Children’s Face Recognition Based on Convolutional Neural Network

Abstract

Abstract Nowadays, the application of deep learning is more and more widely, and children’s face recognition has made great progress. However, in the existing framework of children’s face recognition based on deep learning, many tasks (including face recognition, authentication and attribute classification) are relatively independent, and its overall algorithm is inefficient and time-consuming. In order to solve this problem, this paper proposes a deep convolution network based on keras framework. Taking children’s face recognition, authentication and attributes as the parameters of the network, the whole deep convolution network can be trained step by step. The network can complete three tasks at the same time without further steps. The network model is trained and learned on the training samples. It is an efficient neural network model. The network structure scheme of this method can improve the classification accuracy It has a certain positive impact. The purpose of this paper is to construct a network model structure, which can make the children face recognition effect better and still obtain good performance under the limited data support.