Presentation | 2022-03-08 A Study on Sign Recognition Using Deep Learning Hikaru Isogai, Tsutomu Kimura, Kanda Kazuyuki, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In this study, our purpose is to recognize signs using machine learning. In order to take into account the transition motions that occur in a sign sentence, machine learning adopts the sign sentences as training data, and a trained model is created. We experimented two models: one that incorporates Connectionist Temporal Classification (CTC) which is a method used in speech recognition, and the other is a conformer model that uses a transformer used in natural language processing. As the result, the recognition rate for the entire test data was about 74% by the CTC method and about 32% by the Conformer method. However, the recognition results of the Conformer method showed a phenomenon as over-learning, and we estimated that it might worked properly. We will improve the Conformer method and will investigate a new algorithm that combines the Transformer with CTC. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Sign Recognition / Deep Learning / Connectionist Temporal Classification / Transformer / Conformer |
Paper # | WIT2021-48 |
Date of Issue | 2022-03-01 (WIT) |
Conference Information | |
Committee | WIT / IPSJ-AAC |
---|---|
Conference Date | 2022/3/8(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Online |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Shinji Sakou(Nagoya Inst. of Tech.) |
Vice Chair | Tomohiro Amemiya(Univ. of Tokyo) |
Secretary | Tomohiro Amemiya(Saitama Industrial Tech. Center) / (Teikyo Univ.) |
Assistant | Minako Hosono(AIST) / Aki Sugano(Nagoya Univ.) / Tomoyasu Komori(NHK) |
Paper Information | |
Registration To | Technical Committee on Well-being Information Technology / Special Interest Group on Assistive & Accessible Computin |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | A Study on Sign Recognition Using Deep Learning |
Sub Title (in English) | Comparison between CTC and Conformer |
Keyword(1) | Sign Recognition |
Keyword(2) | Deep Learning |
Keyword(3) | Connectionist Temporal Classification |
Keyword(4) | Transformer |
Keyword(5) | Conformer |
1st Author's Name | Hikaru Isogai |
1st Author's Affiliation | National Institute of Technology, Toyota College(NIT, Toyota College) |
2nd Author's Name | Tsutomu Kimura |
2nd Author's Affiliation | National Institute of Technology, Toyota College(NIT, Toyota College) |
3rd Author's Name | Kanda Kazuyuki |
3rd Author's Affiliation | National Museum of Ethnology(National Museum of Ethnology) |
Date | 2022-03-08 |
Paper # | WIT2021-48 |
Volume (vol) | vol.121 |
Number (no) | WIT-418 |
Page | pp.pp.29-34(WIT), |
#Pages | 6 |
Date of Issue | 2022-03-01 (WIT) |