Robust text line detection in historical documents: learning and evaluation methods

Text line segmentation is one of the key steps in historical document understanding. It is challenging due to the variety of fonts, contents, writing styles and the quality of documents that have degraded through the years. In this paper, we address the limitations that currently prevent people from...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:International journal on document analysis and recognition Ročník 25; číslo 2; s. 95 - 114
Hlavní autoři: Boillet, Mélodie, Kermorvant, Christopher, Paquet, Thierry
Médium: Journal Article
Jazyk:angličtina
Vydáno: Berlin/Heidelberg Springer Berlin Heidelberg 01.06.2022
Springer Nature B.V
Springer Verlag
Témata:
Annotations
Computer Science
Datasets
Documents
Engineering Sciences
Fonts
Image Processing and Computer Vision
Original Paper
Pattern Recognition
Segmentation
Signal and Image processing
Generic architecture
Evaluation strategy
Text line detection
Historical documents
Goal-directed evaluation
Text line detection ; Historical documents;Generic architecture;Evaluation strategy ; Goal-directed evaluation
ISSN:1433-2833, 1433-2825
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Text line segmentation is one of the key steps in historical document understanding. It is challenging due to the variety of fonts, contents, writing styles and the quality of documents that have degraded through the years. In this paper, we address the limitations that currently prevent people from building line segmentation models with a high generalization capacity. We present a study conducted using three state-of-the-art systems Doc-UFCN, dhSegment and ARU-Net and show that it is possible to build generic models trained on a wide variety of historical document datasets that can correctly segment diverse unseen pages. This paper also highlights the importance of the annotations used during training: Each existing dataset is annotated differently. We present a unification of the annotations and show its positive impact on the final text recognition results. In this end, we present a complete evaluation strategy using standard pixel-level metrics, object-level ones and introducing goal-oriented metrics.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1433-2833
1433-2825
DOI:10.1007/s10032-022-00395-7