Facial Expression Recognition Based on Improved MobileNetV2 Network Model

In order to solve the problems of large size, large number of parameters and low accuracy of recognizing images with occluded faces in current neural network models, a facial expression recognition model based on improved MobileNetV2 is proposed. The model adopts linear bottleneck structure and inverted residual structure to reduce the size of the network model, increase the feature expression capability, and solve the gradient vanishing problem that occurs when the network depth increases; At the same time, the attention mechanism Squeeze-and-Excitation(SE) module and h-swish(HS) activation function are introduced to improve the model accuracy and reduce the number of parameters and calculations. This experiment was conducted on the facial expression datasets Fer2013 and CK+, and the accuracy of facial expression recognition reached 70.21% and 98.12% respectively on the proposed network model, demonstrating the effectiveness of the proposed model in expression recognition.