A Facial Expression Recognition Algorithm based on CNN and LBP Feature

In recent years, facial expression recognition technology has been widely used in computer vision, security monitoring and image classification. However, in practical application, it is difficult to solve the rotation problem of facial expression image, which leads to the decrease of expression recognition rate and is difficult to meet the actual demand. Although the convolutional neural network (CNN) can extract the high -dimensional features of the image and has the invariance of gray scale, it does not have the invariance of rotation. Local binary model (LBP) is a feature extraction algorithm with rotation invariance, which can solve the rotation problem to some extent. To solve the above problems, this paper proposes a face expression recognition algorithm based on CNN and LBP, and compares this algorithm with other algorithms. The simulation results show that this algorithm can improve the expression recognition rate under rotation to some extent.