2023-06-27 12:39:01
The Barcelona Supercomputing Center – National Supercomputing Center (BSC-CNS) and the Museo Nacional del Prado have presented the project Brother Angelicowhich shows how artificial intelligence (AI) can help bring cultural heritage closer to the public. systems machine learning allow to recognize the content of the paintings and their historical and iconographic context, so that it is possible to obtain a detailed description of each frame without human intervention.
The Museo Nacional del Prado has developed different projects within the framework of AI in recent years. In 2019 it implemented increased reading on descriptive texts of the records of works published on the web through a Natural Language Understanding (NLU) engine that allows recognizing the entities and concepts dealt with in them to facilitate a contextualized reading for the user.
Now, with the support of the Barcelona Supercomputing Center, it will take a further step in the application of AI for the study and dissemination of its collections and will implement a system that will facilitate the object recognition on the images of the works themselves.
The artificial intelligence project will make it possible to recognize objects on pictorial works
“With the NLU we help our users to a better understanding of explanatory texts of the works thanks to their increased reading”, explains Javier Pantoja, Head of the Digital Development Area of the Museo Nacional del Prado. “In 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 subject matter of the works.”
AI is a powerful tool that can be of great use to cultural heritage professionals due to its ability to analyze large amounts of data. BSC researchers have developed an object detection AI model that they have trained with descriptions of thousands of paintings so that it is capable of accurately analyzing the content of the paintings, to the point of detecting details or objects that may go unnoticed by the human eye.
FrAI Angelico is a prototype based on the technology of a previous similar project, funded by the European Union, which was called Saint George on a Bikecoordinated by the BSC in collaboration with the European Foundation.
In the first phase, 25 works will be analyzed, but the objective is to establish a more stable collaboration that allows an overall analysis of the entire fund from the Prado Museum, considered the most important cultural institution in the country with more than 35,000 works of art, of which 8,000 belong to the collection of paintings, one of the most prominent in Europewith works by artists such as Velázquez, Goya, El Greco, Rubens, Titian or Rafael, among others.
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 forms and interpret them in its temporal context.
With the NLU we help our users to better understand the explanatory texts
Javier Pantoja, Head of the Digital Development Area of the Museo Nacional del Prado
This has been one of the main challenges of the project, since until now the systems trained in a certain context made interpretation errors in different environments, which led them to identify mobile phones or baseball bats in paintings from the 16th or 17th centuries. .
In the same way, the new models are also capable of detecting objects that are common in pictorial representations of the pastsuch as a skull, a crown of thorns, angels or demons.
The next challenge is to teach these AI systems to interpret abstract concepts in the classical european paintingsuch as two naked bodies plus an angel probably represent Adam and Eve or a dove accompanied by an angel and a person 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,” he says. Joaquim MoreBSC researcher.
“Comparing the analysis of the new models trained in 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”, he adds.
More accessible works for people with visual disabilities
The possibility that AI systems are capable of detecting the objects that appear in the paintings will help the Prado Museum and other institutions in the cultural heritage sector to describe and classify your artworks automaticallywhich will facilitate the interpretation of the meaning of the paintings.
The Prado Museum houses one of the most outstanding pictorial collections in Europe
The results of FrAI Angelico can be used to study the thematic relations among thousands of elements of different works simultaneously, develop iconographic documentation on the Museum’s works and support the classification of works by themes and objects represented.
All this always with the ultimate goal of increase public interest in art and cultural heritage. Also, as an example, this is especially useful for visually impaired people, who will be able to benefit from a more accessible format of pictorial works thanks to more detailed descriptions of the images.
“Thanks to this initiative, it will be possible to analyze the paintings, detect objects that the visitor may not have perceived, infer themes, discover relationships between their elements or interpret its symbolism in order to create cultural and dissemination initiatives such as virtual exhibitions with related paintings from anywhere in the world”, points out María Cristina MarinescuBSC researcher.
“This work will serve as the basis for a new way of studying and understanding our cultural heritage,” he concludes.
Rights: Creative Commons.
#develop #artificial #intelligence #interpret #works #art