Philipp Zumstein

https://blogs.dropbox.com/tech/2017/04/creating-a-modern-ocr-pipeline-using-computer-vision-and-deep-learning/

https://blog.altoros.com/optical-character-recognition-using-one-shot-learning-rnn-and-tensorflow.html HT @cneud via Twitter

https://www.youtube.com/playlist?list=PLHgYXaZMqUrjPv7TjFoI1iLG_dYsZznTT

Cont'd Attention OCR

2

Mentioned in https://github.com/kba/awesome-ocr/pull/13, cont'd here: > The [synth 90k text recognition dataset](http://www.robots.ox.ac.uk/%7Evgg/data/text/) is probably a useful addition to the list. > Also of interest: https://github.com/edward-zhu/umaru

Online Jupyter Notebook running Anystyle

1

I just tried and could set up a jupyter notebook including anystyle which can be launched online by the following link: [](https://mybinder.org/v2/gist/zuphilip/a035db2329db7b1eb6c846c738c3e63f/master?filepath=sample.ipynb) Maybe this is interesting for someone else. It...

Feature Request: Detect empty items in a list

2

I would expect that the `empty-values` rule would also warn me about any empty point in a list, i.e. something like this ```yaml key: - value1 - - value3 ```...

Is XPDF an alternative of poppler tools?

3

See also https://github.com/zotero/cross-xpdf

Currently, when clicking on a XPI file in Firefox, it first tries to install this as a Firefox plugin. Thus, one usually need to right click on the file and...

Determine available languages and provide a choice for them

4

Currently, we use a fixed language as `deu` or `eng` for OCR with Tesseract. But in a lot of cases it is even better to choose `script/Latin`, or for old...