Digital art recommendation system : A personalized virtual tour of digital collections

Abstract: The purpose of this project is to create a website with a React-based prototype recommendation system of a large cultural collection. The aim of the website is to provide a function that allows a user to upload an image to which the system consequently recommends correlating artwork from the publicly available collection of the Metropolitan Museum of Modern Art (MET). The correlation coefficient between the uploaded image and the artworks from (MET) is acquired through Pearson Correlation. Furthermore the artwork with the highest correlation to the uploaded picture is shown first, then each subsequent artwork is shown in order of highest correlation. The main challenge for building this prototype was to combine the different components together with JavaScript and the REACT framework. The recommendation engine demands numerical representations of these artworks, and most effort was given to the automatic conversion of photos of artworks into a proper format for the recommendation engine.