Research on Facial Expression Recognition Based on Convolutional Neural Network
Download as PDF
Wang Xuyang, Chen Jinheng
The main research methods of face recognition technology include geometric features and algebraic features. With the advent of artificial intelligence era, the rapid development of machine learning, the BP neural network and CNN (Convolutional Neural Network) model under deep learning have greatly improved the speed and accuracy of face recognition, which has greatly improved the stability, accuracy and rapidity of face recognition system. For a long time, as an important part of computer vision research, the traditional method of selecting features manually by machine learning and then training shallow classifiers for recognition is not satisfactory in the field of facial expression recognition. Facial expression involves machine learning contents such as image processing, computer vision, pattern recognition, etc. It is a multidisciplinary field. This paper attempts to apply the method of deep learning to facial expression recognition, construct a deep convolution neural network suitable for facial expression recognition, and put forward some effective improvement schemes in training algorithm and structure.
Expression recognition, Convolutional neural network, Image processing