Hand Gestures Recognition Based on SEMG Signal Using Wavelet and Pattern Recognisation

In this paper, we introduced a novel and simple methods of extracting the general features of the hand gestures from surface EMG signal patterns: Hand Extension (H.E), Hand Grasp(H.G),Wrist Extension(W.E),Wrist Flexion(W.F)Pinch(P),Thumb Flexion (T.F). Hand gesture EMG signal classification is demonstrated as a method for prosthesis applications. Recorded electrode signals from the Abductor Pollicies longus above the elbow are noise filtered and transformed into features using wavelet transforms. Feature sets for six different hand gestures are classified by minimum distance classifier technique. Features construction, recognition accuracy and an approach for an extension of the technique to a variety of real world application areas are presented. KEY TERMS: Surface Electromyography, wavelet, SEMG signal features, pattern recognition, prosthesis.