A New Approach in Persian Handwriting Recognition Using Writing Path

In this paper, we propose a novel method to recognize online Persian handwritten letters by using the letters´ writing path. We consider the body of letters, as two curves. By comparing the curves of those two functions from input letter with our stored samples, we suggest some possible letters in a sorted list; in which the most similar one to the input letter comes first. Later we use some generic features of Persian letters to recognize the handwriting. In order to increase the accuracy of the algorithm, we also use the first and second order of writing path derivatives. The acquired recognition accuracy reported is 98.95% in contrast with other methods.