Oh noooo... This will completely ruin accuracy. Not talking about speed...


On Tue, Mar 29, 2011 at 8:17 PM, Max Cantor <[email protected]> wrote:
> I might be completely wrong, but, you might be able to upscale the image if 
> you first skeletonize each glyph and reconstruct the a glyph from the 
> vectorized skeleton.
>
> I'm only putting this out as a possibility, I have no idea how to do this and 
> i imagine it would be very slow.
>
> On Mar 30, 2011, at 0:09, Dmitri Silaev <[email protected]> wrote:
>
>> I said all this assuming you're trying to improve the accuracy. If so,
>> it's even enough to just upscale your original image by like 3 or 4
>> times. E.g. check the results for the file I've attached. But a better
>> thing to do is get your source images already in a higher res.
>>
>> Warm regards,
>> Dmitri Silaev
>>
>>
>>
>>
>>
>> On Tue, Mar 29, 2011 at 8:06 PM, Robert P. J. Day <[email protected]> 
>> wrote:
>>> On Tue, 29 Mar 2011, Dmitri Silaev wrote:
>>>
>>>> Imho you're going in the wrong direction. Thresholding won't help.
>>>> I've thresholded the image manually with Photoshop and Tesseract's
>>>> result was the same as I for the original image.
>>>>
>>>> You need to get the image in a higher res, yours is 72 DPI only,
>>>> that's not enough for Tesseract. In plain English it means you need
>>>> more pixels per letter.
>>>
>>>  ok, that's reasonable, i'll just be more restrictive about which
>>> tiff files i accept for further processing.  thanks.
>>>
>>> rday
>>>
>>> --
>>>
>>> ========================================================================
>>> Robert P. J. Day                               Waterloo, Ontario, CANADA
>>>                        http://crashcourse.ca
>>>
>>> Twitter:                                       http://twitter.com/rpjday
>>> LinkedIn:                               http://ca.linkedin.com/in/rpjday
>>> ========================================================================
>>>
>>
>> --
>> 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.
>>
>> <phototest3.tif>
>
> --
> 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 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.

Reply via email to