MIT and Microsoft build a new algorithm to find hidden links between historic paintings

If you use Twitter regularly, you must’ve come across celebrities as food tweet threads. Some examples are Rihanna as Indian food and Olly Alexander as cakes. The idea is to match the look and color of the food to the celeb’s clothes. Researchers from MIT‘s Computer Science and Artificial Intelligence Laboratory (CSAIL) and Microsoft have created a new algorithm that matches paintings from the Metropolitan Museum of Art and Amsterdam’s Rijksmuseum through hidden stylistic connections.  The MosAIc system is inspired by the “Rembrandt and Velazquez” exhibit in the Rijksmuseum that has paired up paintings which might seem different but actually have some connection in terms of interpretation or style. For example, in the exhibit Francisco de Zurbarán’s, The Martyrdom of Saint Serapion is paired up with Jan Asselijn’s The Threatened Swan; both of them have visual similarities in terms of posture. Credit: MIT The researchers spun up an algorithm that finds similar images to a query. For example: “which musical instrument is closest to this painting of a blue and white dress?” They found that result is a blue and white porcelain violin — that also helped them draw cultural exchanges between The Dutch and the Chinese.  MosAIc is similar to Google’s X degrees of separation experiment which…  


We will be happy to hear your thoughts

Leave a reply

Enable registration in settings - general