%0 Journal Article
%A YU An-Yu
%A YU Xian-Lun
%T Facial expression recognition based on improved ResNet
%D 2023
%R 10.19682/j.cnki.1005-8885.2023.2003
%J Journal of China Universities of Posts and Telecommunications
%P 28-38
%V 30
%N 1
%X <span>Facial expression recognition (FER) is a vital application of image processing technology. In this paper, a FER&nbsp;</span><span>model based on the residual network is proposed. The proposed model introduces the idea of the DenseNet, in&nbsp;</span><span>which the outputs of the residual blocks are not simply added but are linked to the channel dimension. In addition,&nbsp;</span><span>transfer learning is used to reduce training costs and accelerate training speed. The accuracy and robustness of the&nbsp;</span><span>proposed FER model were tested by K-fold cross-validation. Experimental results show that the proposed method&nbsp;</span><span>has competitive performances on FER2013, FER plus (FERPlus), and the real-world affective faces database&nbsp;</span><span>(RAF-DB).</span>
%U https://jcupt.bupt.edu.cn/EN/10.19682/j.cnki.1005-8885.2023.2003