A Gesture Recognition Algorithm Based on PCA and BP Neural Network
Hong Yi Li, Junjie Chen, Xin Li, Di Zhao · Advanced materials research · 2013
Gesture recognition has many applications in fields such as the intelligent robot, human computer interaction and so on. The classical BP neural network has its advantages in modeling the highly nonlinear mapping from features to gesture meanings, and could avoid hard-coded feature extraction. However, it usually takes a rather long training and testing time, especially in dealing with redundant high dimensional data. To address this drawback, we combine the BP neural network and PCA, and propose an improved algorithm. Experiments demonstrate the feasibility and efficiency of the proposed algorithm by comparing with the classical one.