@phdthesis{Wick2020,
  author    = {Wick, Christoph},
  title     = {Optical Medieval Music Recognition},
  doi       = {10.25972/OPUS-21434},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-214348},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2020},
  abstract  = {In recent years, great progress has been made in the area of Artificial Intelligence (AI) due to the possibilities of Deep Learning which steadily yielded new state-of-the-art results especially in many image recognition tasks. Currently, in some areas, human performance is achieved or already exceeded. This great development already had an impact on the area of Optical Music Recognition (OMR) as several novel methods relying on Deep Learning succeeded in specific tasks. Musicologists are interested in large-scale musical analysis and in publishing digital transcriptions in a collection enabling to develop tools for searching and data retrieving. The application of OMR promises to simplify and thus speed-up the transcription process by either providing fully-automatic or semi-automatic approaches. This thesis focuses on the automatic transcription of Medieval music with a focus on square notation which poses a challenging task due to complex layouts, highly varying handwritten notations, and degradation. However, since handwritten music notations are quite complex to read, even for an experienced musicologist, it is to be expected that even with new techniques of OMR manual corrections are required to obtain the transcriptions. This thesis presents several new approaches and open source software solutions for layout analysis and Automatic Text Recognition (ATR) for early documents and for OMR of Medieval manuscripts providing state-of-the-art technology. Fully Convolutional Networks (FCN) are applied for the segmentation of historical manuscripts and early printed books, to detect staff lines, and to recognize neume notations. The ATR engine Calamari is presented which allows for ATR of early prints and also the recognition of lyrics. Configurable CNN/LSTM-network architectures which are trained with the segmentation-free CTC-loss are applied to the sequential recognition of text but also monophonic music. Finally, a syllable-to-neume assignment algorithm is presented which represents the final step to obtain a complete transcription of the music. The evaluations show that the performances of any algorithm is highly depending on the material at hand and the number of training instances. The presented staff line detection correctly identifies staff lines and staves with an \$F_1\$-score of above \$99.5\\%\$. The symbol recognition yields a diplomatic Symbol Accuracy Rate (dSAR) of above \$90\\%\$ by counting the number of correct predictions in the symbols sequence normalized by its length. The ATR of lyrics achieved a Character Error Rate (CAR) (equivalently the number of correct predictions normalized by the sentence length) of above \$93\\%\$ trained on 771 lyric lines of Medieval manuscripts and of 99.89\\% when training on around 3.5 million lines of contemporary printed fonts. The assignment of syllables and their corresponding neumes reached \$F_1\$-scores of up to \$99.2\\%\$. A direct comparison to previously published performances is difficult due to different materials and metrics. However, estimations show that the reported values of this thesis exceed the state-of-the-art in the area of square notation. A further goal of this thesis is to enable musicologists without technical background to apply the developed algorithms in a complete workflow by providing a user-friendly and comfortable Graphical User Interface (GUI) encapsulating the technical details. For this purpose, this thesis presents the web-application OMMR4all. Its fully-functional workflow includes the proposed state-of-the-art machine-learning algorithms and optionally allows for a manual intervention at any stage to correct the output preventing error propagation. To simplify the manual (post-) correction, OMMR4all provides an overlay-editor that superimposes the annotations with a scan of the original manuscripts so that errors can easily be spotted. The workflow is designed to be iteratively improvable by training better models as soon as new Ground Truth (GT) is available.},
  subject      = {Neumenschrift},
  language  = {en}
}
@phdthesis{Reul2020,
  author    = {Reul, Christian},
  title     = {An Intelligent Semi-Automatic Workflow for Optical Character Recognition of Historical Printings},
  doi       = {10.25972/OPUS-20923},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-209239},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2020},
  abstract  = {Optical Character Recognition (OCR) on historical printings is a challenging task mainly due to the complexity of the layout and the highly variant typography. Nevertheless, in the last few years great progress has been made in the area of historical OCR resulting in several powerful open-source tools for preprocessing, layout analysis and segmentation, Automatic Text Recognition (ATR) and postcorrection. Their major drawback is that they only offer limited applicability by non-technical users like humanist scholars, in particular when it comes to the combined use of several tools in a workflow. Furthermore, depending on the material, these tools are usually not able to fully automatically achieve sufficiently low error rates, let alone perfect results, creating a demand for an interactive postcorrection functionality which, however, is generally not incorporated. This thesis addresses these issues by presenting an open-source OCR software called OCR4all which combines state-of-the-art OCR components and continuous model training into a comprehensive workflow. While a variety of materials can already be processed fully automatically, books with more complex layouts require manual intervention by the users. This is mostly due to the fact that the required Ground Truth (GT) for training stronger mixed models (for segmentation as well as text recognition) is not available, yet, neither in the desired quantity nor quality. To deal with this issue in the short run, OCR4all offers better recognition capabilities in combination with a very comfortable Graphical User Interface (GUI) that allows error corrections not only in the final output, but already in early stages to minimize error propagation. In the long run this constant manual correction produces large quantities of valuable, high quality training material which can be used to improve fully automatic approaches. Further on, extensive configuration capabilities are provided to set the degree of automation of the workflow and to make adaptations to the carefully selected default parameters for specific printings, if necessary. The architecture of OCR4all allows for an easy integration (or substitution) of newly developed tools for its main components by supporting standardized interfaces like PageXML, thus aiming at continual higher automation for historical printings. In addition to OCR4all, several methodical extensions in the form of accuracy improving techniques for training and recognition are presented. Most notably an effective, sophisticated, and adaptable voting methodology using a single ATR engine, a pretraining procedure, and an Active Learning (AL) component are proposed. Experiments showed that combining pretraining and voting significantly improves the effectiveness of book-specific training, reducing the obtained Character Error Rates (CERs) by more than 50\%. The proposed extensions were further evaluated during two real world case studies: First, the voting and pretraining techniques are transferred to the task of constructing so-called mixed models which are trained on a variety of different fonts. This was done by using 19th century Fraktur script as an example, resulting in a considerable improvement over a variety of existing open-source and commercial engines and models. Second, the extension from ATR on raw text to the adjacent topic of typography recognition was successfully addressed by thoroughly indexing a historical lexicon that heavily relies on different font types in order to encode its complex semantic structure. During the main experiments on very complex early printed books even users with minimal or no experience were able to not only comfortably deal with the challenges presented by the complex layout, but also to recognize the text with manageable effort and great quality, achieving excellent CERs below 0.5\%. Furthermore, the fully automated application on 19th century novels showed that OCR4all (average CER of 0.85\%) can considerably outperform the commercial state-of-the-art tool ABBYY Finereader (5.3\%) on moderate layouts if suitably pretrained mixed ATR models are available.},
  subject      = {Optische Zeichenerkennung},
  language  = {en}
}