Tesseract 4.x uses lines, not chars.
Bye
Lorenzo
Il giorno lun 12 nov 2018 alle ore 05:42 ha scritto:
> Dear All,
>
> Currently, tesseract training is based on the pair (tiff and box).
> It's not easy to make box file (char level) if we try to train some scanned
> document images not ge
That means we can label some existing images with text line boxes instead
of individual char boxes in current tesseract 4.0? I checked the box files
generated by the training process and found that char boxes were still
there.
Thanks,
Jun
在 2018年11月12日星期一 UTC+8下午5:26:48，Lorenzo Blz写道：
>
> Tes
Il giorno lun 12 nov 2018 alle ore 11:53 ha scritto:
> That means we can label some existing images with text line boxes instead
> of individual char boxes in current tesseract 4.0? I checked the box files
> generated by the training process and found that char boxes were still
> there.
>
Yes it
Hi,
I recently experienced that Tesseract 4 is not identifying images with text in
white and background colored
Is there any specific preprocessing?
Thanks,
Raghu
--
You received this message because you are subscribed to the Google Groups
"tesseract-ocr" group.
To unsubscribe from this grou
Can you please provide images for testing?
Zdenko
po 12. 11. 2018 o 12:38 raghunath rs napísal(a):
> Hi,
>
> I recently experienced that Tesseract 4 is not identifying images with
> text in white and background colored
>
> Is there any specific preprocessing?
>
> Thanks,
> Raghu
>
> --
> You r
What kind of error message you get?
Please share your image for testing too.
Zdenko
ne 11. 11. 2018 o 15:39 Martin Jenniges
napísal(a):
> Hello,
>
>
> I have found the follow Tip for tesseract; but when I give this parameter
> with -c *textord_min_linesize 3.25 in tesseract 4, I receive a err
Use Otsu Inverse from OpenCV.
https://www.meccanismocomplesso.org/en/opencv-python-otsu-binarization-thresholding/
On Mon, Nov 12, 2018 at 6:38 AM raghunath rs
wrote:
> Hi,
>
> I recently experienced that Tesseract 4 is not identifying images with
> text in white and background colored
>
> Is
It's clear now. Thanks for the information.
Jun
在 2018年11月12日星期一 UTC+8下午7:38:19，Lorenzo Blz写道：
> Il giorno lun 12 nov 2018 alle ore 11:53 >
> ha scritto:
>
>> That means we can label some existing images with text line boxes instead
>> of individual char boxes in current tesseract 4.0? I check
hi,zdenop
My origin output of chcp is "936"
As you said，I think it should be a problem with console coding.But i don't
know how to solve this coding problem.
In the end, I solved this problem in another way.I use software named
"fontcreator" to modify the name of the fonts and changed the name t
I've not used Tesseract in many years until today. I'm very impressed with
what I see now.
I need to process a PNG 300 DPI b/w image and have it create an Indexed PDF
file. I've run a command line to do this and was very happy with the
quality of the result but I would like to be able to feed
10 matches
Mail list logo
