In case that file doesn't work with tesseract4, you can try
MICR.traineddata from
https://github.com/Shreeshrii/tessdata_MICR/tree/master/MICR-legacy
I was able to OCR the three images posted earlier in this thread:
⑈000144⑈ 400756051⑆ 23⑈ 11
⑈069565⑈ 364013051⑆ 79⑈ 11
⑈420360⑈ 36400
Hi I found a trained MCIR font for tesseract in this google group. Hope
this helps!
https://groups.google.com/forum/#!searchin/tesseract-ocr/micr/tesseract-ocr/obWI4cz8rXg/_Yl8RuCeJAkJ
On Friday, May 10, 2019 at 1:58:09 AM UTC-7, Pkumar .. wrote:
>
> thanks foe reply but i cant find trainneddat
Other option how to OCR check is described here:
https://www.pyimagesearch.com/2017/07/24/bank-check-ocr-with-opencv-and-python-part-i/
https://www.pyimagesearch.com/2017/07/31/bank-check-ocr-opencv-python-part-ii/
Zdenko
pi 10. 5. 2019 o 11:14 Zdenko Podobny napísal(a):
> You can train it by
You can train it by yourself.
There is aslo one PR https://github.com/tesseract-ocr/tessdata/pull/121 but
result is not perfect.
Zdenko
pi 10. 5. 2019 o 10:58 Pkumar .. napísal(a):
> thanks foe reply but i cant find trainneddata for MICR font.
>
> can you help me where i found that and how i
thanks foe reply but i cant find trainneddata for MICR font.
can you help me where i found that and how i modify my code for it
On Wednesday, 8 May 2019 17:36:31 UTC+5:30, zdenop wrote:
>
> What is reason for showing as you code? You are running tesseract from
> shell, so...
>
> If you have pr
What is reason for showing as you code? You are running tesseract from
shell, so...
If you have problem with tesseract output (I guess) - you will need
trainneddata for MICR font.
Zdenko
Dňa streda, 8. mája 2019 8:02:56 UTC+2 Pkumar .. napísal(-a):
>
> I have a problem with the current tessera
6 matches
Mail list logo
