TR available in neuroprose

[Thomas Fontaine]

************** PLEASE DO NOT FORWARD TO OTHER NEWSGROUPS ****************

The following technical report has been placed in the neuroprose 
archives at Ohio State University:


		CHARACTER RECOGNITION USING A MODULAR
		  SPATIOTEMPORAL CONNECTIONIST MODEL

		 Thomas Fontaine and Lokendra Shastri

	      Technical Report MS-CIS-92-24/LINC LAB 219

	     Computer and Information Science Department
			200 South 33rd Street
		      University of Pennsylvania
		     Philadelphia, PA 19104-6389


We describe a connectionist model for recognizing handprinted
characters.  Instead of treating the input as a static signal, the
image is scanned over time and converted into a time-varying signal.
The temporalized image is processed by a spatiotemporal connectionist
network suitable for dealing with time-varying signals.  The resulting
system offers several attractive features, including shift-invariance
and inherent retention of local spatial relationships along the
temporalized axis, a reduction in the number of free parameters, and
the ability to process images of arbitrary length.

Connectionist networks were chosen as they offer learnability, rapid
recognition, and attractive commercial possibilities.  A modular and
structured approach was taken in order to simplify network
construction, optimization and analysis.

Results on the task of handprinted digit recognition are among the
best reported to date on a set of real-world ZIP code digit images,
provided by the United Stated Postal Service.  The system achieved a
99.1\% recognition rate on the training set and a 96.0\% recognition
rate on the test set with no rejections.  A 99.0\% recognition rate on
the test set was achieved when 14.6\% of the images were rejected.



************************ How to obtain a copy ************************

I'm sorry, but hardcopies are not available.

To obtain via anonymous ftp:

unix> ftp archive.cis.ohio-state.edu (or 128.146.8.52)
Name: anonymous
Password: neuron
ftp> cd pub/neuroprose
ftp> binary
ftp> get fontaine.charrec.ps.Z
ftp> quit
unix> uncompress fontaine.charrec.ps.Z
unix> lpr fontaine.charrec.ps.Z (or however you print Postscript)

[Please note that some of the figures were produced with a Macintosh
and the resulting Postscript may not print on all printers.  People
using an Apple LaserWriter should have no problems, though.]