[1]张夏丰,阚秀,曹乐,等.基于肌电信号与肌肉形变信号的手语识别[J].中国医学物理学杂志,2021,38(11):1392-1399.[doi:DOI:10.3969/j.issn.1005-202X.2021.11.014]
　ZHANG Xiafeng,KAN Xiu,CAO Le,et al.Sign language recognition based on electromyogram signal and muscle deformation signal[J].Chinese Journal of Medical Physics,2021,38(11):1392-1399.[doi:DOI:10.3969/j.issn.1005-202X.2021.11.014]
点击复制

基于肌电信号与肌肉形变信号的手语识别()
分享到：

《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]

卷:
38卷
期数:
2021年第11期
页码:
1392-1399
栏目:
医学信号处理与医学仪器
出版日期:
2021-11-26

文章信息/Info

Title:
Sign language recognition based on electromyogram signal and muscle deformation signal
文章编号:
1005-202X（2021）11-1392-08
作者:
张夏丰; 阚秀; 曹乐; 杨诞; 张文艳
上海工程技术大学电子电气工程学院， 上海 201620
Author(s):
ZHANG Xiafeng;  KAN Xiu;  CAO Le;  YANG Dan;  ZHANG Wenyan
School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201620, China
关键词:
手语识别; 表面肌电信号; 肌肉形变; 端点检测; 特征提取
Keywords:
Keywords: sign language recognition surface electromyogram signal muscle deformation endpoint detection feature extraction
分类号:
R318；TP391.4
DOI:
DOI:10.3969/j.issn.1005-202X.2021.11.014
文献标志码:
A
摘要:
针对手语手势识别问题，提出一种基于肌电信号与肌肉形变信号的手语识别架构。首先，设计信号采集系统；然后，采集肌电信号与肌肉形变信号，利用滤波及小波降噪等方法对原始数据进行降噪处理。采用基于能熵比的双门限端点检测法提取信号有效活动段；分别提取肌电信号以及肌肉形变信号特征，将所提取的信号特征融合组成特征向量；最后，采用基于网格搜索的支持向量机识别模型对所采集手语动作进行识别。信号融合后手语识别正确率达到97.2%，相对于仅采用肌电信号的手语识别方法，融入肌肉形变信号后识别率提高9.3%。结果表明，基于肌电信号和肌肉形变信号的手语识别框架对动态手语手势具有良好的识别效果。
Abstract:
Abstract: Regarding to sign language and gesture recognitions, a framework for sign language recognition based on electromyogram (EMG) signal and muscle deformation signal is proposed. A signal acquisition system is designed and then is used to collect EMG signal and muscle deformation signal. The noise in original data is removed by filtering and wavelet denoising. The effective active segment of the signal is extracted by the double-threshold endpoint detection method based on energy-to-entropy ratio and the features of EMG signal and muscle deformation signal are extracted. The extracted signal features are fused to form eigenvectors. Finally, the collected sign language motions are identified by support vector machine recognition model based on grid search. The accuracy of the sign language recognition method after signal fusion is improved to 97.2%. Compared with the sign language recognition method which only uses EMG signal, the recognition rate is improved by 9.3% after fusing with muscle deformation signal. The experimental results show that the framework for sign language recognition based on EMG signal and muscle deformation signal has good recognition effect on dynamic sign language and gesture.

相似文献/References:

