Noise reduction for face identification in videos

The wealth of information extracted from a sequence of frames in a video provides samples of the subject in different illuminations, head poses, and facial expressions. However, various sources can impose noise on data (e.g., occlusion, low resolution, and face detection failures). In this thesis, a novel framework is proposed that employs the well-studied concepts in quantum probability theory to design a representation structure capable of making inferences with multiple sources of uncertainty. The dual extension of this framework is aimed at reducing the effect of noisy frames in a video. It is also used to guide the sampling process in a novel learning scheme, called specialization generalization, which is designed to support efficient learning, as well as neutralizing the effect of noisy samples in the identification process. The contributions of this thesis are not method-specific and can be utilized for enhancement of other face identification approaches in the literature. --Leaf i.