Hello,
I'm trying to apply White- and Blacklists to my OCR-result. If I call:
SetVariable("tessedit_char_whitelist", "0123456789")
Then all characters in the result are converted to numbers between 0
and 9. Is that the correct behaviour
of this option? After my understanding of a whitelist, only t
Yes, Tesseract black lists and whitelists are useful almost
exclusively in situations where you really don't have the blacklisted
characters anywhere in the image (otherwise Tesseract will return the
next best guess, no matter how poor) or vice-versa where you have only
the whitelisted characters i
Yes a filtering by regular expressions sounds good, though I had
hoped tesseract could do this on its own. I might try a set of
trainedata
limited to numbers as well, in addition to white and black lists.
Maybe that works, I will post my results when finished.
thanks for your reply!
8flm6
On 1 J
Hi
I think the result is perfectly correct.
To get just the numbers, surely you must use whitelist instead of the
blacklist, and then go through your output and replace all non-numerics with
a space!
I expect you will need some punctuation too +- ,.: etc If these occur in the
text part then they ne
Actually, it doesn't serve regexp - the while list as an enumeration is
supported only.
On Friday, July 1, 2011 at 9:59:26 PM UTC+2, 8flm6 wrote:
>
> Yes a filtering by regular expressions sounds good, though I had
> hoped tesseract could do this on its own. I might try a set of
> trainedata
>
5 matches
Mail list logo
