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

Tao Hong; Stephen W. Lam; Jonathan J. Hull; Sargur N. Srihari

doi:10.1117/12.205827

Translator Disclaimer

30 March 1995 Visual similarity analysis of Chinese characters and its uses in Japanese OCR

Tao Hong, Stephen W. Lam, Jonathan J. Hull, Sargur N. Srihari

Author Affiliations +

Proceedings Volume 2422, Document Recognition II; (1995) https://doi.org/10.1117/12.205827
Event: IS&T/SPIE's Symposium on Electronic Imaging: Science and Technology, 1995, San Jose, CA, United States

Abstract

Traditionally, a Chinese or Japanese optical character reader (OCR) has to represent each 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 are related to each other by training on fonts; and character images from a text page can be related to each other based on the 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 post processing in Japanese text recognition is also discussed.

Citation Download Citation

Tao Hong, Stephen W. Lam, Jonathan J. Hull, and Sargur N. Srihari "Visual similarity analysis of Chinese characters and its uses in Japanese OCR", Proc. SPIE 2422, Document Recognition II, (30 March 1995); https://doi.org/10.1117/12.205827

ACCESS THE FULL ARTICLE