Research – Services – Network

READ (Recognition and Enrichment of Archival Documents) is an e-Infrastructure project funded by the European Commission and combines research, services and network building. It is focused on making archival material more accessible through the development of cutting-edge technologies.  You can get an overview of all the tools and technologies we are developing in our Interfaces Map.

Research is carried out in Pattern Recognition, Document Image Analysis, Computer Vision, and Natural Language Processing. Leading research groups from these fields are taking part in the project and will set new standards in Handwritten Text Recognition (HTR), Key Word Spotting, Layout Analysis, Automatic Writer Identification and related fields.

Services are provided to the main target groups of the project:

  • Archives, libraries and content holders
  • Humanities scholars
  • Public users and volunteers (crowd-users)
  • Computer scientists

We are dedicated to meeting the needs of our target groups. A wide portfolio of services is therefore offered through the service platform Transkribus.

Network building will be encouraged at all levels:

  • Archives and libraries are invited to join the project with a Memorandum of Understanding which will enable them to take part in testing the technology and contributing to the improvement of our tools
  • Humanities scholars are able to use the Transkribus platform for their own purposes, e.g. preparing training data for the HTR engines so that they are attuned to the specific documents in a collection of interest, or organising collaborative projects for transcribing historical documents
  • Public users and volunteers will be supported with specific user interfaces
  • Computer scientists will receive test and reference data for their research projects

Handwritten historical documents can be difficult to understand due to complex variations in handwriting styles, languages, character sets, layout and legibility.  But advances in research are making it possible for computers to process handwritten material.  The development of HTR technology therefore has the potential to revolutionize access to historical collections held by archives all over the world.

READ is an international collaboration between 14 partners drawn from the domains of computer science, archives and humanities research.  The project is funded by the European Union’s Horizon 2020 research and innovation programme under grant agreement No. 674943.