SyncAI.news, a Varaisys broadcasting
Generalization of Text Line Segmentation for HTR in Historical Documents
GH

Gayan H. Pathirage, Stephan M. Unter, Simon Corbill\'e, Elisa H. Barney Smith

· 1 min read

ResearcharXiv cs.CV

Generalization of Text Line Segmentation for HTR in Historical Documents

arXiv:2611.24726v1 Announce Type: new Abstract: In this paper we investigate the generalization capability of state-of-the-art object detection models (Hi-SAM, YOLO, and RT-DETR) for the automatic segmentation of text lines in historical documents. Generalization is needed because it is not practical for museums and archives to produce large amounts of labeled samples for each new collection. We also evaluate the few-shot setting by fine-tuning the networks with only a small number of training samples per target dataset. To this end, we use nine different datasets that differ significantly in visual layout and language. Additionally, we discuss why mean average precision (mAP), a classic evaluation metric for object detection, is insufficient for assessing the quality of a text line segmentation model. Depending on the dataset, our CRNN models achieve character error rates (CER) ranging from 2.48% to 7.07% per page for the segmented text lines. This is sufficient for reading comprehension and simple text searches. Finally, we quantify the resource and time requirements of training and inference in different use case settings. This forms the basis for more informed decisions about model and hardware choices based on available resources.

Original source

This story was published by arXiv cs.CV and written by Gayan H. Pathirage, Stephan M. Unter, Simon Corbill\'e, Elisa H. Barney Smith. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News