Weighted Modified Hu Moment in Human Behavior Recognition
t has been shown that the traditional seven Hu invariant moment does not have scaling invariance with low recognition rate in human behavior recognition. In order to improve the recognition rate, a human behavior recognition method will be put forward in this paper based on weighted modified Hu moments. Firstly, the traditional seven Hu moments will be extended to ten Hu moments to get more image details. Then, the extended Hu moments will be modified to make the Hu moments has the feature of scaling invariance. Lastly, the weighted modified Hu moment will be obtained through least squares method based on minimum variance criterion. The simulation of the sequence images shows that the weighted modified Hu moment can improve the recognition rate effectively.