Research on Face Recognition Based on the Fusion of Convolution and Wavelet Neural Network

Abstract

Intelligent artificial neural network (ANN) is an important method of reasoning and deduction of face recognition, which greatly improves the correctness and efficiency of intelligent decision making. The existed neural network algorithm for face recognition is difficult to take both self-learning and local reasoning into account, making the algorithm of face recognition highly complex and the processing delay too long. In order to solve the problem of high complexity and long delay, this paper analyzes the adaptability of the neural network theory and face recognition. Some newest algorithms are introduced, such as the backward feedback BP neural network, fine-tuning wavelet neural network, self -learning particle swarm neural network, and identity-preserving convolution neural network. A new method of face recognition based on the fusion of convolution and wavelet neural network is proposed, which optimizes the design of dynamic matching input layer, reduces the scale of large-scale data input, designs the implicit layer design of expansion with sharing and self-learning. It effectively achieve fusing self-learning and local reasoning. Besides it also improves the accuracy of face recognition by using the adaptive controllable feedback output layer.