Abstract
This paper describes face recognition across facial expressions variations. We focus on an automatic feature extraction technique which is not only efficient but also accurate for person identification. A 3D wireframe model is fitted to face images using a robust objective function. Furthermore, we extract structural and textural information which is coupled with temoral information from the motion of local facial features. The extracted information is combined to form a feature vector descriptor for each image. This set of features has been tested on two databases for face recognition across facial expressions. We use Bayesian Network (BN) and Binary Decision Trees (BDT) as classifiers. The developed system is automatic, real-time capable and efficient.
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.
