-
These are the orphan ideas transferred from ticket #67 and concerning ideas for what statistics we can compute and visualise:
- group by format family, display the number of occurrences of each forma…
bansp updated
5 months ago
-
please leave a short comment in this issue if you (plan to) have a JournalTouch installation. we might @-mention you if there are critical updates or new versions
-
This seems like a good source for the same:
https://www.pyimagesearch.com/2018/09/17/opencv-ocr-and-text-recognition-with-tesseract/
~~Also, the link provided by @aimanfatima (https://github.com/U…
-
UTF-8 allows different representations for the same character. Dinglehoppers currently does not detect that such different representations are identical characters, but handles them like a recognition…
-
A simple Testmail to one recipient works, but a longer mail to multiple recipient fails. Needs more investigation
```
Apr 08 13:02:41 xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx python/send_mail.py: send_…
-
I am using https://github.com/UB-Mannheim/ocr-fileformat which includes the prima-page-converter.
Given [this file](https://files.gitter.im/609272e76da03739847bdbf8/s5U8/10.1515_zfrs-1980-0101.xml)…
-
Nr. 35/1875: First page of Central-Handelsregister is missing.
-
Open Mensa still keeps sucking.
New data sources welcome [WIP]
-
> Commit https://github.com/OCR-D/format-converters/commit/5b9568fd2b6dbfe891ef81826b7fffea7d21d814 was missing in our installation (fixed now). I noticed that just running `make all` or `make install…
-
I tried use it in MKV, AVI, MP4, but the results is the same.
I am working in windows 10 over Python 3.11
and have installed the https://github.com/UB-Mannheim/tesseract/
![image](https://user-im…