OCR4all - An Open-Source Tool Providing a (Semi-)Automatic OCR Workflow for Historical Printings

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 recognition and segmentation, character recognition and post-processing. The drawback of these tools often is their limited applicability by non-technical users like humanist scholars and in particular the combined use of several tools in a workflow. In this paper we present an open-source OCR software called OCR4all, which combines state-of-the-art OCR components and continuous model training into a comprehensive workflow. A comfortable GUI allows error corrections not only in the final output, but already in early stages to minimize error propagations. 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. Experiments showed that users with minimal or no experience were able to capture the text of even the earliest printed books with manageable effort and great quality, achieving excellent character error rates (CERs) below 0.5%. The fully automated application on 19th century novels showed that OCR4all can considerably outperform the commercial state-of-the-art tool ABBYY Finereader on moderate layouts if suitably pretrained mixed OCR models are available. The architecture of OCR4all allows the easy integration (or substitution) of newly developed tools for its main components by standardized interfaces like PageXML, thus aiming at continual higher automation for historical printings.

End-to-end platform evaluation for Spanish Handwritten Text Recognition

“…Not only the text recognition task, but also the segmentation workflows needed to be covered, preferably in one single software package. OCR4All (Reul et al, 2019) was the chosen software package, including the training tasks of HTR models for the Spanish language. This software contains several modules for the image pre-processing phases (binarization, noise removal and paragraph and line segmentation), and also has a complete infrastructure for training, evaluation and inference of text recognition models based on CNN-LSTM architectures.…”

Optical Character Recognition of 19th Century Classical Commentaries: the Current State of Affairs

“…First, Lace 6 is a GUI-based platform for the visualization and manual correction of OCR output, designed for automatic conversion to TEI-encoded XML. Second, OCR4all [14] is an open source OCR tool explicitly developed for users with no prior technical background, and especially those working on the earliest printed books. It implements an iterative workflow that allows for rapidly training very accurate OCR models for specific publications or publication series.…”

“…In the second workflow, images were segmented and pre-processed before being passed to Tesseract. However, since Tesseract could not be prevented from resegmenting words in its own fashion 14 , this workflow performed poorly (results not reported).…”

Optical character recognition with neural networks and post-correction with finite state methods

“…In Germany, there is the OCR-D 4 coordination project, with 8 project modules focused on various stages of OCR. Also in Germany, OCR4all [28] has recently published an open-source tool providing a (semi-)automatic OCR Workflow for historical prints. The workflow was created using different open-source tools.…”