pyocr

pyocr copied to clipboard

Tests/Tesseract: Differences between Pyocr and reference output

5

For some reason there are differences between the references and the actual results. And it seem the actual results are good, so it's problably a bug in ```update_test_data.sh```

jflesch

Confidence score

6

Is it possible to get a confidence score for the predictions (not orientation) ?

MathieuCliche

[libtesseract] output of get_available_builders() is incomplete

2

I see the code of https://github.com/openpaperwork/pyocr/blob/master/src/pyocr/libtesseract/tesseract_raw.py#L381 https://github.com/openpaperwork/pyocr/blob/master/src/pyocr/libtesseract/__init__.py#L110 It's showed the libtesseract was supported the numeric mode，but why in `get_available_builders` not allow us use `DigitBuilder`？

wwqgtxx

preserve_interword_spaces in tesseract

1

Hi Team, Currently i am using pyocr with tesseract 3.05.01. I am using pyocr.get_available_tools() to get tesseract. Is there any way i can preserve_interword_spaces for tesseract with help of pyocr.

anilnaik1988

Expose load_system_dawg for non textual ouput

3

--load_system_dawg 0 would be helpful as an argument in image_to_text, perhaps as an options dictionary. Feel free to call it something that makes it language agnostic

awiebe

Libtesseract: need stress-testing

7

Someone has been reporting crashes of Paperwork when running the OCR. They are using Tesseract 3.04.01 .. so there may be something wrong with the libtesseract binding. (Note: currently, the...

jflesch

Cuneiform: Split text areas before OCR

1

Cuneiform tends to stop reading pages when it reachs a large non-readable area. Because of this, when using Cuneiform, all the keywords are not actually extracted. A way to work...

jflesch

Even when using the LineBoxBuilder, it seems too much data is stripped from the hOCR files.

jflesch