Presentation | 1998/6/19 Hand-Printed Numeral Recognition by Query Learning Hitoshi Sakano, Naoki Mukawa, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | This paper proposes a new character recognition system using query learning. The query learning is a useful technique for high accurate and high speed learning. However it has not been applied to character recognition problem, since human cannot recognize the queries in feature space used in character recognition system. The authors have already proposed a method for reconstructing a character image from feature space using Genetic Algorithm. Here, the method is applied to a "translator"in query learning of character recognition. The experimental results of handprinted numeral recognition show the advantage of the proposed method. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Numeral recognition / Query Learning / Genetic Algorithm |
Paper # | PRMU98-45 |
Date of Issue |
Conference Information | |
Committee | PRMU |
---|---|
Conference Date | 1998/6/19(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Pattern Recognition and Media Understanding (PRMU) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Hand-Printed Numeral Recognition by Query Learning |
Sub Title (in English) | |
Keyword(1) | Numeral recognition |
Keyword(2) | Query Learning |
Keyword(3) | Genetic Algorithm |
1st Author's Name | Hitoshi Sakano |
1st Author's Affiliation | Laboratories of Information Technology NTT Data Corporation() |
2nd Author's Name | Naoki Mukawa |
2nd Author's Affiliation | Laboratories of Information Technology NTT Data Corporation |
Date | 1998/6/19 |
Paper # | PRMU98-45 |
Volume (vol) | vol.98 |
Number (no) | 127 |
Page | pp.pp.- |
#Pages | 7 |
Date of Issue |