1992
@techreport{FoS1992a,
vgclass = {report},
vgproject = {nn},
author = {Thomas Fontaine and Lokendra Shastri},
title = {Character Recognition Using a Modular Spatiotemporal Connectionist Model},
number = {MS-CIS-92-24},
institution = {University of Pennsylvania},
address = {Philadelphia, PA 19104-6389},
month = {March},
year = {1992},
abstract = {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 for handprinted digit recognition are among the best reported
to date on a set of real-world ZIP code digit images, provided by the
United States Postal Service. The system achieved a 99.1\% recognition
rate on the training set and a 96\% 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.},
}