On-line Handwritten Arabic Character Recognition using Artificial Neural Network

• DOI: 10.5120/8819-2819
• Publication Date: 2012-10-19T11:25:08Z
• Authors: Khaoula Addakiri; Mohamed Bahaj
• Keywords: Line (geometry)

In this paper, an efficient approach for the recognition of online Arabic handwritten characters is presented.The method employed involves three phases: First, pre-processing in which original image transformed into a binary .Second , training neural networks with feed-forward back propagation algorithm .Finally, character through use Neural Network techniques.The proposed tested on 1400 different written by ten users.Each user wrote 28 five times order to get writing variations.Experiment results showed effectiveness our recognizing characters.