Research on Facial Expression Recognition Based on Improved Inception Network

Abstract

Facial expression recognition is one of the hot research fields in computer vision. Deep learning method is widely used due to its excellent performance in feature characterization. However, convolutional neural network, which is commonly used in the field of image classification, is prone to challenges such as too many parameters, difficulty in training and too many network layers. We proposed an improved inception network to solve the above. In this model, small-scale filter was used to replace large-scale one and multi-channel features were extracted. In addition, a smaller stochastic gradient value introduced in the ReLU makes the weights of some neurons be able to update. AM-softmax is adopted as the loss function with respect of the issue that the large intra-class distance about expression features. The recognition rates of the proposed model on CK+ and FER2013 are 98.32% and 71.12%, respectively. The experimental results verify the effectiveness of the proposed algorithm.

Classroom Video Image Emotion Analysis Method for Online Teaching Quality Evaluation

“…It is more direct and effective to capture the emotional changes of teachers and students and classroom emotions through facial expressions. In recent years, with the development of facial expression recognition technology, it has become an inevitable trend to promote the application of image processing in online teaching classroom emotion analysis [6][7][8][9][10][11][12][13][14].…”