You could have better results with 300-DPI, binary or grayscale images.
On Sunday, August 4, 2013 7:04:20 PM UTC-5, Zeulopes wrote:
>
> Hello Guys!
>
> I'm using tesseract API (version 3.02) to single character recognition in
> English (eng.traineddata), with the following parameters:
>
> api->SetPageSegMode(tesseract::PSM_SINGLE_CHAR);
> and
> api->SetVariable("tessedit_char_whitelist", "0123456789,");
>
> When I pass an image containing a single digit (see image "three.png") it
> works very well, but it produces nothing (no results) when I pass an image
> of "comma" character (see image comma.png) even though included the "," on
> tessedit_char_whitelist variable.
> I tried with different sizes and resolutions with no success.
>
> Do you guys have any idea what's I'm doing wrong or even missing? Is there
> any way to "set up" tesseract to recognize the "comma"?
>
> Best regards!
>
> attached images are:
>
>
>
> <https://lh3.googleusercontent.com/-5xpT4ip8W4w/Uf7nm7cB6fI/AAAAAAAAADY/pyakXc7yvwY/s1600/three.png><https://lh6.googleusercontent.com/-iI_xcoRRdjA/Uf7nd3g8O-I/AAAAAAAAADQ/3EnoUU0NdLc/s1600/comma.png>
>
--
--
You received this message because you are subscribed to the Google
Groups "tesseract-ocr" group.
To post to this group, send email to [email protected]
To unsubscribe from this group, send email to
[email protected]
For more options, visit this group at
http://groups.google.com/group/tesseract-ocr?hl=en
---
You received this message because you are subscribed to the Google Groups
"tesseract-ocr" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to [email protected].
For more options, visit https://groups.google.com/groups/opt_out.
