Robust gesture detection and recognition using dynamic time warping and multi-class probability estimates

A robust hand gesture detection and recognition algorithm using dynamic time warping and multi-class probability estimates is proposed. Quaternion based directional features of the hand are extracted using the color-depth camera Kinect. The directional features utilized have position and orientation invariance. Dynamic time warping of the signal sequence is done to achieve gesture size and speed invariance, and to enhance the gesture detection capability. The gestures are detected by hierarchical thresholding of the gesture probability and warping distance. Classification of gestures is done by multi-class probability estimates. The proposed algorithm is tested using a 12 class alphabet gesture database having variations in size, orientation, and speed. The algorithm provided 97.72% detection and 96.85% recognition accuracies respectively. A comparison of the proposed method with existing approaches (for detection as well as recognition) shows its better performance.