As the first mandatory step you need to do perspective correction, e.g.
using paper sheet boundaries (is it a lottery ticket?)

Then depending on how it goes further with Tesseract you may need either to:
- Train for this particular font
- Blur a bit to make characters more "fleshy"
- Scale down vertically by a factor of 1.5 to match closer to standard
trained fonts

Each step in turn is a multi-step process. PM me if you're interested.

Best regards,
Dmitri Silaev
www.CustomOCR.com





On Mon, Jun 29, 2015 at 10:21 PM, Cenk KIZILDAĞ <[email protected]>
wrote:

> Hi,
>
> I would like to recognize only digits with the code sample below:
>
> try
>             {
>
>
>              System.Drawing.Bitmap imagee=new Bitmap(pictureBox1.Image);
>              System.Drawing.Bitmap
> imagee2=AForge.Imaging.Image.Clone(imagee,System.Drawing.Imaging.PixelFormat.Format24bppRgb);
>              //GET IMAGE FROM FILE
>
>              //CONVERT IMAGE TO TEXT
>              tessnet2.Tesseract ocr = new tessnet2.Tesseract();
>              ocr.SetVariable("tessedit_char_whitelist", "0123456789");
>              ocr.Init(@"C:\Users\197199\Documents\Visual Studio
> 2013\Projects\OCR\OCR\bin\Debug\tessdata", "eng", true);
>
>               List<tessnet2.Word> res=ocr.DoOCR(imagee2,Rectangle.Empty);
>
>              foreach(tessnet2.Word word in res)
>              {
>              textBox1.Text=textBox1.Text+word.Text+Environment.NewLine;
>              }
>              //CONVERT IMAGE TO TEXT
>             }
>             catch( Exception ex)
>             {
>                 textBox1.Text = ex.Message;
>             }
>
> Here is the image that I would like to recognize:
>
>
> <https://lh3.googleusercontent.com/-2s9jnjIoWjA/VZGaIGBoF9I/AAAAAAAAC6s/1tz4TUuq6WY/s1600/Ekran%2BAl%25C4%25B1nt%25C4%25B1s%25C4%25B12.JPG>
>
> And the outcome is:
>
> *88*
> *12*
> *18*
> *28*
> *41*
> *48*
>
> How can I fix this? Any help please.
>
> Thanks in advance & Best Regards.
>
>  --
> 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].
> To post to this group, send email to [email protected].
> Visit this group at http://groups.google.com/group/tesseract-ocr.
> To view this discussion on the web visit
> https://groups.google.com/d/msgid/tesseract-ocr/2e7c2183-63e9-49da-ac7e-c1079273199e%40googlegroups.com
> <https://groups.google.com/d/msgid/tesseract-ocr/2e7c2183-63e9-49da-ac7e-c1079273199e%40googlegroups.com?utm_medium=email&utm_source=footer>
> .
> For more options, visit https://groups.google.com/d/optout.
>

-- 
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].
To post to this group, send email to [email protected].
Visit this group at http://groups.google.com/group/tesseract-ocr.
To view this discussion on the web visit 
https://groups.google.com/d/msgid/tesseract-ocr/CAKzLxFNcnVQVyXX9xYF_w1Cq-zOARLLgvL3Qcs0_3uQhbOBzUQ%40mail.gmail.com.
For more options, visit https://groups.google.com/d/optout.

Reply via email to