BSC and Prado Museum Teach AI to View and Interpret Works of Art
June 27, 2023 -- The Barcelona Supercomputing Center - Centro Nacional de Supercomputación (BSC-CNS) and the Museo Nacional del Prado have unveiled the FrAI Angelico project. This innovative initiative showcases how artificial intelligence (AI) can make cultural heritage more accessible to the public.
Central to the project is the utilization of machine learning (ML) systems which are designed to identify the content of paintings along with their historical and iconographic contexts. This advanced technology enables a detailed description of each painting to be produced without any human intervention.
In recent years, the Museo Nacional del Prado has spearheaded various AI projects. In 2019, it initiated an enhanced interpretation of the descriptive texts for artworks displayed on its website. This was facilitated through a Natural Language Understanding (NLU) engine. The engine can identify the entities and concepts discussed in these texts, thereby providing users with a more contextualized reading experience.
Now, in collaboration with BSC-CNS, the museum is taking another significant step in harnessing AI for studying and promoting its collections. The museum plans to implement a system designed to assist in recognizing objects in the images of the artworks.
Javier Pantoja, Head of Digital Development at the Museo Nacional del Prado, elaborated, "With NLU, we help our users to better understand the explanatory texts of the works, thanks to their augmented reading. With this project, our intention is, among other things, to support the work of documentalists and specialists in the recognition and description of objects, figures and themes of the works."
AI is a powerful tool for cultural heritage professionals, primarily due to its proficiency in analyzing vast quantities of data. Researchers at BSC's Computational Applications for Science and Engineering (CASE) department have developed an AI model specifically for object detection. This AI model has been trained with descriptions of thousands of paintings, enabling it to accurately analyze the content of paintings in the Prado Museum. It can even identify details or objects that might escape the notice of the human eye.
FrAI Angelico is a prototype that builds upon the technology of an earlier EU-funded project, Saint George on a Bike. This previous project was coordinated by the Barcelona Supercomputing Center (BSC) in partnership with the Europeana Foundation.
In its initial phase, the FrAI Angelico project will analyze 25 artworks. However, the long-term goal is to foster a more enduring collaboration that enables a comprehensive analysis of the entire Prado Museum collection. This collection, deemed the most significant cultural institution in the country, houses over 35,000 works of art.
Among these, 8,000 pieces form part of the painting collection, recognized as one of the most important in Europe. It features works by celebrated artists such as Velázquez, Goya, El Greco, Rubens, Titian, and Raphael, to name a few.
Mobile Phones in 16th Century Paintings
Object recognition systems are trained with images that show the different elements that surround us. Once trained, these AI models can detect new shapes and interpret them in their temporal context. This has been one of the main challenges of the project, as until now systems trained in a given context made interpretation errors in different environments, leading them to identify mobile phones or baseball bats in paintings from the 16th or 17th centuries.
Similarly, the new models are also able to detect objects that are common in pictorial representations of the past, such as a skull, a crown of thorns, angels or demons. The next challenge is to teach these AI systems to interpret abstract concepts in classical European paintings; such as that two naked bodies plus an angel probably represent Adam and Eve, or a dove accompanied by an angel and a person represent the Holy Spirit.
"With the FrAI Angelico project, we also seek to provoke reflection on the potential of AI to recognize the past, culture or symbols," explained Joaquim Moré, researcher in the CASE group at the BSC. "Comparing the analysis of the new models trained at the BSC with the results of other current object recognition systems is an exercise that invites us to think about how we look at the past with the eyes of the present and revives the fascination produced by the contemplation of a painting and the discovery of what is not apparent."
More Accessible Works of Art for the Visually Impaired
The proficiency of AI systems in identifying objects within paintings will significantly aid the Prado Museum and other cultural heritage institutions. It will enable them to automatically describe and categorize their artworks, thereby simplifying the interpretation of works of art.
The results from the FrAI Angelico project can serve various purposes. They can be used to study the thematic relationships among thousands of elements from different artworks simultaneously. This aids in the development of iconographic documentation related to the museum's collections, and it also supports the classification of artworks based on themes and objects depicted. In addition, this technology will be particularly beneficial for visually impaired individuals. They stand to gain from a more accessible format of the artworks due to the enhanced descriptions of the images.
"Thanks to this initiative, it will be possible to analyze the paintings, detect objects that the visitor may not have noticed, infer themes, discover relationships between their elements or interpret their symbolism in order to create cultural and dissemination initiatives such as virtual exhibitions with related paintings from all over the world. And, above all, this work will serve as the basis for a new way of studying and understanding our cultural heritage," concluded Maria Cristina Marinescu, researcher in the CASE group at the BSC.
About BSC
Barcelona Supercomputing Center-Centro Nacional de Supercomputación (BSC-CNS) is the national supercomputing center in Spain. The center is specialized in high performance computing (HPC) and manages MareNostrum, one of the most powerful supercomputers in Europe, located in the Torre Girona chapel.
Source: BSC-CNS