CITlab ARGUS for historical handwritten documents
This work addresses the problem of digitizing historical documents for archivists and researchers, but it is incremental as it applies existing methods to a specific competition task.
The paper tackled the recognition of historical handwritten documents using a system based on multi-dimensional recurrent neural networks (MDRNN) and connectionist temporal classification (CTC), achieving participation in the HTRtS competition at ICFHR 2014.
We describe CITlab's recognition system for the HTRtS competition attached to the 14. International Conference on Frontiers in Handwriting Recognition, ICFHR 2014. The task comprises the recognition of historical handwritten documents. The core algorithms of our system are based on multi-dimensional recurrent neural networks (MDRNN) and connectionist temporal classification (CTC). The software modules behind that as well as the basic utility technologies are essentially powered by PLANET's ARGUS framework for intelligent text recognition and image processing.