Outputs (21)

Encoding of Digitised Documents (2025)
Thesis

This work presents solutions to the multifaceted problem of document encoding in the context of digitisation processes. It addresses aspects related to structure and layout on page level as well as mechanisms for representing underlying textual infor... Read More about Encoding of Digitised Documents.

NAME – A Rich XML Format for Named Entity and Relation Tagging (2023)
Presentation / Conference Contribution

We present NAME XML, a schema for named entities and relations in documents. The standout features are: option to reference a variety of document formats (such as PAGE XML or plain text), support of entity hierarchies, custom entity types via ontolog... Read More about NAME – A Rich XML Format for Named Entity and Relation Tagging.

A survey of OCR evaluation tools and metrics (2021)
Presentation / Conference Contribution

The millions of pages of historical documents that are digitized in libraries are increasingly used in contexts that have more specific requirements for OCR quality than keyword search. How to comprehensively, efficiently and reliably assess the qual... Read More about A survey of OCR evaluation tools and metrics.

Flexible character accuracy measure for reading-order-independent evaluation (2020)
Journal Article

The extraction of textual information from scanned document pages is a fundamental stage in any digitisation effort and directly determines the success of the overall document analysis and understanding application scenarios. To evaluate and improve... Read More about Flexible character accuracy measure for reading-order-independent evaluation.

A cloud-hosted MapReduce architecture for syntactic parsing (2019)
Presentation / Conference Contribution

Syntactic parsing is a time-consuming task innatural language processing particularlywherea largenumber of text files are beingprocessed. Parsingalgorithms are conventionally designed to operate on a single machine in a sequenti... Read More about A cloud-hosted MapReduce architecture for syntactic parsing.

Efficient and effective OCR engine training (2019)
Journal Article
Clausner, C., Antonacopoulos, A., & Pletschacher, S. (2020). Efficient and effective OCR engine training. International Journal on Document Analysis and Recognition, 23(1), 73-78. https://doi.org/10.1007/s10032-019-00347-8

We present an efficient and effective approach to train OCR engines using the Aletheia document analysis system. All components required for training are seamlessly integrated into Aletheia: training data preparation, the OCR engine’s training proces... Read More about Efficient and effective OCR engine training.

ICDAR2017 Competition on Recognition of Early Indian Printed Documents – REID2017 (2017)
Presentation / Conference Contribution

This paper presents an objective comparative evaluation of page analysis and recognition methods for historical documents with text mainly in Bengali language and script. It describes the competition (modus operandi, dataset and evaluation methodolog... Read More about ICDAR2017 Competition on Recognition of Early Indian Printed Documents – REID2017.

ICDAR2017 Competition on Recognition of Documents with Complex Layouts – RDCL2017 (2017)
Presentation / Conference Contribution

This paper presents an objective comparative evaluation of page segmentation and region classification methods for documents with complex layouts. It describes the competition (modus operandi, dataset and evaluation methodology) held in the context o... Read More about ICDAR2017 Competition on Recognition of Documents with Complex Layouts – RDCL2017.

Creating a complete workflow for digitising historical census documents : considerations and evaluation (2017)
Presentation / Conference Contribution

The 1961 Census of England and Wales was the first UK census to make use of computers. However, only bound volumes and microfilm copies of printouts remain, locking a wealth of information in a form that is practically unusable for research. In this... Read More about Creating a complete workflow for digitising historical census documents : considerations and evaluation.

Unearthing the recent past : digitising and understanding statistical information from census tables (2017)
Presentation / Conference Contribution

Censuses comprise a wealth of information at a large (national) scale that allow governments (who commission them) and the public to have a detailed snapshot of how people live (geographical distribution and characteristics). In addition to underpinn... Read More about Unearthing the recent past : digitising and understanding statistical information from census tables.