Abstract
Urdu online handwriting recognition is a very challenging task due to its cursive nature. Pre-processing of the raw input strokes is crucial part for the success of character recognition system. The findings from online data are not enough for recognition of Urdu due to the complexities of Urdu Script. This paper describes the preprocessing steps for online character recognition. A novel technique is presented for preprocessing of Urdu online text in which both online and offline domain are used to remove the variations and to increase the efficiency of the recognition system for online input. The proposed technique is also the necessary step towards character recognition, person identification, personality determination where input data is processed from all perspectives.