EURECOM

Katel Le Floc’h & François Murgadella: » Download the press release «

Abstract We introduce, in this paper, a new scheme of score level fusion for face authentication from visible and thermal face data. This proposed scheme provides a fast and straightforward integration into existing face recognition systems and does not require recollection of enrollment data in thermal spectrum.

Image credit: Unsplash Abstract Crowd density analysis is a crucial component in video surveillance mainly for security monitoring. This paper proposes a novel approach for crowd density classification, in which learned features substitute the commonly used handcrafted features.