Improvement of continuous dynamic programming for human gesture recognition
Hang Wu, Ryutaro KIDO, Tadayoshi Shioyama · 2002
This paper describes an improved continuous dynamic programming (CDP) for human gesture recognition. In order to cope with the variation in the amplitude of the input signal, a reference pattern set containing patterns with different mean amplitudes is used instead of a single reference pattern. Next, a new multiple search path determination strategy is developed to replace the traditional single one to deal with the variation in the speed of the input gesture. Also, a matching error controlled path determination method is introduced to reduce the influence of noises. The experimental results show this CDP can give stable recognition results compared with the conventional one.