TR available

[Dr. Josef Skrzypek]

UCLA MPL TR 89-10

	Visual Recognition of Script Characters;
	 Neural Network Architectures.

 		     Josef Skrzypek 
	              Jeff Hoffman 

		 Machine Perception Laboratory 
		  Computer Science Department 
		   University of California 
		    Los Angeles, CA 90024
 

Visual recognition of script characters is introduced in the context of
the neural network paradigm and the results of applying one specific
neural architecture are analyzed. First, computer classification of
script characters is partitioned into preprocessing, recognition and
postprocessing techniques which are briefly reviewed in terms of
suitability for implementation as neural net architectures. The second
part of the paper introduces one example of neural net solution to
script recognition.  Handwriting is assumed to be defined as
concatenation of ballistic hand movements where characters can be
represented as functions of position and velocity. We adapt a
hypothesized model of human script generation where characters can be
composed from a limited number of basic strokes which are learned using
visual and positional feedback. The neural representation of these
characters is used for assembling motor program during writing and it
can be used for their visual recognition during reading. A modified,
three-layer "backpropagation" algorithm is used to learn features of
each single character that are independent of writing style.
Preliminary results suggest 80% recognition rate.