On 21 July 2010 09:50, rthomas wrote:
>
>
> On Jul 21, 10:23 am, rthomas wrote:
>> > Nobody has mentioned any plans to write a .net wrapper for Tesseract
>> > 3, and the developer of tessnet2 has mentioned that he would rather
>> > pay for someone to reimplement Tesseract than touch it again, so
On 21 July 2010 09:23, rthomas wrote:
>>
>> Nobody has mentioned any plans to write a .net wrapper for Tesseract
>> 3, and the developer of tessnet2 has mentioned that he would rather
>> pay for someone to reimplement Tesseract than touch it again, so I
>> wouldn't hold my breath, if I were you.
>
On Jul 21, 10:23 am, rthomas wrote:
> > Nobody has mentioned any plans to write a .net wrapper for Tesseract
> > 3, and the developer of tessnet2 has mentioned that he would rather
> > pay for someone to reimplement Tesseract than touch it again, so I
> > wouldn't hold my breath, if I were you.
>
> Nobody has mentioned any plans to write a .net wrapper for Tesseract
> 3, and the developer of tessnet2 has mentioned that he would rather
> pay for someone to reimplement Tesseract than touch it again, so I
> wouldn't hold my breath, if I were you.
>
Yes, but the main reason is because I had
As I said, we just need Jimmy to find 4-5 hours of his free time to
knock this one out :-)!
On Jul 20, 11:01 am, Taxman wrote:
> "This bad problem is just about fixing Tesseract to accept the reality
> that not all text have the same height for all letters because not
> everything is a book."
>
>
"This bad problem is just about fixing Tesseract to accept the reality
that not all text have the same height for all letters because not
everything is a book."
Only some books have uniform text sizes. Textbooks have a large degree
of variability in text size within the same page and probably caus
On 20 July 2010 02:52, Austin Henderson wrote:
> As a developer I am cautious to estimate the amount of time a code change
> will take.
:D I like you a lot right now.
> I am thrilled to have the code and look forward to enhancements
> as they are ported to .net environments.
Nobody has mentione
As a developer I am cautious to estimate the amount of time a code change
will take. I am thrilled to have the code and look forward to enhancements
as they are ported to .net environments. For now I am cleaning up the image
in pre processing steps to remove blobs that are inconsistent with others
On 19 July 2010 19:01, patrickq wrote:
> Wrong ... option 2 won't really work unless you want to cut-out
> individual words. This image where everything in on one line still
> fails with the same insane forcing of the letters in "John" to be
> interpreted as tall letters:
> http://www.scanbizcards
-
> From: Jimmy O'Regan
> Sent: Monday, July 19, 2010 9:56 AM
> To: tesseract-ocr@googlegroups.com
> Subject: Re: Tesseract Reading Issue
>
> On 19 July 2010 15:34, Austin Henderson wrote:
> > Thank you for your feedback.
> > I am working with some automated im
o be higher).
I am not really sure I understand the significance of the values passed
for
this option though.
Thanks
Austin
-Original Message- From: patrickq
Sent: Monday, July 19, 2010 9:00 AM
To: tesseract-ocr
Subject: Re: Tesseract Reading Issue
Setting the segmentation mode to P
ds to be lower), or if
you get spaces between letters (needs to be higher).
> I am not really sure I understand the significance of the values passed for
> this option though.
>
> Thanks
> Austin
>
>
> -Original Message- From: patrickq
> Sent: Monday, July 19,
as different objects?
> Do you think tosp_table_xht_sp_ratio could have any impact on this if I
> tweak it?
> I am not really sure I understand the significance of the values passed for
> this option though.
>
> Thanks
> Austin
>
> -Original Message-
>
nks
Austin
-Original Message-
From: patrickq
Sent: Monday, July 19, 2010 9:00 AM
To: tesseract-ocr
Subject: Re: Tesseract Reading Issue
Setting the segmentation mode to PSM_SINGLE_LINE doesn't help (I
checked).
Here is an even more striking example: "John Doe" and
Setting the segmentation mode to PSM_SINGLE_LINE doesn't help (I
checked).
Here is an even more striking example: "John Doe" and
"j...@widgets.com": http://www.scanbizcards.com/johndoe.jpg
Just because the email address uses a smaller font, Tesseract 3.0
stubbornly insists on interpreting all the
On 19 July 2010 13:30, Jimmy O'Regan wrote:
> On 19 July 2010 13:20, patrickq wrote:
>> This is a great example of a serious problem with Tesseract when
>> analyzing any image with fonts of variable sizes such as a street
>> sign, flyer, business card etc. What happens is that Tesseract's
>> adap
On 19 July 2010 13:20, patrickq wrote:
> This is a great example of a serious problem with Tesseract when
> analyzing any image with fonts of variable sizes such as a street
> sign, flyer, business card etc. What happens is that Tesseract's
> adaptive classifier makes assumptions about letter heig
This is a great example of a serious problem with Tesseract when
analyzing any image with fonts of variable sizes such as a street
sign, flyer, business card etc. What happens is that Tesseract's
adaptive classifier makes assumptions about letter heights and uses
that knowledge when recognizing the
I have two files
http://dl.dropbox.com/u/1531272/pg1-CROP.jpg
and
http://dl.dropbox.com/u/1531272/pg1-CROP-Lines.jpg
Note on the "Lines" file there are dark lines on the left and right
side of this image.
I am trying to understand why the tessnet dll would render such
different readings for t
19 matches
Mail list logo
