Unfolding the Past: A Comprehensive Deep Learning Approach to Analyzing Incunabula Pages
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911020118704128 |
|---|---|
| author | Ropel, Klaudia Kutt, Krzysztof Miranda, Luiz do Valle Nalepa, Grzegorz J. |
| author_facet | Ropel, Klaudia Kutt, Krzysztof Miranda, Luiz do Valle Nalepa, Grzegorz J. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_18069 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Unfolding the Past: A Comprehensive Deep Learning Approach to Analyzing Incunabula Pages Ropel, Klaudia Kutt, Krzysztof Miranda, Luiz do Valle Nalepa, Grzegorz J. Digital Libraries Computer Vision and Pattern Recognition 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. |
| title | Unfolding the Past: A Comprehensive Deep Learning Approach to Analyzing Incunabula Pages |
| topic | Digital Libraries Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.18069 |