activity
20172022
most citedOpen Source Handwritten Text Recognition on Medieval Manuscripts using Mixed Models and Document-Specific Finetuning

1 citations · 1 across the 2 of their papers we have counts for

collaborators

8 papers

cs.CV20221 cited

Open Source Handwritten Text Recognition on Medieval Manuscripts using Mixed Models and Document-Specific Finetuning

Christian Reul, Stefan Tomasek, Florian Langhanki +1

This paper deals with the task of practical and open source Handwritten Text Recognition (HTR) on German medieval manuscripts. We report on our efforts to construct mixed recogniti…

cs.CV2021

Mixed Model OCR Training on Historical Latin Script for Out-of-the-Box Recognition and Finetuning

Christian Reul, Christoph Wick, Maximilian Nöth +3

In order to apply Optical Character Recognition (OCR) to historical printings of Latin script fully automatically, we report on our efforts to construct a widely-applicable polyfon…

cs.CV2018

State of the Art Optical Character Recognition of 19th Century Fraktur Scripts using Open Source Engines

Christian Reul, Uwe Springmann, Christoph Wick +1

In this paper we evaluate Optical Character Recognition (OCR) of 19th century Fraktur scripts without book-specific training using mixed models, i.e. models trained to recognize a…

cs.CL2018

Ground Truth for training OCR engines on historical documents in German Fraktur and Early Modern Latin

Uwe Springmann, Christian Reul, Stefanie Dipper +1

In this paper we describe a dataset of German and Latin \textit{ground truth} (GT) for historical OCR in the form of printed text line images paired with their transcription. This…

cs.CV2018

Calamari - A High-Performance Tensorflow-based Deep Learning Package for Optical Character Recognition

Christoph Wick, Christian Reul, Frank Puppe

Optical Character Recognition (OCR) on contemporary and historical data is still in the focus of many researchers. Especially historical prints require book specific trained OCR mo…

cs.CV2018

Improving OCR Accuracy on Early Printed Books by combining Pretraining, Voting, and Active Learning

Christian Reul, Uwe Springmann, Christoph Wick +1

We combine three methods which significantly improve the OCR accuracy of OCR models trained on early printed books: (1) The pretraining method utilizes the information stored in al…