How does it work? The machine model in the background identifies typical visual features, distinguishing 9 different document types.
Training data were provided by the Organisation for Corruption and Crime Reporting Project (OCCRP).
For technical information see our paper or visit our GitHub repository.
We are happy to share our work or to assist you in setting up your own document classifier, customised for your needs. Feel free to contact us via ...
If you want to cite this, please refer to our paper: ...
Made by...
Department of Computer Science, University of Chile, Santiago, Chile
Department of Information Systems and Social Networks, University of Bamberg, Bamberg, Germany
M.A. Political Sciences/International Economic Policy, Free University Berlin and Sciences Po Paris
Department of Statistics and Operations Research, University of North Carolina at Chapel Hill, Chapel Hill, USA
German Research Center for Artificial Intelligence (DFKI), Kaiserslautern, Germany
German Research Center for Artificial Intelligence (DFKI), Kaiserslautern, Germany
Department of Computer Science, Rhineland-Palatinate Technical University at Kaiserslautern-Landau, Germany
In cooperation with OCCRP
