I think you can try some things like:
1 - Set Segmentation Mode to PSM_SINGLE_LINE. I don't know the wrapper but
maybe a rectangle is got before apply OCR process.
2 - Get the image for you interest area and save it to verify if the
coordinates are correct or if the isolated area are skewed for example. In
that case you can get get the are save it and execute tesseract -psm 7 go
see the results.
On Wednesday, August 2, 2017 at 11:47:32 AM UTC-3, ilochray wrote:
> I am using Tesseract 3.0.4 with the Tesseract-OCR .Net wrapper. I am
> reading a page which contains account numbers and payment amounts along
> with other data.
> If I read the entire page using ...
> var Page2 = Engine.Process(PixPage, PageSegMode.Auto)
> , the account numbers and payment amounts are 100% accurate.
> If I select and read the zones on the page where they appear by using ...
> var Page = Engine.Process(PixPage, Region, PageSegMode.Auto)
> the accuracy drops to about 85%.
> Is there a way round this?
You received this message because you are subscribed to the Google Groups
To unsubscribe from this group and stop receiving emails from it, send an email
To post to this group, send email to firstname.lastname@example.org.
Visit this group at https://groups.google.com/group/tesseract-ocr.
To view this discussion on the web visit
For more options, visit https://groups.google.com/d/optout.