OCR files
PAGE line bounds to CSV
Export axis-aligned TextLine bounds and text from PAGE XML.
Your inputs
Start with an exampleYour result
Example resultAa — A small example of your colors.
How it works
Take each polygon’s minimum/maximum x and y in image pixels. Export page, image, line ID, bounds, original points and one TextEquiv text value.
The sample polygon spans x=10–110 and y=20–50, giving width 100 and height 30.
Limits
Up to 10000 lines and 10000 points per polygon. This does not repair polygons, certify PAGE schemas, rasterize masks or infer reading order. TextEquiv index 0 is preferred; otherwise the first is retained.