In this talk we seek to provide insight on the general topic of visual soft biometrics (gender, age, ethnicity, etc.). First, we present a new refined definition of soft biometrics, emphasizing on the aspect of human compliance, and then proceed to identify candidate traits that accept this novel definition. Second, we introduce some image processing techniques related to the estimation of some traits (weight, color of clothes, make-up, age and gender). Third, we address relations between traits and discuss associated benefits and limitations of these traits. We consider a new application, namely human identification solely carried out by a bag of facial, body and accessory soft biometric traits, and as an evidence of its practicality, we provide preliminary promising results. Finally, we conclude our presentation by some of our on-going activities in the domain of facial aesthetics based on facial soft biometric traits.
Keynote speech 1: Bag of visual soft biometrics for person identification: New trends and challenges
ICSIPA 2015, IEEE International Conference on Signal and Image Processing Applications, 19-21 October 2015, Kuala Lumpur, Malaysia
© 2015 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
PERMALINK : https://www.eurecom.fr/publication/4869