| Item type |
紀要論文 / Departmental Bulletin Paper(1) |
| 公開日 |
2011-11-08 |
| タイトル |
|
|
タイトル |
Selection of a Similar Writer for Personal Handwritten Character Recognition |
|
言語 |
en |
| 言語 |
|
|
言語 |
eng |
| キーワード |
|
|
言語 |
en |
|
主題Scheme |
Other |
|
主題 |
Handwriting |
| キーワード |
|
|
言語 |
en |
|
主題Scheme |
Other |
|
主題 |
Hiragana recognition |
| キーワード |
|
|
言語 |
en |
|
主題Scheme |
Other |
|
主題 |
Character recognition |
| キーワード |
|
|
言語 |
en |
|
主題Scheme |
Other |
|
主題 |
Handwriting character recognition |
| キーワード |
|
|
言語 |
en |
|
主題Scheme |
Other |
|
主題 |
Personal tablet computer |
| 資源タイプ |
|
|
資源タイプ識別子 |
http://purl.org/coar/resource_type/c_6501 |
|
資源タイプ |
departmental bulletin paper |
| 著者 |
Kimura, Takuya
Hattori, Masahiro
Tsuruoka, Shinji
Kawanaka, Hiroharu
Takase, Haruhiko
Miyake, Yasuji
|
| 抄録 |
|
|
内容記述タイプ |
Abstract |
|
内容記述 |
It becomes the diffusion period of a tablet (key-board less) computer for electronic book and electronic pub-lishing, and every business elite will bring a personal tablet computer. The usage of personal tablet computer includes taking memo using the touch panel display. The taking memo using the touch panel display is written by a finger or a pen. The memo includes a figure and a character written by his finger or pen. The user desires the handwritten character recognition. The useful handwritten character recognition software, however, has not developed for Japanese characters. We will develop the personal handwritten character recogni-tion system in high accuracy using the tablet can use the tra-jectory of his finger or pen. In this paper, we describe the effectiveness of personal character recognition and a selection method of a similar writer in personal character recognition. We proposed two new recognition methods: “similar mean dictionary (SMD)” and “similar feature space dictionary (SFSD)” to improve the personal character recognition. These dictionaries use only one character, and they can estimate the personality of writing style using characters written by a simi-lar writer. The similar feature space dictionary improved the character recognition rate to 91.0 % which obtains the similar accuracy with personal dictionary. It is confirmed that only one character written by a user (specific writer) is very effec-tive for handwritten character recognition. |
| 書誌情報 |
Proceedings of the Second International Workshop on Regional Innovation Studies : (IWRIS2010)
号 2,
p. 59-62,
発行日 2011-10-01
|
| フォーマット |
|
|
内容記述タイプ |
Other |
|
内容記述 |
application/pdf |
| 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 |
| 出版者 |
|
|
出版者 |
Graduate School of Regional Innovation Studies, Mie University |
| 資源タイプ（三重大） |
|
|
値 |
Departmental Bulletin Paper / 紀要論文 |
60C15236.pdf (501.4 kB)
