Recognition of handwritten numerals using topological structures and Fourier descriptors of numeral contours

A new recognition structure for handwritten numerals is proposed. The metho d is basically a multistage structure combined with a parallel recognition classifier, which is based on the topological properties of the characters, statistical analysis, the positions of centroids of outer and interior con tours, and the distance of the furthest point of the character outer contou r from the centroid. This new scheme eventually classifies input characters into one of 14 subgroups. This recognition structure is more effective tha n a single-stage classifier, especially for handwritten characters, because of the vast variations in writing styles. After preprocessing (broken-char acter mending, gap filing, noise removal and contour smoothing) and contour following, a handwritten character is classified into one of three groups according to its topological properties. Then, each group is further classi fied into subgroups and so on. After classification as to which of the 14 s ubgroups the input character belongs to, the final recognition is based on a comparison of the Fourier descriptors of the outer contour of the input c haracter and those of prototypes of that subgroup. In our experiment, 1000 characters from the NIST [33] database were used for the statistical analys is, and 427 prototypes representing different writing styles were chosen fo r comparison; then 5841 different characters were used for testing. The rec ognition rate obtained was 98.31%, with a reliability of 99.12%, a substitu tion rate of 0.87% and a rejection rate of 0.82%.