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. / Die Optische Zeichenerkennung (Optical Character Recognition, OCR) auf historischen Drucken stellt nach wie vor eine große Herausforderung dar, hauptsächlich aufgrund des häufig komplexen Layouts und der hoch varianten Typographie. In den letzten Jahre gab es große Fortschritte im Bereich der historischen OCR, die nicht selten auch in Form von Open Source Tools interessierten Nutzenden frei zur Verfügung stehen. Der Nachteil dieser Tools ist, dass sie meist ausschließlich über die Kommandozeile bedient werden können und somit nicht-technische Nutzer schnell überfordern. Außerdem sind die Tools häufig nicht aufeinander abgestimmt und verfügen dementsprechend nicht über gemeinsame Schnittstellen.
Diese Arbeit adressiert diese Problematik mittels des Open Source Tools OCR4all, das verschiedene State-of-the-Art OCR Lösungen zu einem zusammenhängenden Workflow kombiniert und in einer einzigen Anwendung kapselt. Besonderer Wert liegt dabei darauf, auch nicht-technischen Nutzern zu erlauben, selbst die ältesten und anspruchsvollen Drucke selbstständig und mit höchster Qualität zu erfassen. OCR4all ist vollständig über eine komfortable graphische Nutzeroberfläche bedienbar und bietet umfangreiche Möglichkeiten hinsichtlich Konfiguration und interaktiver Nachkorrektur. Zusätzlich zu OCR4all werden mehrere methodische Erweiterungen präsentiert, um die Effektivität und Effizienz der Trainings- und Erkennungsprozesse zur Texterkennung zu optimieren.
Während umfangreicher Evaluationen konnte gezeigt werden, dass selbst Nutzer ohne nennenswerte Vorerfahrung in der Lage waren, OCR4all eigenständig auf komplexe historische Drucke anzuwenden und dort hervorragende Zeichenfehlerraten von durchschnittlich unter 0,5% zu erzielen. Die methodischen Verbesserungen mit Blick auf die Texterkennung reduzierten dabei die Fehlerrate um über 50% im Vergleich zum etablierten Standardansatz.
| Identifer | oai:union.ndltd.org:uni-wuerzburg.de/oai:opus.bibliothek.uni-wuerzburg.de:20923 |
| Date | January 2020 |
| Creators | Reul, Christian |
| Source Sets | University of Würzburg |
| Language | English |
| Detected Language | English |
| Type | doctoralthesis, doc-type:doctoralThesis |
| Format | application/pdf |
| Rights | https://creativecommons.org/licenses/by/4.0/deed.de, info:eu-repo/semantics/openAccess |
Page generated in 0.0029 seconds