Probabilistic recognition of human faces from video

TitleProbabilistic recognition of human faces from video
Publication TypeConference Papers
Year of Publication2002
AuthorsChellappa R, Kruger V, Zhou S
Conference NameImage Processing. 2002. Proceedings. 2002 International Conference on
Date Published2002///
KeywordsBayes, Bayesian, CMU;, distribution;, Face, faces;, gallery;, handling;, human, image, images;, importance, likelihood;, methods;, NIST/USF;, observation, posterior, probabilistic, probability;, processing;, propagation;, recognition;, sampling;, sequential, signal, still, Still-to-video, Uncertainty, video, Video-to-video

Most present face recognition approaches recognize faces based on still images. We present a novel approach to recognize faces in video. In that scenario, the face gallery may consist of still images or may be derived from a videos. For evidence integration we use classical Bayesian propagation over time and compute the posterior distribution using sequential importance sampling. The probabilistic approach allows us to handle uncertainties in a systematic manner. Experimental results using videos collected by NIST/USF and CMU illustrate the effectiveness of this approach in both still-to-video and video-to-video scenarios with appropriate model choices.