Online Arabic Handwritten Character Recognition using Online-Offline Feature Extraction and Back-Propagation Neural Network

The main theme of this paper is performing online handwriting recognition for Arabic character using back propagation neural network and it experiments the performance of it using online features of characters as input to the BPNN in comparison with combining online and offline character features as the input. That's done through the following stages : online data acquisition, online & offline preprocessing, online & offline feature extraction (directional & geometric features), classification using back propagation neural network to classify the character to one of 15 character classes and finally, delayed strokes handling using logic programming to recognize the character according to the character class and its delayed strokes accounts and positions.