A Design of a Hybrid Algorithm for Optical Character Recognition of Online Hand-Written Arabic Alphabets


The growing relevance of printed and digitalized hand-written characters hasnecessitated the need for convalescent automatic recognition of characters in OpticalCharacter Recognition (OCR). Among the handwritten characters, Arabic is one ofthose with special attention due to its distinctive nature, and the inherent challengesin its recognition systems. This distinctiveness of Arabic characters, with thedifference in personal writing styles and proficiency, are complicating theeffectiveness of its online handwritten recognition systems. This research, based onlimitations and scope of previous related studies, studied the recognition of Arabicisolated characters through the identification of its features and dots in view ofproducing an efficient online Arabic handwriting isolated character recognitionsystem. It proposes a hybrid of decision tree and Artificial Neural Network (ANN),as against being combined with other algorithms as found in previous studies. Theproposed recognition process has four main steps with associated sub-steps. Theresults showed that the proposed method achieved the highest performance at96.7%, whereas the benchmark methods which are EDMS and Naeimizaghiani had68.88% and 78.5 % respectively. Based on this, ANN has the best performancerecognition rate at 98.8%, while the best rate for decision tree was obtained at97.2%.