A facial expression recognition method with improved residual network is proposed to address the problems of low recognition accuracy and loss of detailed features in the discriminative task due to inappropriate pooling in current facial expression recognition models. First, multi-scale importance pooling with adaptively learned input feature weights is proposed to improve the model's ability to retain and recognize global features. Second, asymmetric convolution is used to augment the convolution kernels to improve the characterization of local features, and the set of asymmetric convolution kernels trained to convergence is fused and equivalently converted to the original network structure to avoid introducing additional parameter optimization in the inference stage. Finally, the expression recognition accuracies of 85.53% and 72.72% were achieved in two publicly available datasets, RAF-DB and FER2013, respectively, and the experimental results demonstrate the effectiveness of the proposed method with certain application prospects.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.