On-line handwritten cursive character recognition system

During the last two decades have been proposed many handwritten character recognition systems, however until now there are still many limitations, especially for the cursive handwritten characters. In this paper a new algorithm for cursive handwritten characters recognition based on the Spline functions is proposed, in which the inverse process of the handwritten character construction task will be used to recognize the character. From the samples got by using a digitizer board, the sequence of the most significant points (optimal knots) of the handwriting character will be obtained, and then the natural Spline function (Slalom method) and the steepest descent method will be used to interpolate and approximate the character shape. Using a training set consisting of the sequence of optimal knots, each character model will be constructed. Finally the unknown input character will be, compared with each model of all characters to get the similarity scores. The character model with higher similarity score will be considered as the recognized character of the input data. In me recognition stage, two-steps classification is realized detail analysis for some groups of similar characters. The global recognition rate of the proposed system is 94.5%.