Research on Video Expression Recognition Based on Migrated Convolutional Neural Network

Abstract

Face expression recognition is an important part of artificial intelligence research and development, and it is also one of the important technologies to ensure the human-computer friendly interaction to truly achieve the intelligent goal. After understanding the dynamic time warping and its improved algorithm, this paper analyzes how to design video facial expression recognition system based on 3D-CNN according to the construction and application of convolutional neural network.