WEKO3
アイテム
機械学習を用いた空中手書き文字認識の検討
https://doi.org/10.57375/00002289
https://doi.org/10.57375/000022890166476f-2921-4f08-aae6-f214aeabf33f
名前 / ファイル | ライセンス | アクション |
---|---|---|
012-018.pdf (5.7 MB)
|
|
Item type | 紀要論文 / Departmental Bulletin Paper(1) | |||||
---|---|---|---|---|---|---|
公開日 | 2020-03-05 | |||||
タイトル | ||||||
タイトル | 機械学習を用いた空中手書き文字認識の検討 | |||||
タイトル | ||||||
タイトル | Studies on Aerial Handwritten Character Recognition Using Machine Learning | |||||
言語 | en | |||||
言語 | ||||||
言語 | jpn | |||||
キーワード | ||||||
主題Scheme | Other | |||||
主題 | Character Recognition, Handwriting in the Air, Machine Learning | |||||
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 | |||||
ID登録 | ||||||
ID登録 | 10.57375/00002289 | |||||
ID登録タイプ | JaLC | |||||
著者 |
花房, 大佑
× 花房, 大佑× 西田, 好宏× Daiyuu, Hanafusa× Yoshihiro, Nishida |
|||||
抄録 | ||||||
内容記述タイプ | Abstract | |||||
内容記述 | This paper presents a method to recognize a character handwritten in the air. We had prototyped an aerial handwritten hiragana character recognition system that detect single character period by hovering in the air using DP (dynamic programming) matching. In this time, we investigate an aerial handwritten character recognition system using machine learning. We use two features, vector and picture. Feature of vector is relative direction of handwriting information. It is a time series information so we use LSTM (Long Short Term Memory) to learn data of characters. Feature of picture is absolutely handwriting information. We use CNN (Convolution Neural Network) to learn data of characters, because this model is suitable for picture recognize. We compared correct recognition rate of using LSTM and using CNN. We estimated features of both methods. | |||||
書誌情報 |
福井工業大学研究紀要 号 49, p. 12-18, 発行日 2019-12-20 |
|||||
出版者 | ||||||
出版者 | 福井工業大学 | |||||
書誌レコードID | ||||||
識別子タイプ | NCID | |||||
関連識別子 | TF10121950 | |||||
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 |