[1]吴志敏,杜佳乐,乔晓艳.经穴位电刺激下的表面肌电信号特征分析[J].中国医学物理学杂志,2015,32(01):77.[doi:10.3969/j.issn.1005-202X.2015.01.019]
[2]陈文敏,肖玲玲,李慧慧,等. 单侧痛腰椎间盘突出症的表面肌电信号特征[J].中国医学物理学杂志,2017,34(10):1022.[doi:DOI:10.3969/j.issn.1005-202X.2017.10.011]
　[J].Chinese Journal of Medical Physics,2017,34(11):1022.[doi:DOI:10.3969/j.issn.1005-202X.2017.10.011]
[3]雷建超,刘栋博,房玉,等.基于表面肌电信号的性别差异性手势识别[J].中国医学物理学杂志,2020,37(3):337.[doi:DOI:10.3969/j.issn.1005-202X.2020.03.016]
　LEI Jianchao,LIU Dongbo,FANG Yu,et al.Recognition of hand gestures with gender differences based on surface electromyographic signals[J].Chinese Journal of Medical Physics,2020,37(11):337.[doi:DOI:10.3969/j.issn.1005-202X.2020.03.016]
[4]刘若汐,饶家声,魏瑞晗,等.恒河猴表面肌电信号小波去噪的复合评价指标[J].中国医学物理学杂志,2020,37(9):1169.[doi:10.3969/j.issn.1005-202X.2020.09.017]
　LIU Ruoxi,RAO Jiasheng,WEI Ruihan,et al.A composite evaluation indicator of wavelet denoising in surface electromyography of rhesusmonkey[J].Chinese Journal of Medical Physics,2020,37(11):1169.[doi:10.3969/j.issn.1005-202X.2020.09.017]
[5]包其扬,王军霞,岳小力.基于子带频谱墒算法检测表面肌电信号肌肉疲劳性[J].中国医学物理学杂志,2020,37(10):1302.[doi:DOI:10.3969/j.issn.1005-202X.2020.10.015]
　BAO Qiyang,WANG Junxia,YUE Xiaoli.Detection of muscle fatigue based on surface electromyography signals segmented by subband spectral entropy algorithm[J].Chinese Journal of Medical Physics,2020,37(11):1302.[doi:DOI:10.3969/j.issn.1005-202X.2020.10.015]
[6]冯凯,董秀成,刘栋博.基于经验模态分解-小波包变换的表面肌电信号手势识别[J].中国医学物理学杂志,2021,38(4):461.[doi:DOI:10.3969/j.issn.1005-202X.2021.04.013]
　FENG Kai,DONG Xiucheng,LIU Dongbo.Empirical mode decomposition and wavelet packet transform applied to surface EMG signal for hand gesture recognition[J].Chinese Journal of Medical Physics,2021,38(11):461.[doi:DOI:10.3969/j.issn.1005-202X.2021.04.013]
[7]周明娟,王语园,王田戈,等.针对微弱表面肌电信号的采集电路设计[J].中国医学物理学杂志,2021,38(5):625.[doi:DOI:10.3969/j.issn.1005-202X.2021.05.019]
　ZHOU Mingjuan,WANG Yuyuan,WANG Tiange,et al.Design of acquisition circuit for weak surface electromyography signals[J].Chinese Journal of Medical Physics,2021,38(11):625.[doi:DOI:10.3969/j.issn.1005-202X.2021.05.019]
[8]张建华,王豪,李克祥,等.基于KPCA的膝关节多模式连续运动估计[J].中国医学物理学杂志,2023,40(6):742.[doi:DOI:10.3969/j.issn.1005-202X.2023.06.012]
　ZHANG Jianhua,WANG Hao,LI Kexiang,et al.KPCA-based continuous motion estimation of knee joint in multiple motion modes[J].Chinese Journal of Medical Physics,2023,40(11):742.[doi:DOI:10.3969/j.issn.1005-202X.2023.06.012]
[9]张思河,曹乐,王金玮,等.基于表面肌电信号的BiLSTM-SA双臂肌力估计[J].中国医学物理学杂志,2023,40(11):1383.[doi:DOI:10.3969/j.issn.1005-202X.2023.11.011]
　ZHANG Sihe,CAO Le,WANG Jinwei,et al.BiLSTM-SA model for muscle strength estimation from sEMG[J].Chinese Journal of Medical Physics,2023,40(11):1383.[doi:DOI:10.3969/j.issn.1005-202X.2023.11.011]

备注/Memo

备注/Memo:
【收稿日期】2021-05-17 【基金项目】国家自然科学基金（61703270） 【作者简介】张夏丰，硕士研究生，研究方向：生物医学信号采集与处理，E-mail: 799435451@qq.com 【通信作者】阚秀，博士，副教授，研究方向：数据处理、网络化系统研究，E-mail: xiu.kan@sues.edu.cn
更新日期/Last Update: 2021-11-27