An On-line Arabic Handwriting Recognition System: Based on a New On-line Graphemes Segmentation Technique

In this paper we present a new system for on-line Arabic handwriting recognition based on a new on-line graphemes segmentation technique that depends on the local writing direction. Baseline detection, delayed strokes detection, PAW (Piece of Arabic Word) main stroke construction, and characters construction from the basic graphemes are issues that are addressed in this paper. Experiments are performed on the ADAB-database to validate the system and the segmentation method. The results show a significant improvement in terms of the contribution of segmentation errors to the overall system errors while providing high performance with a simple on-line feature extraction.