Abstract: Face recognition is effective when input low resolutions are of high resolution (HR). Face images captured by surveillance cameras are of low resolution (LR) uncontrolled pose and illumination etc. There are several methods to improve the quality of low resolution image and perform the face recognition process. This paper primarily focuses on the review of those methods. The main objective is to find out and compare completely automatic approaches for recognizing low-resolution face images captured in uncontrolled environment. The approaches used are Discriminative super resolution, Hallucination using Eigen transformation, singular value decomposition, Simultaneous super resolution and recognition.
Keywords: Low resolution, hallucination, super resolution.