A Real Time Numeric Character Recognition System Using Artificial Neural Network

In a Human Computer Interaction System the recognition of any handwritten character plays an important role. The recognition of numeric character is thus a matter of concern in order to operate a computer in a real time environment. In this paper a method of numeric character recognition is proposed where the fingertip movement is used for the recognition of handwritten character recognition. Our finger tip changes its direction during the writing of numeric characters. This variation in angular movements is used to construct the dataset for the recognition system. This angular variation is used as the input of Multilayer Neural Network training and its validity was tested for a number of objects. Experimental result shows that the proposed algorithm shows better result for the real time applications.