PROJECT TITLE :

Face Recognition Across Non-Uniform Motion Blur, Illumination, and Pose - 2015

ABSTRACT:

Existing methods for performing face recognition in the presence of blur are based on the convolution model and cannot handle non-uniform blurring things that regularly arise from tilts and rotations in hand-held cameras. During this paper, we propose a methodology for face recognition in the presence of area-varying motion blur comprising of arbitrarily-formed kernels. We have a tendency to model the blurred face as a convex combination of geometrically remodeled instances of the centered gallery face, and show that the set of all pictures obtained by non-uniformly blurring a given image forms a convex set. We first propose a nonuniform blur-sturdy algorithm by making use of the idea of a sparse camera trajectory in the camera motion space to make an energy operate with l1-norm constraint on the camera motion. The framework is then extended to handle illumination variations by exploiting the fact that the set of all pictures obtained from a face image by non-uniform blurring and changing the illumination forms a bi-convex set. Finally, we tend to propose a chic extension to conjointly account for variations in pose.