Orbis Pictus – book revival for cultural and creative sectors

Collections of the Czech libraries contain a vast amount of information. Despite the dominance of textual information, a significant part of our cultural heritage is also information captured graphically, be it drawings, maps, diagrams, graphs, photographs, tables or other primarily graphic elements. As digitisation progresses, the deployment of OCR and full-text search systems is opening up hitherto hidden textual cultural heritage to the public. The aim of the presented project is to open the graphic content of digital libraries to the public in a similar way. Using machine learning methods, it will be possible to identify the graphic elements contained in digitized documents, to categorize them by type, to add contextual data to facilitate their retrieval and to extend the range of services of our digital libraries by a system for retrieving the graphic elements identified in this way. An important part of the project's outputs will be a tool for finding different images of the same persons and a database of identified persons. The project will thus result, among other things, in a significant facilitation of access by external users to graphic elements contained in library collections and their further use in other creative industries.