文献の詳細
言語 | 英語 |
---|---|
著者 | Hirotomo Aso, Shin'ichiro Omachi, Masayuki Kimura, Yutaka Katsuyama |
論文名 | SEIUN - A Fast and Intelligent Character Recognition System |
論文誌名 | Systems and Computers in Japan |
Vol. | 25 |
No. | 3 |
ページ | pp.18-29 |
出版社 | Scripta Technica, Inc. |
年月 | 1994年3月 |
要約 | It is useful for Japanese and Chinese character recognition to use image-type processing for selection of limited number of candidates by grasping whole rough image (rough classification) and then decide the final candidate by logical-type processing (fine classification). In this paper, we describe architecture and performance of SEIUN (Systolic Elaborated Intelligent Ultra-high-speed Neosystem), which is a fast and intelligent character recognition system integrating image-type and logical-type processings. This system has a host computer, an optical image scanner and an image processor developed by the authors. The architecture of the image processor is a pipelined combination of systolic arrays. The performance is that it carries out rough classification of 2,965 kinds of printed Chinese characters at a speed of about 200 characters per second. The rate that the correct candidate is in the first three candidates is greater than 99.99% if all the characters are 20 point size. The image processor executes variable functions by changing parameters, for example, recognition by partial image, extraction of blurred region of character image, alternate use of dictionaries for multi-font text, matching by using feature vectors for word recognition and so on. |
@Article {Aso1994, author = {Hirotomo Aso and Shin'ichiro Omachi and Masayuki Kimura and Yutaka Katsuyama}, title = {SEIUN - A Fast and Intelligent Character Recognition System}, journal = {Systems and Computers in Japan}, year = {1994}, month = mar, volume = {25}, number = {3}, pages = {18--29}, publisher = {Scripta Technica, Inc.} }