A New Encoding System: Application to On-line Arabic Handwriting

Abstract

In this paper, we propose a new encoding system for On-line Arabic handwriting. To identify patterns, our human perceptual system is based on basic features called perceptual codes. Analysing handwriting, we notice the existence of elementary and global ones. Gathering the elementary perceptual codes in various constraints we obtain global ones, and to obtain different forms of handwriting, we proceed by combining them. So, we present a new approach to improve handwriting segmentation via perceptual encoding system. This system uses the fuzzy set theory to detect the elementary perceptual codes (EPCs) and the genetic algorithms for the global perceptual ones (GPCs). To validate our new approach, a large Arabic lexicon was developed containing words, alphabet and digits acquired by different writers on digitizing tablet, in addition to ADAB database set. The obtained results show successful representations of Arabic handwritten script via perceptual codes.