The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Sepanjang pengetahuan kami, terdapat beberapa kajian tentang pengenalan penulis peringkat aksara tulisan tangan hanya menggunakan data pecutan dan halaju sudut. Dalam makalah ini, kami mencadangkan pendekatan pembelajaran mendalam untuk mengenal pasti penulis hanya menggunakan data sensor inersia tulisan tangan udara. Khususnya, kami memisahkan perwakilan darjah kebebasan (DoF) yang berbeza bagi tulisan tangan udara untuk mengekstrak kebergantungan tempatan dan perhubungan dalam CNN yang berbeza secara berasingan. Percubaan pada set data awam mencapai purata prestasi yang baik tanpa sebarang pengekstrakan ciri rekaan tangan tambahan.
Yanfang DING
South China University of Technology
Yang XUE
South China University of Technology
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Salinan
Yanfang DING, Yang XUE, "A Deep Learning Approach to Writer Identification Using Inertial Sensor Data of Air-Handwriting" in IEICE TRANSACTIONS on Information,
vol. E102-D, no. 10, pp. 2059-2063, October 2019, doi: 10.1587/transinf.2019EDL8070.
Abstract: To the best of our knowledge, there are a few researches on air-handwriting character-level writer identification only employing acceleration and angular velocity data. In this paper, we propose a deep learning approach to writer identification only using inertial sensor data of air-handwriting. In particular, we separate different representations of degree of freedom (DoF) of air-handwriting to extract local dependency and interrelationship in different CNNs separately. Experiments on a public dataset achieve an average good performance without any extra hand-designed feature extractions.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2019EDL8070/_p
Salinan
@ARTICLE{e102-d_10_2059,
author={Yanfang DING, Yang XUE, },
journal={IEICE TRANSACTIONS on Information},
title={A Deep Learning Approach to Writer Identification Using Inertial Sensor Data of Air-Handwriting},
year={2019},
volume={E102-D},
number={10},
pages={2059-2063},
abstract={To the best of our knowledge, there are a few researches on air-handwriting character-level writer identification only employing acceleration and angular velocity data. In this paper, we propose a deep learning approach to writer identification only using inertial sensor data of air-handwriting. In particular, we separate different representations of degree of freedom (DoF) of air-handwriting to extract local dependency and interrelationship in different CNNs separately. Experiments on a public dataset achieve an average good performance without any extra hand-designed feature extractions.},
keywords={},
doi={10.1587/transinf.2019EDL8070},
ISSN={1745-1361},
month={October},}
Salinan
TY - JOUR
TI - A Deep Learning Approach to Writer Identification Using Inertial Sensor Data of Air-Handwriting
T2 - IEICE TRANSACTIONS on Information
SP - 2059
EP - 2063
AU - Yanfang DING
AU - Yang XUE
PY - 2019
DO - 10.1587/transinf.2019EDL8070
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E102-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2019
AB - To the best of our knowledge, there are a few researches on air-handwriting character-level writer identification only employing acceleration and angular velocity data. In this paper, we propose a deep learning approach to writer identification only using inertial sensor data of air-handwriting. In particular, we separate different representations of degree of freedom (DoF) of air-handwriting to extract local dependency and interrelationship in different CNNs separately. Experiments on a public dataset achieve an average good performance without any extra hand-designed feature extractions.
ER -