Ground Truth for training OCR engines on historical documents in German Fraktur and Early Modern Latin

09/14/2018
by   Uwe Springmann, et al.
0

In this paper we describe a dataset of German and Latin ground truth (GT) for historical OCR in the form of printed text line images paired with their transcription. This dataset, called GT4HistOCR, consists of 313,173 line pairs covering a wide period of printing dates from incunabula from the 15th century to 19th century books printed in Fraktur types and is openly available under a CC-BY 4.0 license. The special form of GT as line image/transcription pairs makes it directly usable to train state-of-the-art recognition models for OCR software employing recurring neural networks in LSTM architecture such as Tesseract 4 or OCRopus. We also provide some pretrained OCRopus models for subcorpora of our dataset yielding between 95% (early printings) and 98% (19th century Fraktur printings) character accuracy rates on unseen test cases, a Perl script to harmonize GT produced by different transcription rules, and give hints on how to construct GT for OCR purposes which has requirements that may differ from linguistically motivated transcriptions.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/15/2017

Transfer Learning for OCRopus Model Training on Early Printed Books

A method is presented that significantly reduces the character error rat...
research
08/06/2016

OCR of historical printings with an application to building diachronic corpora: A case study using the RIDGES herbal corpus

This article describes the results of a case study that applies Neural N...
research
06/15/2021

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

In order to apply Optical Character Recognition (OCR) to historical prin...
research
10/13/2021

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

Together with critical editions and translations, commentaries are one o...
research
08/26/2019

End-To-End Measure for Text Recognition

Measuring the performance of text recognition and text line detection en...
research
10/09/2018

Decipherment of Historical Manuscript Images

European libraries and archives are filled with enciphered manuscripts f...
research
06/12/2023

Contrastive Attention Networks for Attribution of Early Modern Print

In this paper, we develop machine learning techniques to identify unknow...

Please sign up or login with your details

Forgot password? Click here to reset