BullingerDB: A Dataset for Handwritten Text Recognition and Writer Retrieval
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916061828349952 |
|---|---|
| author | Peer, Marco Bertrand, Anna-Scius Scheurer, Patricia Fischer, Andreas |
| author_facet | Peer, Marco Bertrand, Anna-Scius Scheurer, Patricia Fischer, Andreas |
| contents | We present BullingerDB, a large-scale benchmark dataset for historical document analysis based on the correspondence of Heinrich Bullinger (1504-1575). The corpus comprises 20,898 pages and 499,222 text lines written by 796 writers over six decades, featuring stylistic variation, multilingual content (mostly Latin and Early New High German) as well as meta-information such as writer identity and time. We evaluate BullingerDB on text recognition and writer retrieval. TrOCR, the best performing model, achieves a CER of 9.1%. For writer retrieval, we introduce a temporal nDCG metric to assess time-aware retrieval. While temporally coherent retrieval is achievable, mAP (78.3%) scores indicate challenges due to long-term stylistic variation. With BullingerDB, we aim to establish a new benchmark for multilingual historical text recognition and temporally-aware writer analysis. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_30235 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | BullingerDB: A Dataset for Handwritten Text Recognition and Writer Retrieval Peer, Marco Bertrand, Anna-Scius Scheurer, Patricia Fischer, Andreas Computer Vision and Pattern Recognition We present BullingerDB, a large-scale benchmark dataset for historical document analysis based on the correspondence of Heinrich Bullinger (1504-1575). The corpus comprises 20,898 pages and 499,222 text lines written by 796 writers over six decades, featuring stylistic variation, multilingual content (mostly Latin and Early New High German) as well as meta-information such as writer identity and time. We evaluate BullingerDB on text recognition and writer retrieval. TrOCR, the best performing model, achieves a CER of 9.1%. For writer retrieval, we introduce a temporal nDCG metric to assess time-aware retrieval. While temporally coherent retrieval is achievable, mAP (78.3%) scores indicate challenges due to long-term stylistic variation. With BullingerDB, we aim to establish a new benchmark for multilingual historical text recognition and temporally-aware writer analysis. |
| title | BullingerDB: A Dataset for Handwritten Text Recognition and Writer Retrieval |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.30235 |