A New Approach for the Extraction of Handwriting Perceptual Codes using Fuzzy Logic

In this paper we present a new method to extract the elementary perceptual codes from on-line handwriting scripts. This approach uses the advantages of fuzzy sets theory to classify the on-line handwriting strokes into elementary perceptual codes and the Betaelliptic model for the generation of complex handwriting movements. Human perceptual system is based on some basic features in order to read, write and recognize handwriting. These features are the elementary perceptual codes (EPC) which are on the base to identify patterns. The writing process implies the use of many constraints including the psychological and the physiological ones of the writer. This new method has been tested on the developed data base containing characters, digits and Arabic texts. The achieved results show successful representations of handwritten script with EPCs. Good recognition rates are also reached where the elementary perceptual codes are applied as the characteristics vector of an on-line handwriting Arabic recognition system.