Online Urdu Handwritten Character Recognition: Initial Half Form Single Stroke Characters

摘要: Necessity of unfolding the enticing field handwritten character recognition is revealed with mushroom growth portable devices. Effective human machine interaction insists development a reliable and efficient online system. The quest becomes more challenging when it involves Urdu script based languages especially written in Nastalique font. Urdu, style, context sensitive highly cursive language. Difficulty arises this style writing as shape depends whether isolated, initial, medial or terminal position word. In paper, characters their initial half form have been studied. Data collected using pen-tablet signal stored binary file containing x y coordinates pressure values rather than an image to reduce complexity problem. Wavelets transform applied analyze signal. Back propagation neural network classifier for single stroke designed overall accuracy 91.3%.