@article{FischerHarteltPuppe2023,
  author    = {Fischer, Norbert and Hartelt, Alexander and Puppe, Frank},
  title     = {Line-level layout recognition of historical documents with background knowledge},
  series = {Algorithms},
  volume    = {16},
  journal   = {Algorithms},
  number    = {3},
  issn      = {1999-4893},
  doi       = {10.3390/a16030136},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-310938},
  year      = {2023},
  abstract  = {Digitization and transcription of historic documents offer new research opportunities for humanists and are the topics of many edition projects. However, manual work is still required for the main phases of layout recognition and the subsequent optical character recognition (OCR) of early printed documents. This paper describes and evaluates how deep learning approaches recognize text lines and can be extended to layout recognition using background knowledge. The evaluation was performed on five corpora of early prints from the 15th and 16th Centuries, representing a variety of layout features. While the main text with standard layouts could be recognized in the correct reading order with a precision and recall of up to 99.9\%, also complex layouts were recognized at a rate as high as 90\% by using background knowledge, the full potential of which was revealed if many pages of the same source were transcribed.},
  language  = {en}
}
@article{WickHarteltPuppe2019,
  author    = {Wick, Christoph and Hartelt, Alexander and Puppe, Frank},
  title     = {Staff, symbol and melody detection of Medieval manuscripts written in square notation using deep Fully Convolutional Networks},
  series = {Applied Sciences},
  volume    = {9},
  journal   = {Applied Sciences},
  number    = {13},
  issn      = {2076-3417},
  doi       = {10.3390/app9132646},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-197248},
  year      = {2019},
  abstract  = {Even today, the automatic digitisation of scanned documents in general, but especially the automatic optical music recognition (OMR) of historical manuscripts, still remains an enormous challenge, since both handwritten musical symbols and text have to be identified. This paper focuses on the Medieval so-called square notation developed in the 11th-12th century, which is already composed of staff lines, staves, clefs, accidentals, and neumes that are roughly spoken connected single notes. The aim is to develop an algorithm that captures both the neumes, and in particular its melody, which can be used to reconstruct the original writing. Our pipeline is similar to the standard OMR approach and comprises a novel staff line and symbol detection algorithm based on deep Fully Convolutional Networks (FCN), which perform pixel-based predictions for either staff lines or symbols and their respective types. Then, the staff line detection combines the extracted lines to staves and yields an F\(_1\) -score of over 99\% for both detecting lines and complete staves. For the music symbol detection, we choose a novel approach that skips the step to identify neumes and instead directly predicts note components (NCs) and their respective affiliation to a neume. Furthermore, the algorithm detects clefs and accidentals. Our algorithm predicts the symbol sequence of a staff with a diplomatic symbol accuracy rate (dSAR) of about 87\%, which includes symbol type and location. If only the NCs without their respective connection to a neume, all clefs and accidentals are of interest, the algorithm reaches an harmonic symbol accuracy rate (hSAR) of approximately 90\%. In general, the algorithm recognises a symbol in the manuscript with an F\(_1\) -score of over 96\%.},
  language  = {en}
}