A comprehensive survey of unimodal facial databases in 2D and 3D domains

Abstract

Biometrics is an automated authentication mechanism that allows the identification or verification of individuals based on unique physiological and behavioral characteristics. In addition to novel biometric recognition frameworks and protocols, standard databases containing biometric trait information are essential for providing convincing results. This survey paper presents a comprehensive list of publicly available database for the biometric modality of face in both 2D and 3D domains. For each of the studied database, we have presented a brief description of the database which describes the motivation behind their creation, their salient characteristics and the domains of their utility. Additionally, we have provided an active URL link for each database which contains either their direct download link or the web-page which describes the procedure for their acquisition. Our study would allow researchers working in areas related to face recognition to conveniently gather information about all the available resources (databases), learn their associated characteristics, and subsequently select an appropriate database which best suits their research objectives. © 2019 Elsevier B.V.