A hybrid Wavelet Neural Network and Switching Particle Swarm Optimization algorithm for face direction recognition

Face direction recognition is an important research issue in human-computer interaction. In order to improve recognition accuracy, a novel hybrid approach called Switching Particle Swarm Optimization-Wavelet Neural Network (SPSO-WNN) is presented. In this model, we employ the recently proposed Switching Particle Swarm Optimization (SPSO) algorithm to optimize the parameters of weights, scale factors, translation factors and threshold in Wavelet Neural Network (WNN). The proposed SPSO-WNN method has fast convergence speed and higher learning ability than conventional WNNs. Especially, a mode-dependent velocity updating equation with Markovian switching parameters is introduced in SPSO to overcome the contradiction between the local search and the global search, which makes it easy to jump the local minimum. The experiment results of the recognition for face direction show the feasibility and effectiveness of the proposed method. Compared with Particle Swarm Optimization-Wavelet Neural Network (PSO-WNN), Genetic Algorithm-Wavelet Neural Network (GA-WNN) and WNN, the proposed method has much better performance over them.