H. Miyao, Y. Nakano, A. Tani, H. Tabaru and T. Hananoi
A Printed Japanese Character Recognition System Using Multiple Commercial OCRs
Journal of Advanced Computational Intelligence, Vol. 8, pp.200-207 (2004)
Abstract
It is well known that integration of multiple OCR outputs can give higher performance than a single OCR. This idea was applied to the printed Japanese recognition and better performance was obtained. In the conventional experiments, the zoning, or the indication of the text region was done manually and this has been a problem from the practical viewpoint. An approach to match the classified regions outputted by multiple OCRs was proposed. By the proposed method, a high recognition rate of 98.8% was obtained from OCR systems whose performance is no better than 97.6%.
| mail address: | |
← お手数ですが打ち込んで下さい |
First Written January 22, 2005
Transplanted to So-net May 3, 2005
Last Update April 8, 2007
© Yasuaki Nakano 2005-2007