Face Expression Recognition based on Improved Rank Expansion Network
Guangyu Wang, Xiaoshu Luo, Zhaoxing Xu, Fangyu Feng, Jiangjie Xu · 2022 IEEE 5th Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC) · 2022
A face expression recognition method based on an improved rank expansion network is proposed to address the problem that when traditional convolutional neural networks recognize facial expressions, the network has difficulty in fully extracting the important expression features leading to low recognition accuracy. First, based on the idea of migration learning, the pre-training parameters of large-scale image sets are used to initialize the rank expansion network and accelerate the training of the model. Then, the face expression features are further enriched by fusing the underlying detailed features and the high-level semantic features at different scales. Finally, a stepped attention module is embedded before feature fusion to construct the contextual relationships of semantic features from three different dimensions to strengthen the expression of important features. The experimental results show that the improved network achieves 88.07% and 88.68% accuracy on the face expression datasets RAF-DB and FERPlus, which is a significant improvement over the original network.