Presentation 2020-05-15
Online handwriting recognition based on LSTM-Autoencoder
Junji Sakurai, Jun Rokui,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Correct data and incorrect data are required for online handwriting recognition. However, It is difficult to prepare enough fake data. In this research, we propose an online handwriting recognition method using LSTM Autoencoder. LSTM can perform detailed estimation based on past values of time series data, but model training requires correct data and incorrect data. On the other hand, the Autoencoder can estimate with only correct data, but is not suitable for detailed estimation of time-series data. We have experimentally confirmed that LSTM Autoencoder is effective for online handwriting recognition.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) machine learning / LSTM / Autoencoder / online handwriting recognition / biometrics
Paper # PRMU2020-6
Date of Issue 2020-05-07 (PRMU)

Conference Information
Committee PRMU / IPSJ-CVIM
Conference Date 2020/5/14(2days)
Place (in Japanese) (See Japanese page)
Place (in English) online
Topics (in Japanese) (See Japanese page)
Topics (in English) Business based on computer vision and pattern recognition
Chair Yoichi Sato(Univ. of Tokyo)
Vice Chair Toru Tamaki(Hiroshima Univ.) / Akisato Kimura(NTT)
Secretary Toru Tamaki(NTT) / Akisato Kimura(OMRON SINICX)
Assistant Yusuke Uchida(DeNA) / Takayoshi Yamashita(Chubu Univ.)

Paper Information
Registration To Technical Committee on Pattern Recognition and Media Understanding / 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) Online handwriting recognition based on LSTM-Autoencoder
Sub Title (in English)
Keyword(1) machine learning
Keyword(2) LSTM
Keyword(3) Autoencoder
Keyword(4) online handwriting recognition
Keyword(5) biometrics
1st Author's Name Junji Sakurai
1st Author's Affiliation University of Shizuoka(Univ of Shizuoka)
2nd Author's Name Jun Rokui
2nd Author's Affiliation University of Shizuoka(Univ of Shizuoka)
Date 2020-05-15
Paper # PRMU2020-6
Volume (vol) vol.120
Number (no) PRMU-14
Page pp.pp.29-34(PRMU),
#Pages 6
Date of Issue 2020-05-07 (PRMU)