Covariates of face recognition

Abstract

Face recognition has found several applications ranging from cross border security, surveillance, access control, multimedia to forensics. Face recognition under variations due to pose, illumination, and expression has been extensively studied in literature and several approaches have been proposed to address these covariates. Many applications of face recognition require matching face images with variations in age and disguise such as matching a recent photo with your passport image or image on driver’s license. In literature, techniques have also been proposed to recognize face images with variations in age and disguise. These challenges can be grouped as existing covariates of face recognition. However, with ever increasing applications of face recognition there has emerged a need to understand new fascinating challenges in face recognition, emerging covariates of face recognition. Covariates such as forensic sketches, surgically altered faces, low resolution faces, and look-alikes or twins are some of the challenges that have emerged as new covariates of face recognition. These covariates have important law enforcement applications; therefore, it has now become imperative for current face recognition systems to be robust to these challenges. This report focuses on three different aspects. First, it presents a review of different techniques proposed to address the existing covariates, limitations of current techniques and future scope of advancements. Second, it presents how the emerging covariates have evolved, what are the challenges, proposed techniques, and future research directions for each of these covariates. Finally, the report presents an evolutionary granular approach to address one of the emerging covariate, plastic surgery.