EMG-based hand gesture recognition for realtime biosignal interfacing

In this paper the development of an electromyogram (EMG) based interface for hand gesture recognition is presented. To recognize control signs in the gestures, we used a single channel EMG sensor positioned on the inside of the forearm. In addition to common statistical features such as variance, mean value, and standard deviation, we also calculated features from the time and frequency domain including Fourier variance, region length, zerocrosses, occurrences, etc. For realizing real-time classification assuring acceptable recognition accuracy, we combined two simple linear classifiers (k-NN and Bayes) in decision level fusion. Overall, a recognition accuracy of 94% was achieved by using the combined classifier with a selected feature set. The performance of the interfacing system was evaluated through 40 test sessions with 30 subjects using an RC Car. Instead of using a remote control unit, the car was controlled by four different gestures performed with one hand. In addition, we conducted a study to investigate the controllability and ease of use of the interface and the employed gestures.

[1]  M. Akay,et al.  Biosignal pattern recognition and interpretation systems. 2. Methods for feature extraction and selection , 1993, IEEE Engineering in Medicine and Biology Magazine.

[2]  M. S. Blois,et al.  What is medical informatics? , 1986, The Western journal of medicine.

[3]  G Tröster,et al.  The Agenda of Wearable Healthcare , 2005, Yearbook of Medical Informatics.

[4]  Johannes Wagner,et al.  From Physiological Signals to Emotions: Implementing and Comparing Selected Methods for Feature Extraction and Classification , 2005, 2005 IEEE International Conference on Multimedia and Expo.

[5]  Pattie Maes,et al.  Intimate interfaces in action: assessing the usability and subtlety of emg-based motionless gestures , 2007, CHI.

[6]  Touradj Ebrahimi,et al.  Brain-computer interface in multimedia communication , 2003, IEEE Signal Process. Mag..

[7]  Enrico Costanza,et al.  EMG as a Subtle Input Interface for Mobile Computing , 2004, Mobile HCI.

[8]  Peter Norvig,et al.  Bioelectric Control of a 757 Class High Fidelity Aircraft Simulation , 2000 .

[9]  Wookho Son,et al.  A new means of HCI: EMG-MOUSE , 2004, 2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583).

[10]  Marimuthu Palaniswami,et al.  Hand gestures for HCI using ICA of EMG , 2006 .

[11]  Atau Tanaka,et al.  A Wireless, Network-based Biosensor Interface for Music , 2002, ICMC.

[12]  Nagisa Munekata,et al.  Entertainment feature of a game using skin conductance response , 2004, ACE '04.

[13]  K. R. Wheeler.  Device control using gestures sensed from EMG , 2003, Proceedings of the 2003 IEEE International Workshop on Soft Computing in Industrial Applications, 2003. SMCia/03..

[14]  Rajesh P. N. Rao,et al.  Real-Time Classification of Electromyographic Signals for Robotic Control , 2005, AAAI.

[15]  M Reischl,et al.  [Expanding control possibilities of myoelectric hand prostheses]. , 2002, Biomedizinische Technik. Biomedical engineering.

[16]  Johannes Wagner,et al.  Emote toWin: Affective Interactions with a Computer Game Agent , 2004, GI Jahrestagung.