Please provide a sample tiff, single page will do, for testing.
On 25-Apr-2018 2:00 AM, "Cameron McSweeney" wrote:
Yes, and the box files 4.0 made still had the same problem. The accuracy
with 4.0 was much better but it still needs some tweaking, so I figured I
would be
Yes, and the box files 4.0 made still had the same problem. The accuracy
with 4.0 was much better but it still needs some tweaking, so I figured I
would be better off fixing the problem in 3.05
>
--
You received this message because you are subscribed to the Google Groups
"tesseract-ocr"
Have you tried the latest version, tesseract 4.0.0beta?
On Wed 25 Apr, 2018, 12:03 AM Cameron McSweeney,
wrote:
> Tesseract seems to be much too willing to find vertical lines. For
> example, Ds will be divided so that the straight, left portion is separate
> from the
Tesseract seems to be much too willing to find vertical lines. For example,
Ds will be divided so that the straight, left portion is separate from the
right, curved portion. The font is fixed, so stuff like that shouldn't
happen
--
You received this message because you are subscribed to the
Tesseract seems to be much too willing to find vertical lines. For example,
Ds will be divided so that the straight, left portion is separate from the
right, curved portion. The font is fixed, so stuff like that shouldn't
happen
On Tuesday, April 24, 2018 at 11:29:21 AM UTC-4, Cameron
Hi. I compiled an rpm package with tesseract-ocr for CentOS, Fedora,
ScientificLinux, OpenSuse. It must be checked...
https://build.opensuse.org/project/show/home:Alexander_Pozdnyakov
понедельник, 23 апреля 2018 г., 21:22:40 UTC+3 пользователь Eugene Huang
написал:
>
> Hello! Most people are
I have never used equ.traineddata. From feedback in the forum I don't think
it works very well. Maybe equ has not been trained via LSTM training, I
have no way of knowing. Only Ray Smith or other developers from Google can
answer that.
Only LSTM models exist in tessdata_best and tessdata_fast.
@Shree
Thanks for the tip. Just 2 quick questions.
1) From https://github.com/tesseract-ocr/tesseract/wiki/Data-Files, it says
that "osd" and "equ" traineddata files are compatible between Tesseract 3
and 4. In the GitHub tessdata_fast repo
(https://github.com/tesseract-ocr/tessdata_fast),
@Shree
Thanks for the tip. Just 2 quick questions.
1) From https://github.com/tesseract-ocr/tesseract/wiki/Data-Files, it says
that "osd" and "equ" traineddata files are compatible between Tesseract 3
and 4. In the GitHub tessdata_fast repo
(https://github.com/tesseract-ocr/tessdata_fast),
I am working on character recognition at work so I can copy information
from tables in giant TIFF files and write a program that can automatically
use the information from those tables. The tables are computer-generated,
but the information is unavailable to me in any format besides TIFF. The
10 matches
Mail list logo