| Presentation | 2022-05-26 Evaluation of Handwritten Numerical Character Recognition by Concatenated LSTM with Multiple Subjects Noriaki Kaneko, Masakatsu Ogawa, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | With the increasing infection of the new coronavirus (COVID-19), demand for contactless technology is rapidly increasing. To address this demand, we focus on the numerical input. In our conventional studies, we tried to recognize handwritten numerical character by LSTM using three-dimensional hand and finger data obtained by Leap Motion. In concatenated learning model, we separately analyze three-dimensional data obtained by each Leap Motion and recognize them by LSTM composed of dual input layer. In this study, we verify the effectiveness of the proposal learning model with multiple subjects. As a result of the classification accuracy, applying the bidirectional LSTM classification achieves the maximum 94.3% and we confirm the effectiveness of proposed method. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Contactless Operation / Hand Tracking Sensor / Automatic Measurement / Machine Learning |
| Paper # | SeMI2022-1 |
| Date of Issue | 2022-05-19 (SeMI) |
| Conference Information | |
| Committee | SeMI / IPSJ-DPS / IPSJ-MBL / IPSJ-ITS |
|---|---|
| Conference Date | 2022/5/26(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Koji Yamamoto(Kyoto Univ.) |
| Vice Chair | Kazuya Monden(Hitachi) / Yasunori Owada(NICT) |
| Secretary | Kazuya Monden(Cyber Univ.) / Yasunori Owada(Waseda Univ.) / (Osaka Univ.) |
| Assistant | Yuki Katsumata(NTT DOCOMO) / Akihito Taya(Aoyama Gakuin Univ.) / Yu Nakayama(Tokyo Univ. of Agri. and Tech.) |
| Paper Information | |
| Registration To | Technical Committee on Sensor Network and Mobile Intelligence / Special Interest Group on Distributed Processing System / Special Interest Group on Mobile Computing and Pervasive Systems / Special Interest Group on Intelligent Transport Systems and Smart Community |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Evaluation of Handwritten Numerical Character Recognition by Concatenated LSTM with Multiple Subjects |
| Sub Title (in English) | |
| Keyword(1) | Contactless Operation |
| Keyword(2) | Hand Tracking Sensor |
| Keyword(3) | Automatic Measurement |
| Keyword(4) | Machine Learning |
| 1st Author's Name | Noriaki Kaneko |
| 1st Author's Affiliation | Sophia University(Sophia Univ.) |
| 2nd Author's Name | Masakatsu Ogawa |
| 2nd Author's Affiliation | Sophia University(Sophia Univ.) |
| Date | 2022-05-26 |
| Paper # | SeMI2022-1 |
| Volume (vol) | vol.122 |
| Number (no) | SeMI-46 |
| Page | pp.pp.1-4(SeMI), |
| #Pages | 4 |
| Date of Issue | 2022-05-19 (SeMI) |