Recognition of handwritten character database ETL9B using pattern transformation method
Jun Feng Guo, Risaburô Sato, Ning Sun, Yoshiaki Nemoto · Systems and Computers in Japan · 1994
Abstract To enhance the recognition rate of handwritten characters, one has to consider the effects of various changed forms in character patterns. In Reference [1], we have proposed a recognition algorithm using pattern transformation, which can deal flexibly with the changed forms in character patterns. In the fine classification, the algorithm makes three types of pattern transformations for the input pattern, and selects the transformed pattern that matches the standard pattern best. This paper improves that algorithm and constructs a recognition system. As the results of testing with ETL9B, a database of handwritten characters that contains 600,000 Japanese characters and a recognition rate of 96.32 percent was achieved, a new record for ETL9B.