TY - GEN
T1 - Robust gesture detection and recognition using dynamic time warping and multi-class probability estimates
AU - Pisharady, Pramod Kumar
AU - Saerbeck, Martin
PY - 2013/9/16
Y1 - 2013/9/16
N2 - 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.
AB - 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.
KW - Hand gesture recognition
KW - alphabet recognition
KW - directional features
KW - dynamic time warping
KW - hierarchical thresholding
KW - probability estimates
KW - quaternions
UR - http://www.scopus.com/inward/record.url?scp=84883659785&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84883659785&partnerID=8YFLogxK
U2 - 10.1109/CIMSIVP.2013.6583844
DO - 10.1109/CIMSIVP.2013.6583844
M3 - Conference contribution
AN - SCOPUS:84883659785
SN - 9781467359177
T3 - Proceedings of the 2013 IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing, CIMSIVP 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013
SP - 30
EP - 36
BT - Proceedings of the 2013 IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing, CIMSIVP 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013
T2 - 2013 IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing, CIMSIVP 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013
Y2 - 16 April 2013 through 19 April 2013
ER -