NLS Advocates Library Index Card Detection Dataset

100 annotated scanned page images from the Advocates Library manuscript index card collection at the National Library of Scotland. The dataset provides bounding box annotations for training object detection models to locate index cards on pages.

Use Cases

• Train object detection models to locate index cards on scanned manuscript pages.
• Benchmark model performance on historical document layout analysis.
• Develop preprocessing pipelines for digitized library collections to isolate card content.

Strengths

• Contains 100 annotated images, providing a defined scale for model training.
• Annotations include bounding boxes, a standard format for object detection tasks.
• Source is specified as the National Library of Scotland's Advocates Library manuscript collection.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Dataset size and file formats are unspecified, complicating download planning.

Provenance

Source

National Library of Scotland, Advocates Library manuscript collection.

Collection Method

Scanned pages annotated with bounding boxes.

Freshness

Last updated 2026-03-25 14:43:07; freshness should be verified.

Geography

Scotland, United Kingdom.