Experiments on Handwritten Numeral Classification

Results of the application of a new edge-defining preprocessor to the recognition of handwritten numerals are presented. The decision mechanisms which were simulated are simple and are closely related to maximum likelihood decisions. Results are presented of experiments in which 1000 numeral patterns were used to set up a memory, which was then tested on a further 1000 samples. Success rates approaching 95 percent on completely unselected data have been measured. A convenient rejection procedure is described, and the error reject curves produced are shown. These are so encouraging that the scheme must be regarded as the basis of a practical machine for many real life applications.