Abstract
In the current study of facial expression recognition, CNNs have been extensively used and proven to be useful models. In this work, we analyze and improve VGG-16 network by embedding SENet between the convolutional layers and three fully connected layers of the original network to form the SE-VGG-16 network. The proposed network architecture is able to extract additional spatial information regarding interdependencies among feature channels, which is complementary to facial expression recognition. The experiment is performed on dataset FER2013 and improve the accuracy with top-1 error 33.5.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
