Neural network techniques for object orientation detection.Solution by optimal feedforward network and learning vector quantizationapproaches
Morris, R.J.T.
Rubin, L.D.
Tirri, H.
AT&T Bell Labs., Holmdel, NJ;
This paper appears in: Pattern Analysis and Machine Intelligence, IEEE Transactions on
Publication Date: Nov 1990
Volume: 12,
Issue: 11
On page(s): 1107-1115
ISSN: 0162-8828
References Cited: 19
CODEN: ITPIDJ
INSPEC Accession Number: 3837633
Digital Object Identifier: 10.1109/34.61712
Current Version Published: 2002-08-06
Abstract
The computer-vision problem of determining object orientation from
the consensus of orientations of individual symbols or marks is
examined. The problem arises in automatic inspection where orientation
can be detected from printed text but there is no knowledge of the
content of the text. This is a high-dimensional classification problem,
and there is a requirement for highly accurate detection and rapid
processing. The typical multilayer threshold networks are seen as
unsuitable, and the optimal Bayesian detector is derived and found to
have the highly parallel structure of a feedforward network. The
learning vector quantization neural network method of T. Kohonen (1988)
is also applied. Experimental results, comparisons, and a complete
implementation are described
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
