Abstract
Continuous emotion recognition is the key concern of researchers working in the field of facial behavior analysis and human–computer interaction. An attempt for continuous emotion recognition is made along with the sparsity analysis. In the presented work, Gabor filters are used to extract features from facial images. Before applying Gabor filters, preprocessing is done on facial images so as to reduce the variance due to illumination, scaling, and rotation. The Gabor magnitude as well as Gabor phase is used to represent facial features. The features were applied to relevance vector regression for continuous emotion recognition. The sparsity analysis is done by analyzing the support vectors to ensure its application in real time. The proposed approach was evaluated on extended Cohn-Kanade database. The results represent the efficacy of the presented approach.
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.
