Art history studies rely firstly on data, whatever the type, which is then interpreted in layers of contextualization aiming to describe the evolution of human artistic production. This project will build upon the conceptual framework of a renewed epistemology for art history brought by contemporary computational models. The analysis of relevant features inherent to visual culture and the study of hidden correlations between them allows the opportunity for renewed interpretations never accessed before. Therefore, the project is focused on the study of two elemental features present in paintings: face expression and light. First, the use of face mesh models allows the abstraction of facial expressions from depicted faces. Second, by means of Intrinsic Image Decomposition (IID) and image processing techniques it is possible to describe light conditions (i,e., direction, intensity, diffuseness).

The development of a computational model for the study of such features attempts to represent in a mathematical feature space the proportions, light conditions, and colors from depicted faces of particular characters, schools, and iconographies. The interpretation of the generated outcomes will be based on the hypothesis that light creates space, thus the description of light features allows the possibility of revealing compositional patterns across paintings. Light is also present as a sign of knowledge, as illumination has been used as a sign of divine communication. The duality of light and form is present as

a metaphor for the soul and the body. If light is used to suit a message rather than to fulfill the requirements of the physical world, can we find similar light conditions present in different narratives? does the meaning of light have a mathematical representation? can we find relationships between light features and character’s relevance (soul)? Once shade light on the embedded information hidden under paintings, the project opens up new possibilities for a close understanding of contextualized iconographies, as well as distant viewing approaches to the description of particular motifs and patterns that improve our understanding of the interaction between light and expression.