Exploring few-shot text line segmentation approaches in challenging ancient manuscripts

Text line segmentation is a critical component of document layout analysis, particularly for ancient handwritten manuscripts. Its primary goal is to accurately extract individual text lines, a step that significantly influences subsequent tasks such as optical character recognition, text transcription, and information extraction. However, segmenting text lines in historical manuscripts is particularly challenging due to irregular handwriting, faded ink, and complex layouts with overlapping lines and non-linear text flows. Additionally, the limited availability of large annotated datasets makes fully supervised learning approaches impractical for these documents. In this paper, we explore the applicability of three prominent semantic segmentation models when applied in a few-shot learning setting, using only a small number of labeled examples per manuscript. Our results demonstrate the challenges of addressing text line segmentation in the context of scarce labeled data. This provides a promising avenue for future research in document analysis for historical manuscripts.