Quantitative modeling of artist styles in Renaissance face portraiture

Renaissance portraits were depictions of some important royals of those times. Analysis of faces in these portraits can provide valuable dynastical information in addition to enriching personal details of the depicted sitter. Such studies can offer insights to the art-history community in understanding and linking personal histories. In particular, face recognition technologies can be useful for identifying subjects when there is ambiguity. However, portraits are subject to several complexities such as aesthetic sensibilities of the artist or social standing of the sitter. Thus, for robust automated face recognition, it becomes important to model the characteristics of the artist. In this paper, we focus on modeling the styles of artists by considering case studies involving Renaissance art-works. After a careful examination of artistic trends, we arrive at relevant features for analysis. From a set of instances known to match/not match, we learn distributions of match and non-match scores which we collectively refer to as the portrait feature space (PFS). Thereafter, using statistical permutation tests we learn which of the chosen features were emphasized in various works involving (a) same artist depicting same sitter, (b) same sitter but by different artists and (c) same artist but depicting different sitters. Finally, we show that the knowledge of these specific choices can provide valuable information regarding the sitter and/or artist.