Common mistakes on face recognition based on video
Vincent Despiegel, Stéphane Gentric · 2012
Abstract: Automatic border control e gates relies on face recognition in video streams. Two family of methods could be imagined to define a common workflow: encode all that is possible or select the best image of the stream according to a quality assessment. In gates, giving an answer as soon as possible by encoding each and every possible image seems to lead to faster gates. Is it really the case? 1