Presentation 2021-03-06
A Study on Sign Language Recognition Using Deep Learning
Isogai Hikaru, Kimura Tsutomu, Kanda Kazuyuki,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this study, we developed a machine leaning-based sign language recognition system that can recognize each word in a sign language sentence. In our previous study, we developed a learning model using videos of sign language words as training data and obtained a recognition rate of about 90% for words of Sign Language Proficiency Test Grade 6. In addition, we used this training data to recognize sign language sentences using the "Connectionist Temporal Classification" method. However, we found that the recognition rate of words in the sign language sentences decreased because the Home Position was included in the data. Therefore, we attempted to solve this problem by using sign language sentences as training data. As a result, the recognition rate was improved, and we found that the recognition rate improved by increasing the number of sign language sentences used for training.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) sign language / deep learning / Connectionist Temporal Classification
Paper # WIT2020-38
Date of Issue 2021-02-26 (WIT)

Conference Information
Committee WIT / IPSJ-AAC
Conference Date 2021/3/5(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Daisuke Wakatsuki(Tsukuba Univ. of Tech.) / 澤田 秀之(早大)
Vice Chair Shinji Sakou(Nagoya Inst. of Tech.)
Secretary Shinji Sakou(Saitama Industrial Tech. Center) / (Teikyo Univ.)
Assistant Manabi Miyagi(Tsukuba Univ. of Tech.) / Minako Hosono(AIST) / Aki Sugano(Nagoya Univ.)

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 Language Recognition Using Deep Learning
Sub Title (in English) Word recognition from sign language sentences
Keyword(1) sign language
Keyword(2) deep learning
Keyword(3) Connectionist Temporal Classification
1st Author's Name Isogai Hikaru
1st Author's Affiliation National Institute of Technology, Toyota College(NIT, Toyota College)
2nd Author's Name Kimura Tsutomu
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 2021-03-06
Paper # WIT2020-38
Volume (vol) vol.120
Number (no) WIT-419
Page pp.pp.47-52(WIT),
#Pages 6
Date of Issue 2021-02-26 (WIT)