Recognizing people by face and body in Photo Collections
Markus Brenner, Ebroul Izquierdo · 2013
We show how to detect and recognize people based on their faces and bodies in Consumer Photo Collections. We devise a graphical model that incorporates multiple contextual cues to discriminate faces, upper and lower bodies, and ultimately, individuals without relying on faces. For efficiency, we only consider body features when faces are not discriminative enough. Experiments on two datasets demonstrate the effectiveness of our probabilistic approach.