Affiliation:
1. Computer Vision Center, Computer Science Department, Universitat Autònoma de Barcelona, Edifici O, Bellaterra, Barcelona, Spain
2. University of Gothenburg, Gothenburg, Sweden
Abstract
Recent breakthroughs in Artificial Intelligence, Deep Learning, and Document Image Analysis and Recognition have significantly eased the creation of digital libraries and the transcription of historical documents. However, for documents in rare scripts with few labelled training data available, current Handwritten Text Recognition (HTR) systems are too constraining. Moreover, research on HTR often focuses on technical aspects only, and rarely puts emphasis on implementing software tools for scholars in Humanities. In this article, we describe, compare, and analyse different transcription methods for rare scripts. We evaluate their performance in a real-use case of a medieval manuscript written in the runic script (
Codex Runicus
) and discuss advantages and disadvantages of each method from the user perspective. From this exhaustive analysis and comparison with a fully manual transcription, we raise conclusions and provide recommendations to scholars interested in using automatic transcription tools.
Funder
Swedish Research Council
DECRYPT – Decryption of Historical Manuscripts, the Spanish project
CERCA Program/Generalitat de Catalunya and the FI fellowship AGAUR 2020
Publisher
Association for Computing Machinery (ACM)
Subject
Computer Graphics and Computer-Aided Design,Computer Science Applications,Information Systems,Conservation
Reference30 articles.
1. A. Fornés, B. Megyesi, and J. Mas. 2017. Transcription of encoded manuscripts with image processing techniques. In Digital Humanities Conference (DH2017). 441–443.
2. Hierarchical k-means: An algorithm for centroids initialization for K-means;Arai Kohei;Reports of the Faculty of Science and Engineering,2007
3. Towards a Generic Unsupervised Method for Transcription of Encoded Manuscripts
4. Asma Bensalah, Pau Riba, Alicia Fornés, and Josep Lladós. 2019. Shoot less and sketch more: An efficient sketch classification via joining graph neural networks and few-shot learning. In International Workshop on Graphics Recognition (GREC). IEEE, 80–85.
5. Bartosz Bogacz, Nicholas Howe, and Hubert Mara. 2016. Segmentation free spotting of cuneiform using part structured models. In 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR). IEEE, 301–306.