A novel segmentation method of handwritten Chinese number character strings

In this paper, a two-stage approach consisting of coarse and fine segmentation is adopted. For the characters, whose vertical projections combine together, but they don´t connected themselves, we confine them in a window and segment them with a curve line which is acquired by connecting all the middle points in sequence. For the characters connected only by one stroke, firstly we find the candidate segmentation points on the candidate stroke in the image of the thinned character, and then determine the optimal point evaluated by the principles which are presented in this paper. The method mentioned above has been applied to the segmentation of Chinese bank check amounts and get good results.