Comparison of face image quality metrics: Electronic and legacy mug shots

Abstract

Automated face recognition offers an effective method for identifying individuals. Face images have been used in a number of different applications, including driver's licenses, passports and identification cards. To provide some form of standardization for photographs in these applications, ISO / IEC JTC 1 SC 37 have developed standardized data interchange formats to promote interoperability. There are many different publically available face databases available to the research community that are used to advance the field of face recognition algorithms, amongst other uses. In this paper, we examine how an existing database that has been used extensively in research (FERET) compares with two operational data sets with respect to some of the metrics outlined in the standard ISO / IEC 19794-5. The goals of this research are to provide the community with a comparison of a baseline data set and to compare this baseline to a photographic data set that has been scanned in from mug-shot photographs, as well as a data set of digitally captured photographs. It is hoped that this information will provide Face Recognition System (FRS) developers some guidance on the characteristics of operationally collected data sets versus a controlled-collection database.