Bibtex entry:

@article{pr:Kov95b,
   keywords = {ocr, pattern recognition, classifiers, algorithms,
               neural networks},
   author = {Zs. M. Kovacs},
   title="A Novel Architecture for High Quality Hand-Printed Character
          Recognition",
   key={pr:Kov95b},
   journal= {Pattern Recognition},
   volume = {28},
   number = {11},
   pages = {1685--1692},
   month = {Nov},
   year = {1995},
   abstract={
A new architecture for statistical classification of hand-printed
characters is presented. It is based on standard preprocessing and
three feature types, containing geometrical information on the
position of the pixels, on the contour orientation and on the bending
points, respectively. Two feature vectors at a time are used as inputs
to a multi-layer perceptron-based classifier, giving rise to three
simple classifiers operating in parallel.  The outputs of the three
different classifiers are mixed by a final supervisor realized by a
perceptron layer. The overall network has been trained using digits,
upper and lower case letters of the NIST Special Database 3.
Classification results of the NIST Test Data 1 are provided.  The
system has an error rate of 2.59% on the digits of NIST Test Data 1 at
zero rejection rate, while it has 2.99% and 11.00% error rate on the
upper and lower case letters respectively.
},
}

Microelectronics Group Home Page	Staff
Research Activities	Teaching Activity
Publications	Local Stuff
DEIS Home Page	University of Bologna Home Page