WEKO3
アイテム
On distributed representation of output layer for recognizing Japanese Kana characters using neural networks
http://hdl.handle.net/2297/6795
http://hdl.handle.net/2297/6795f2808239-5e4d-4ec9-bee8-ee06223db8ab
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
TE-PR-NAKAYAMA-K-1997-600.pdf (484.6 kB)
|
|
| Item type | 会議発表論文 / Conference Paper(1) | |||||
|---|---|---|---|---|---|---|
| 公開日 | 2017-10-03 | |||||
| タイトル | ||||||
| タイトル | On distributed representation of output layer for recognizing Japanese Kana characters using neural networks | |||||
| 言語 | ||||||
| 言語 | eng | |||||
| 資源タイプ | ||||||
| 資源タイプ識別子 | http://purl.org/coar/resource_type/c_5794 | |||||
| 資源タイプ | conference paper | |||||
| 著者 |
Keeni, Kanad
× Keeni, Kanad× Shimodaira, Hiroshi× Nakayama, Kenji |
|||||
| 書誌情報 |
Proceedings of the International Conference on Document Analysis and Recognition, ICDAR 巻 2, p. 600-603, 発行日 1997-08-01 |
|||||
| 出版者 | ||||||
| 出版者 | IEEE(Institute of Electrical and Electronics Engineers) | |||||
| 抄録 | ||||||
| 内容記述タイプ | Abstract | |||||
| 内容記述 | This paper presents an automatic coding scheme for representing the output layer of a neural network. Compared to local representation where the number of output unit is p, the number of output unit required for the proposed representation is close to log p. The output of seven different printers were used for evaluating the performance of the system. The proposed automatic representation gave the average recognition rate of 98.7% for 71 categories. | |||||
| 著者版フラグ | ||||||
| 出版タイプ | VoR | |||||
| 出版タイプResource | http://purl.org/coar/version/c_970fb48d4fbd8a85 | |||||
