T. Nishimura, Real World Comput. Partnership, Tsukuba Res. Center, Ibaraki, Japan
R. Oka, Real World Comput. Partnership, Tsukuba Res. Center, Ibaraki, Japan
We study spotting recognition of human gestures from time-varying images. We propose a feature extraction method and a spotting method. The feature extraction reduces each frame of motion into a frame image of small size, such as 3 X 3 pixels. We show that the feature with 3 X 3 is the best one to provide robust characteristics to the changes of cloth and background. The spotting recognition rate was about 80% for 8 gesture categories. A new spotting method called non-monotonic continuous DP is proposed for spotting gestures and their variations such as reverse, partial and stop motions. We show the effectiveness of the new spotting method.
Index Terms:
image recognition; human gesture recognition; time-varying images; spotting recognition; feature extraction method; spotting method; image motion; frame image; pixels; robust characteristics; nonmonotonic continuous dynamic programming; reverse motions; partial motion; stop motion
Citation:
T. Nishimura, R. Oka, "Spotting recognition of human gestures from time-varying images," fg, pp.318, Second IEEE International Conference on Automatic Face and Gesture Recognition (FG '96), 1996
PURCHASE ARTICLE: $19
IEEE Xplore Subscribers
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb