target. Each trial used 500 training scenes plus
500 testing scenes. Results indicate that HONNs yield similar geometric
invariant target recognition properties to classical template matching.
However, the HONNs require an order of magnitude less computer
processing time compared with template matching. Results also indicate
that HONNs could be considered for real-time target recognition
applications
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
