Robert Sachunsky

It's a [bug in OpenCV](https://github.com/opencv/opencv/issues/21366), which has been fixed upstream, but no release yet.

Can you please try again with the most recent version of #87?

> Finally went through; took hours. > > Since this only occurs in combination with pc-segmentation and pc-segmentation seems currently the weakest segmentation method, I'll close this case. I would...

> > Finally went through; took hours. > > Since this only occurs in combination with pc-segmentation and pc-segmentation seems currently the weakest segmentation method, I'll close this case. >...

Could you please revisit with the current master version @jbarth-ubhd ?

One obstacle on that road is sufficient ground truth data for testing, though. Does anyone know of a suitable dataset (with differently oriented regions or pages, and/or with skewed regions...

Thanks @stefanCCS for the report. I cannot say much without more context – either in form of debug level log output (e.g. by running with `-l DEBUG`) or with the...

Thanks! I am able to reproduce this now. Unfortunately, it's not strictly a bug, but just inefficient programming. Clipping necessarily has to compare N by N regions somehow. And when...

This repo is _not_ about Tesseract, and not just an API. There are plenty of usage examples in the README, including links to the general documentation of the OCR-D framework....

@NavpreetDevpuri What do you mean by _simple way_? This repo contains an OCR post-correction tool along with a much improved version of [Ocropy 1](https://github.com/tmbarchive/ocropy) and ocrolib, but only for [OCR-D](https://ocr-d.de)...