Abstract

Face recognition is for recognizing human faces from single images out of a large database. The task is difficult because of image variation in terms of position, size, expression, and pose and it is important because this uses in different areas such as surveillance at airports, border crossings, security systems etc. There are two underlying motivations for us to write this survey paper: the first is to provide an up-to-date review of the existing literature, and the second is to offer some insights into the studies of machine recognition of faces. There are many methods exist to perform face detection, on this, Some use flesh tones, some use contours, and other are even more complex involving templates, neural networks, or filters. This all methods generally utilize 2D images for feature extraction and matching. Nowadays some of the algorithms make use of 3D images for the same. It will give more accurate and higher resilience towards covariates, such as expression, illumination and pose variations. But it is challenging because of the high cost of 3D sensors. RGB-D face recognition is introduced to reduce this problem of high cost of 3D sensors, which makes use of the features of both original image and depth image for the face recognition. This survey focuses on different 2D or 3D or combination of both face recognition techniques under different covariates, such as illuminations, expressions, noise, disguised conditions and different pose variations.

Authors and Affiliations