Low cost RGB-D cameras are gaining significant popularity in surveillance scenarios. While RGB images contain good quality discriminative information, depth images captured in uncontrolled environment at a distance does not provide accurate depth map. In this research, we present a learning based reconstruction and mapping algorithm to generate a feature rich representation from the RGB images. These reconstructed images are then used for face identification. The experiments performed on both IIITD RGB-D database and the challenging Kasparov database show that the proposed algorithm yields significant improvements compared to when the original depth map is used for identification. Comparison with existing state-of-the-art algorithm also demonstrates the efficacy of the proposed architecture. © 2016 IEEE.