Visual similarity analysis of Chinese characters and its uses in Japanese OCR

1!aditi~!lallY, ~_ Chin~se or J_ap~ese Optical Character Reader (OCR) has to representeach character category individually as one or more feature prototypes, or a structural description which is a composition of manually derived components such as radicals. Here we propose a new approach in which various kinds of visual similarities between different Chinese characters are analyzed automatically at the feature level. Using this method, character categories will be related to each other by training on fonts; and character images from a text page can be related to each other based on visual similarities they share. This method provides a way to interpret character images from a text page systematically, instead of a sequence of isolated character recognitions. The use of the method for postprocessing in Japanese text recognition will also be discussed.