Abstract
Facial expressions are one of the important non-verbal ways used to understand human emotions during communication. Thus, acquiring and reproducing facial expressions is helpful in analyzing human emotional states. However, owing to complex and subtle facial muscle movements, facial expression modeling from images with face poses is difficult to achieve. To handle this issue, we present a method for acquiring facial expressions from a non-frontal single photograph using a 3D-aided approach. In addition, we propose a contour-fitting method that improves the modeling accuracy by automatically rearranging 3D contour landmarks corresponding to fixed 2D image landmarks. The acquired facial expression input can be parametrically manipulated to create various facial expressions through a blendshape or expression transfer based on the FACS (Facial Action Coding System). To achieve a realistic facial expression synthesis, we propose an exemplar-texture wrinkle synthesis method that extracts and synthesizes appropriate expression wrinkles according to the target expression. To do so, we constructed a wrinkle table of various facial expressions from 400 people. As one of the applications, we proved that the expression-pose synthesis method is suitable for expression-invariant face recognition through a quantitative evaluation, and showed the effectiveness based on a qualitative evaluation. We expect our system to be a benefit to various fields such as face recognition, HCI, and data augmentation for deep learning.
Highlights
The human face conveys a range of biological and social characteristics
To achieve a realistic facial expression synthesis, we propose an exemplar-texture wrinkle synthesis method that extracts and synthesizes appropriate expression wrinkles according to the target expression
Facial expressions are important for understanding the emotional states and intentions of other people
Summary
The human face conveys a range of biological and social characteristics. facial expressions are one of the crucial factors in understanding an individual’s emotional state and intentions in human communication, and facial expression recognition (FER) has attracted considerable attention from academia and commercial industries. A multilinear face model [9] supports a decoupled space of combined variations, such as the identities, expressions, and visemes on the facial shape and provides separate control for these attributes. Deep-learning-based approaches [14,15] have recently been studied to overcome the limitations of a linear 3DMM representation power and the need for 3D facial scans for the learning process Using these promising 3D-based methods, researchers have used a 3D face to correct the input poses toward the frontal view. As with the pose problem, because 2D image warping methods do not correctly account for changes in facial geometry and viewpoint, a number of approaches have been developed to model and animate natural facial expressions in a.
Sign-in/Register to view highlights & summary 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.
