Far-Field, Multi-Camera, Video-to-Video Face Recognition
Aristodemos Pnevmatikakis, Lazaros Polymenakos · 2007
In section 2 of this chapter we will present the state-of-the-art in video-to-video face recognition, mostly near-field with people moving towards the camera.In section 3 we will address all the before-mentioned challenges of video-to-video face recognition, by analyzing the tradeoffs of different face segmentation approaches, face recognition methods and decision fusion strategies.We will base our analysis on a publicly available database of videos, built by the partners of the CHIL project (Waibel et al., 2004) and already used in the CLEAR 2006 evaluations (Stiefelhagen et al., 2007).This database offers recordings at five different sites, 26 individuals, two different gallery video lengths and four different probe video lengths. Far-Field, Multi-Camera, Video-to-Video Face Recognition How to referenceIn order to correctly reference this scholarly work, feel free to copy and paste the following: Aristodemos Pnevmatikakis and Lazaros Polymenakos (2007).Far-Field, Multi-Camera, Video-to-Video Face Recognition, Face Recognition, Kresimir Delac and Mislav Grgic (Ed.),