Understand Me if You Can! Global Soft Biometrics Recognition from Social Visual Data.

In a relatively short period of time, we have observed the explosion of social network platforms which have acquired a prominent role in the people's daily life. Hence, the extensive use of social networks has generated huge amounts of both visual and textual data that started to gain greater attention. However, the development of effective techniques for the acquisition and analysis of social data has drawn the attention of many researchers. The result of the huge mass of social data from different sources and types has provided many opportunities for researchers in the fields of discovering hidden soft biometrics information from data, which can be used for a variety of applications. In this paper, we propose a novel framework to understand and manage both textual and visual data form social networks, such as Facebook to extract the user' soft biometrics information from posted pictures, specifically age, gender, race and smile.