The Moravian Library Labs is a library programme for innovations and experimentation in digital research practice and scholarship. In the Labs, you will find tools and data sets based on our digital collections, research case studies, digital resources, as well as selected research activities or crowdsourcing intentions of the library.
Digital Research Infrastructure for the Language Technologies, Arts and Humanities
Obálkyknih.cz is a collaborative project among Czech libraries and for Czech libraries. In this project, libraries are able to integrate images of book cover pages into their catalogues, allowing for integration of tables of contents, book reviews, and other valuable information. It aggregates different books information sources into one, easy-to-use web service. Developed in collaboration with the Moravian Library in Brno, the project is maintained at the Research Library of South Bohemia in České Budějovice.
One of the main results of this project is a database of Moravian Library's historical collections. Worth mention is also software development in the field of digital libraries, revolving about online publishing of large images. This research influenced national standards for digitisation and also laid foundation to most of the successive projects listed here.
The Moravian Library in Brno houses the esteemed Moll's Map Collection, which has recently earned recognition as a UNESCO Memory of the World registered archive. This remarkable collection has undergone digitization and can be accessed online at mapy.mzk.cz. Furthermore, the entire collection has been georeferenced with the assistance of the staremapy.cz portal and indexed by OldMapsOnline.org. To aid catalogers in organizing sheet maps from extensive map series, the Moravian Library has developed the MapSeries tool.
Open – Loaded is an international project focused on digitisation, accessibility and educational use of art collections in memory institutions. Project team: Olomouc Museom of Art, Moravian Library, Library of the Czech Academy of Sciences and National Archives of Iceland.
EU projects
eBooks-On-Demand-Network Opening Publications for European Netizens project aims to make publications from the 20th and 21st centuries available in digital form for the general public. Moravian Library's role in EOD OPEN is to make contributions of our European partners publicly accessible by anyone in the world. We collect useful data from our partners' digital libraries and upload their digitized works to the common portal.
NAKI II
After five years of implementation, five projects were completed in which the Moravian Library with universities and other libraries. Three of these projects brought several new tools and technologies that expanded and streamlined work with digitalized materials.
The project aimed to create technology and tools to improve accessibility of digitized historic documents based on methods of machine learning (neural networks), computer vision and language modelling. These methods enable existing digital archives and libraries to provide full-text search and content extraction for low quality historic printed and all hand written documents. For more try PERO-OCR application, which allows users to automatically transcribe several types of printed and handwritten documents.
The RightLib project created a technical infrastructure for accessing out-of-commerce publications in digital libraries, enabling remote access and on-site usage. It included the development of RightLib, a prototype linked with the Czech Digital Library.
The aim of the proposed project was to design a set of the new functionalities and independent tools that enables the extensive data mining procedures in digital libraries to cover the digital humanities researchers needs. The second project goal was to use this content in the applied research.
NAKI III — running projects
Optical music recognition using machine learning for digital libraries. The project aims to identify music notation in digitised documents and convert it to a searchable database of printed music.
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 present project is to open the graphic content of digital libraries to the public in a similar way.
The full-text search used in library systems is the simplest possible. In contrast, current web search engines work with the words' meanings, making it possible to find texts that are relevant to the topic searched, though not containing the exact search term. The main goal of this project is therefore to improve the searchability of the full-text representation of digitized documents at the level of text meaning and to improve the possibilities of natural navigation between related documents.
The project aims to create a semi-automatic digitisation line using machine learning tools to increase the efficiency of the digitisation process and, where possible, replace a number of manual activities by modern software.
Poslední aktualizace: 29.05.2023, 08:23