SILKNOW is a Horizon 2020 project that produced an intelligent computational system that goes beyond current technologies to improve our understanding of European silk heritage. The project applied next-generation ICT (information and communications technologies) research to meet the needs of users in various fields, such as museums, education, tourism, cultural and creative industries.
Silk was a major factor in technological progress in Europe, allowing for the exchange of ideas and driving innovation. Punched cards were first used in Jacquard silk looms, long before modern computers were even imagined, while the Western Silk Road, a network of production and market centres, connected countries across the continent.
SILKNOW helps preserve the intangible heritage of ancient weaving techniques by using pre-existing digitised information about silk to study, showcase and preserve silk digital collections. Users can access the collections through an exploratory search engine, spatio-temporal maps and 3D visual and tangible simulations. This broad approach is made possible through the close cooperation of a multidisciplinary team with a wide range of expertise.
The pre-existing data was analysed and processed with advanced text analytics and image-based deep learning techniques in order to homogenise their content, automatically retrieve semantic information, complete poorly tagged data and translate the text into four languages. This data can then be accessed and searched by anyone, making the information easy to find and accessible.
Among the most important results were the multilingual thesaurus, which allows users to use local terms and phrases in their search terms, helping to standardise these terms. Another is the Virtual Loom, a ground-breaking tool that produces 3D representations of fabrics at the yarn level and preserves historical weaving techniques, most of which are only known by artisans who usually orally transmit their knowledge. ADASilk (Advanced Data Analysis for Silk heritage), integrates an exploratory search engine and a Spatio-temporal map, built on top of the SILKNOW’s knowledge graph that contains nearly 40,000 fabric entries with images and other relevant information describing them. Finally, the educational materials called La Ruta de la Seda were specially designed for learning Spanish while learning about silk in Europe.
“SILKNOW has created an innovative system to facilitate the transfer of the knowledge of silk weaving. This project represents an important example of how crafts, and therefore intangible heritage, can be linked to digital tools and how these tools can be used to democratise access to technical knowledge. The project’s machine-learning thesaurus is particularly interesting and has the potential to be applied in other areas of research,” stated the Awards’ Jury.