Sample from the UK Observatories Year Book

The Observatories Year Book, available as digital images from the National Met Library and Archive, is a high priority candidate for an automatic transcription system as it is printed tables of data, with high-quality images available.

Observatories Year Book sample image, alongside the word blocks produced by Textract. Red and blue chequerboard patterns show tables Textract has found on the page.

• Script to run Textract
• Textract output (as JSON)
• Script to plot comparison figure
• A closer look at the block layout
• A closer look at the tables detected