Multi-Stroke handwriting character recognition based on sEMG using convolutional-recurrent neural networks

被引：0

作者：

Beltran-Hernandez J.G. ^{[1
]}

Ruiz-Pinales J. ^{[1
]}

Lopez-Rodriguez P. ^{[1
]}

Lopez-Ramirez J.L. ^{[1
]}

Avina-Cervantes J.G. ^{[1
]}

机构：

[1] Digital Signal Processing and Telematics Groups, Engineering Division of the Campus Irapuato-Salamanca (DICIS), Universidad de Guanajuato, Palo Blanco, Salamanca, Guanajuato

来源：

Ruiz-Pinales, Jose (pinales@ugto.mx) | 1600年 / American Institute of Mathematical Sciences卷 / 17期

关键词：

Convolutional neural networks; Gated recurrent unit; Long short-Term memory; Surface EMG;

D O I：

10.3934/MBE.2020293

中图分类号：

学科分类号：

摘要：

Despite the increasing use of technology, handwriting has remained to date as an efficient means of communication. Certainly, handwriting is a critical motor skill for childrens cognitive development and academic success. This article presents a new methodology based on electromyographic signals to recognize multi-user free-style multi-stroke handwriting characters. The approach proposes using powerful Deep Learning (DL) architectures for feature extraction and sequence recognition, such as convolutional and recurrent neural networks. This framework was thoroughly evaluated, obtaining an accuracy of 94.85%. The development of handwriting devices can be potentially applied in the creation of artificial intelligence applications to enhance communication and assist people with disabilities. © 2020 American Institute of Mathematical Sciences. All rights reserved.

引用

页码：5432 / 5448

页数：16

共 48 条

[11]

Lansari A., Bouslama F., Khasawneh M., Al-Rawi A., A novel electromyography (EMG) based classification approach for Arabic handwriting, Proceedings of the International Joint Conference on Neural Networks, (2003)

[12]

Huang G., Zhang D., Zheng X., Zhu X., An EMG-based handwriting recognition through dynamic time warping, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology, pp. 4902-4905, (2010)

[13]

Linderman M., Lebedev M. A., Erlichman J. S., Recognition of Handwriting from

[14]

Li C., Ma Z., Yao L., Zhang D., Improvements on EMG-based handwriting recognition with DTW algorithm, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), (2013)

[15]

Chihi I., Afef A., Mohamed B., Analysis of Handwriting Velocity to Identify Handwriting Process from Electromyographic Signals, Am. J. Appl. Sci, 9, pp. 1742-1756, (2012)

[16]

Slim M. A., Abdelkrim A., Benrejeb M., An efficient handwriting velocity modelling for electromyographic signals reconstruction using Radial Basis Function neural networks, 2015 7th International Conference on Modelling, Identification and Control (ICMIC), pp. 1-6, (2015)

[17]

Okorokova E., Lebedev M., Linderman M., Ossadtchi A., A dynamical model improves reconstruction of handwriting from multichannel electromyographic recordings, Front. Neurosci, 9, pp. 1-15, (2015)

[18]

Wei W., Dai Q., Wong Y., Hu Y., Kankanhalli M., Geng W., Surface-Electromyography-Based Gesture Recognition by Multi-View Deep Learning, IEEE Trans. Biomed. Eng, 66, pp. 2964-2973, (2019)

[19]

Dash A., Sahu A., Shringi R., Gamboa J., Afzal M. Z., Malik M. I., Et al., AirScript-Creating Documents in Air, 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), (2017)

[20]

Roy P., Ghosh S., Pal U., A CNN Based Framework for Unistroke Numeral Recognition in Air-Writing, 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 404-409, (2018)

← 1 2 3 4 5 →