Multiple Hand Gesture Recognition using Surface EMG Signals
DOI:
https://doi.org/10.14738/jbemi.31.1738Keywords:
Human-machine control interface, SEMG (Surface Electromyographic) signals, classification, degree of freedom (DOF), crosstalk biological signals.Abstract
Significance of robotics in serving the human being is increasing day by day. A large number of impairments and disabilities in human body force the researchers to think on the necessity of simple and natural human-machine control interface. The idea of the project is the acquisition of SEMG (Surface Electromyographic) signals from the forearm and to recognize the various hand gestures. The resulting classification is then used to control a two degree of freedom (DOF) robotic gripper.
Muscular activity is sensed by placing the EMG sensors/electrodes on the skin. The acquired signal from these electrodes is very small in amplitude and corrupted by different artifacts due to positioning and pasting of electrodes, transmission line and crosstalk with other biological signals. Pre-amplification is required to boost up the signal and then filtration is required to get the desired usable band of frequency. After that artifact-free EMG signal is further amplified, which can be fed to the control circuitry (microcontroller) to control the Hobby Servo motor of the robotic gripper hand. All the process is implemented for the real time scenario.
References
(1) Shahid S. Higher Order Statistics Techniques Applied to EMG Signal Analysis and Characterization. Ph.D. thesis, University of Limerick; Ireland, 2004.
(2) Nikias CL, Raghuveer MR. Bispectrum estimation: A digital signal processing framework. IEEE Proceedings on Communications and Radar. 1987; 75 (7):869–891.
(3) Basmajian JV, de Luca CJ. Muscles Alive - The Functions Revealed by Electromyography. The Williams & Wilkins Company; Baltimore, 1985.
(4) Cram JR, Kasman GS, Holtz J. Introduction to Surface Electromyography. Aspen Publishers Inc.; Gaithersburg, Maryland, 1998.
(5) Thexton AJ. A randomization method for discriminating between signal and noise in recordings of rhythmic electromyographic activity. J Neurosci Meth. 1996; 66: 93 –98.
(6) Bornato P, de Alessio T, Knaflitz M. A statistical method for the measurement of the muscle activation intervals from surface myoelectric signal gait. IEEE Trans Biomed Eng.1998; 45: 287–299. doi: 10.1109/10.661154.
(7) Merlo A, Farina D. A Fast and Reliable Technique for Muscle Activity Detection from Surface EMG Signals. IEEE Trans Biomed Eng. 2003; 50 (3):316–323. Doi: 10.1109/TBME.2003.808829.
(8) Gabor D. Theory of communication. J Inst Elect Eng.1946; 93:429–457.
(9) Hefftner G, Zucchini W, Jaros G. The electromyogram (EMG) as a control signal for functional neuro-muscular stimulation part 1: Autoregressive modeling as a means of EMG signature discrimination. IEEE Trans Biomed Eng.1988; 35:230–237. doi: 10.1109/10.1370.
(10) Christodoulou CI, Pattichis CS. A new technique for the classification and decomposition of EMG signals. Proceedings in IEEE International Conference on Neural Networks.1995; 5:2303–2308.
(11) H. Arieta, R. Katoh, H. Yokoi, Y. Wenwei, 2006Development of a multi-DOF electromyography prosthetic system using the adaptive joint mechanism, ABBI 2006, 32110.
