Presentation | 2018-01-18 Discrimination of five-finger tapping operation by CNN for fingerless glove-type myoelectric interface Mamoru Hirota, Junki Sato, Ayumu Tsuboi, Masayuki Yokoyama, Masao Yanagisawa, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In recent years, research on input interfaces that anticipate the spread of VR devices to various fields is widely conducted. Therefore, detailed tracking is required more than conventional motion tracking. In this paper, we aim to develop a fingerless glove type EMG interface with dry electrodes on the back of hand, to identify the tapping motion of 5 fingers as the movement of fingers, and use a convolution neural network for the acquired EMG information. We introduced two types of the classifier, and verified the accuracy of finger action identification. Experiments were conducted on eleven subjects and the obtained electromyogram information was identified by each method. As a result, the average accuracy was 88.61% for identification in linear discriminant analysis and 87.98% for average convolution neural network became. We discussed the cause of this result and future prospects. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | EMG / gesture recognition / interface / CNN |
Paper # | PRMU2017-125,MVE2017-46 |
Date of Issue | 2018-01-11 (PRMU, MVE) |
Conference Information | |
Committee | PRMU / MVE / IPSJ-CVIM |
---|---|
Conference Date | 2018/1/18(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Shinichi Sato(NII) / Yoshinari Kameda(Univ. of Tsukuba) |
Vice Chair | Hironobu Fujiyoshi(Chubu Univ.) / Yoshihisa Ijiri(Omron) / Kenji Mase(Nagoya Univ.) |
Secretary | Hironobu Fujiyoshi(AIST) / Yoshihisa Ijiri(NAIST) / Kenji Mase(Kyoto Univ.) / (NTT) |
Assistant | Masato Ishii(NEC) / Yusuke Sugano(Osaka Univ.) / Takatsugu Hirayama(Nagoya Univ.) / Ryosuke Aoki(NTT) |
Paper Information | |
Registration To | Technical Committee on Pattern Recognition and Media Understanding / Technical Committee on Media Experience and Virtual Environment / Special Interest Group on Computer Vision and Image Media |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Discrimination of five-finger tapping operation by CNN for fingerless glove-type myoelectric interface |
Sub Title (in English) | |
Keyword(1) | EMG |
Keyword(2) | gesture recognition |
Keyword(3) | interface |
Keyword(4) | CNN |
Keyword(5) | |
1st Author's Name | Mamoru Hirota |
1st Author's Affiliation | Waseda University(Waseda Univ) |
2nd Author's Name | Junki Sato |
2nd Author's Affiliation | Waseda University(Waseda Univ) |
3rd Author's Name | Ayumu Tsuboi |
3rd Author's Affiliation | Waseda University(Waseda Univ) |
4th Author's Name | Masayuki Yokoyama |
4th Author's Affiliation | Waseda University(Waseda Univ) |
5th Author's Name | Masao Yanagisawa |
5th Author's Affiliation | Waseda University(Waseda Univ) |
Date | 2018-01-18 |
Paper # | PRMU2017-125,MVE2017-46 |
Volume (vol) | vol.117 |
Number (no) | PRMU-391,MVE-392 |
Page | pp.pp.111-116(PRMU), pp.111-116(MVE), |
#Pages | 6 |
Date of Issue | 2018-01-11 (PRMU, MVE) |