WEKO3
アイテム
指文字認識におけるRGB-Dカメラの精度の影響に関する実験的検討
http://hdl.handle.net/10458/5002
http://hdl.handle.net/10458/5002e3f232fd-ce15-4234-827d-8e26902ef664
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
engineering43_213-217.pdf (866.1 kB)
|
|
| Item type | 紀要論文 / Departmental Bulletin Paper(1) | |||||
|---|---|---|---|---|---|---|
| 公開日 | 2014-09-04 | |||||
| タイトル | ||||||
| タイトル | 指文字認識におけるRGB-Dカメラの精度の影響に関する実験的検討 | |||||
| 言語 | ja | |||||
| タイトル | ||||||
| タイトル | An Experimental Analysis for the Effects of the Precision of RGB-D Cameras for the Finger Character Recognition | |||||
| 言語 | en | |||||
| 言語 | ||||||
| 言語 | jpn | |||||
| キーワード | ||||||
| 言語 | en | |||||
| 主題Scheme | Other | |||||
| 主題 | Finger Character, RGB-D camera, Depth image, Kernel Subspace Method, SVM | |||||
| 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 | |||||
| その他（別言語等）のタイトル | ||||||
| その他のタイトル | ユビモジ ニンシキ ニオケル RGB-D カメラ ノ セイド ノ エイキョウ ニ カンスル ジッケンテキ ケントウ | |||||
| 言語 | ja-Kana | |||||
| 著者 |
横道, 政裕
× 横道, 政裕× 諌山, 羊太× 石原, 誠康× 甲斐, 崇浩× Isayama, Yota× 石原, 誠康× Kai, Takahiro |
|||||
| 抄録 | ||||||
| 内容記述タイプ | Abstract | |||||
| 内容記述 | Computer recognition of sign language and finger character is an important research problem for enabling communication with hearing impaired people. The finger character for Japanese kana consist of 81 poses, and some of them are difficult to be distinguished because their two-dimensional appearances are very similar. Recently, consumer RGB-D cameras have been available with low cost and many researchers have proposed gesture recognition system with them. Among them, some finger character recognition systems which uses RGB-D cameras have been proposed for Japanese kana characters. However, many of them use only single kind of RGB-D camera and do not analyze the effect of the precision of the measurement to the recognition rate. This report examines two kinds of low cost RGB-D cameras for the finger character recognition of Japanese kana. The first is Kinect, which is commonly used for middle range distance, and the second is the DepthSense 325, which is mainly used for short range distance. The recognition performances are evaluated with real data and it is shown that the Kinect takes slightly better recognition rate. | |||||
| 言語 | en | |||||
| 書誌情報 |
ja : 宮崎大学工学部紀要 en : Memoirs of Faculty of Engineering, University of Miyazaki 巻 43, p. 213-217, 発行日 2014-07-31 |
|||||
| 出版者 | ||||||
| 出版者 | 宮崎大学工学部 | |||||
| 言語 | ja | |||||
| 出版者 | ||||||
| 出版者 | Faculty of Engineering, University of Miyazaki | |||||
| 言語 | en | |||||
| ISSN | ||||||
| 収録物識別子タイプ | ISSN | |||||
| 収録物識別子 | 05404924 | |||||
| 書誌レコードID | ||||||
| 収録物識別子タイプ | NCID | |||||
| 収録物識別子 | AA00732558 | |||||
| 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 | |||||
