Konstantin Baierer

We did what @rkhwaja suggested and published [our fork](https://github.com/OCR-D/pyexiftool) as a wheel to pypi as [`ocrd-pyexiftool`](https://pypi.org/project/ocrd-pyexiftool/), so we can use `pip install ocrd-pyexiftool` instead of installing from git.

Yeah, they do support postgres and redis, though not sure whether in the free tier. I have used it for Node.JS and PHP projects but not in the last year...

> unified and free What does "unified" mean? What engine runs in the backend? And how "free" is it?

What is Zonal text search/extraction?

No, sorry, I don't have that dataset myself. C.f. https://github.com/cneud/ocr-gt/issues/12 there are many interested in it, perhaps someone subscribed to this repo knows how to get it...

The list is @cneud's work and it's maintained at https://github.com/cneud/ocr-gt. We're working on a project making open-source OCR readily deployable in libraries, archives etc. (https://github.com/OCR-D / http://ocr-d.de). An important part...

https://github.com/jsvine/pdfplumber

I don't think being from 2011 makes it obsolete. There's some interesting talks in there, in fact I think I posted it as an issue sometime before, at least meant...

Related: Deriving LaTeX source code from rendered formulas: https://github.com/harvardnlp/im2markup (Demo: http://lstm.seas.harvard.edu/latex/) by @da03, @srush

Have not tried it but there is https://github.com/naptha/ocracy/blob/master/ocropy/pyrnn2clstm.py