# Unfolding the Past: A Comprehensive Deep Learning Approach to Analyzing Incunabula Pages

arXiv: https://arxiv.org/abs/2506.18069 · HTML: https://mlsanity.com/paper/2506.18069/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 25 references that are in the map.
- First posted on arXiv 22 Jun 2025.

## Builds on (most cited first, 5 of 5)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis](https://mlsanity.com/paper/2206.01062/) (2022)
- [Case Study of a highly automated Layout Analysis and OCR of an incunabulum: 'Der Heiligen Leben' (1488)](https://mlsanity.com/paper/1701.07395/) (2017)
- [Knowledge Graphs for Digitized Manuscripts in Jagiellonian Digital Library Application](https://mlsanity.com/paper/2506.03180/) (2025)

## Built on by (most cited first, 1 of 1)

- [Studying Illustrations in Manuscripts: An Efficient Deep-Learning Approach](https://mlsanity.com/paper/2601.05269/) (2025)

## Abstract (arXiv)

We developed a proof-of-concept method for the automatic analysis of the structure and content of incunabula pages. A custom dataset comprising 500 annotated pages from five different incunabula was created using resources from the Jagiellonian Digital Library. Each page was manually labeled with five predefined classes: Text, Title, Picture, Table, and Handwriting. Additionally, the publicly available DocLayNet dataset was utilized as supplementary training data. To perform object detection, YOLO11n and YOLO11s models were employed and trained using two strategies: a combined dataset (DocLayNet and the custom dataset) and the custom dataset alone. The highest performance (F1 = 0.94) was achieved by the YOLO11n model trained exclusively on the custom data. Optical character recognition was then conducted on regions classified as Text, using both Tesseract and Kraken OCR, with Tesseract demonstrating superior results. Subsequently, image classification was applied to the Picture class using a ResNet18 model, achieving an accuracy of 98.7% across five subclasses: Decorative_letter, Illustration, Other, Stamp, and Wrong_detection. Furthermore, the CLIP model was utilized to generate semantic descriptions of illustrations. The results confirm the potential of machine learning in the analysis of early printed books, while emphasizing the need for further advancements in OCR performance and visual content interpretation.