Recognition of Handwritten Numerals Using a Decision Graph

An optical character reader capable of reading handwritten numerical characters has been developed and applied to mail automation. The recognition of characters is performed by extracting geometrical features out of horizontally divided zones together with their mutual connective relation. The topological structure of character strokes is analyzed by a sequential machine with an input string of stroke segments combined with information on the connective relation. The extracted features are sequentially matched with standard references. A new decision method called decision graph matching is fully utilized. The decision graph consists of a set of decision transition diagrams to be compared with the string of extracted features and a penalty count system to detect the optimum match. High flexibility against unlimited variability of handwritten character shapes is achieved by means of a stored logic system using rewritable magnetic core memory.