Though humanistic in spirit and scholarship, the practice of art history has long recognized the value of science-based investigative techniques, particularly for questions involving artwork authentication. Traditional principles of connoisseurship and provenance research have evolved to include analysis of chemical composition and physical structure. The McMullen Museum and the Art, Art History & Film Department welcome Andrea Frank and Steven Frank for a virtual lecture on the use of convolutional neural networks as a new tool to extend scientific analysis to a painting’s visual features. Trained on the works of an artist under study and visually comparable works of other artists, their system can identify forgeries and propose attributions. It can also assign classification probabilities within a painting, revealing mixed authorship and identifying regions painted by different hands. Although computational, their approach supplements and depends on human expertise in judging a painting’s authenticity and lived history.

Join live at https://bccte.zoom.us/j/93994883582

Andrea Frank, formerly Curator of Visual Resources at Boston College, and Steven J. Frank, computer scientist and intellectual property attorney, are independent researchers and co-founders of Art Eye-D Associates LLC.  Their work has recently appeared in the peer-reviewed journals Leonardo and Neural Computation and has been the subject of articles in the Art Newspaper, Artsy, and Art Critique.