Presentation 2019-02-08
Study on sign language recognition using machine learning
Yuta Takahashi, Tsutomu Kimura, Kazuyuki Kanda,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Our purpose is to recognize kinetic movements in sign language through machine learning which consists of a recurrent neural network. The signs examined were 101 signs in Sign Language Proficiency Test Grade 6, played by 12 examinees for several times. The total number of the data was 7,763. The data were the trajectories of X and Y axes of the wrist, the elbow, the shoulder of each side. Approximately 90% of the data were taken as learning data and the rest were to evaluate our neural network. As a result of cross validation, the accuracy was about 75%. The false recognitions were supposed to occur by similarity of the signs.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) sign language / machine learning / deep learning / cross validation
Paper # WIT2018-60
Date of Issue 2019-01-31 (WIT)

Conference Information
Committee WIT / ASJ-H
Conference Date 2019/2/7(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Ehime Univ.
Topics (in Japanese) (See Japanese page)
Topics (in English) Psychological and Physiological Acoustics and Well-being Information Technology, etc.
Chair Chikamune Wada(Kyushu Inst. of Tech.) / Kenji Ozawa(Yamanashi Univ.)
Vice Chair Daisuke Wakatsuki(Tsukuba Univ. of Tech.) / Seiji Nakagawa(Chiba Univ.)
Secretary Daisuke Wakatsuki(AIST) / Seiji Nakagawa(Nagoya Inst. of Tech.)
Assistant Manabi Miyagi(Tsukuba Univ. of Tech.) / Takeaki Shionome(Teikyo Univ.) / Takashi Handa(Saitama Industrial Tech. Center)

Paper Information
Registration To Technical Committee on Well-being Information Technology / Auditory Research Meeting
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Study on sign language recognition using machine learning
Sub Title (in English)
Keyword(1) sign language
Keyword(2) machine learning
Keyword(3) deep learning
Keyword(4) cross validation
1st Author's Name Yuta Takahashi
1st Author's Affiliation National Institute of Technology, Toyota College(NITTC)
2nd Author's Name Tsutomu Kimura
2nd Author's Affiliation National Institute of Technology, Toyota College(NITTC)
3rd Author's Name Kazuyuki Kanda
3rd Author's Affiliation National Museum of Ethnology(Minpaku)
Date 2019-02-08
Paper # WIT2018-60
Volume (vol) vol.118
Number (no) WIT-440
Page pp.pp.59-64(WIT),
#Pages 6
Date of Issue 2019-01-31 (WIT)