Not sure if this was right or now but given the before errors were
"warnings" I continued onward and got these errors with Scrollview.jar -
[Wed Sep
26-19:17:29][MEPMBP2017][()markphillips](~/Documents/Development/Tesseract/tesseract/java)
I guess the build failed from before...
[Wed Sep
26-19:27:21][MEPMBP2017][()markphillips](~/Documents/Development/Tesseract/tesseract)
=>>text2image --list_available_fonts --fonts_dir=/Library/Fonts
dyld: Library not loaded: /usr/local/opt/icu4c/lib/libicui18n.62.dylib
Referenced from:
Just goole for help. There are plenty examples. e.g.
https://stackoverflow.com/questions/24570916/add-external-libraries-to-cmakelist-txt-c
Zdenko
st 26. 9. 2018 o 14:38 Adam Richards napísal(a):
> Hi Zdenko,
>
> Sorry, I'm just still unsure how exactly to get this working? What should
> I be
Hi Zdenko,
Sorry, I'm just still unsure how exactly to get this working? What should I
be doing to set my Tesseract_INCLUDE_DIRS and Tesseract_LIBRARIES
manually...
Any further help you could provide would be appreciated,
thanks,
Adam
On Monday, September 24, 2018 at 4:46:05 PM UTC+10,
I assume you mean the charlesw/tesseract wrapper on Github. Questions are
more directly answered there. What steps did you perform and what is the
symptom?
--
You received this message because you are subscribed to the Google Groups
"tesseract-ocr" group.
To unsubscribe from this group and
No, I always train from scratch.
best fast.traindata doesn't recognize eng and persian and the accuracy is
too low in some fonts.
I want to solve this problem.
For fine tune can have different unicharset. As I read in wiki of
tesseract, it is the number of class of lstm. So if Mr. Smit has trained
>By version alpha, I trained about 1000 line and it is not so bad
You must have only done fine tuning of model then and now you are trying to
train from scratch.
On Wed, 26 Sep 2018, 04:01 Khosrobeigy.zohreh,
wrote:
> I know, actually I am master in lstm. I want to resolve all error and then
>
I know, actually I am master in lstm. I want to resolve all error and then
train big text.
By version alpha, I trained about 1000 line and it is not so bad. But in
version beta 4 I got many error.
In alpha,
# Use LSTM
tessedit_ocr_engine_mode 1
tessedit_pageseg_mode 6
# Arabic page layout
Hi Vipin
I didn't get much further with that wrapper I'm afraid. In the end, I went
for building tesseract from the C++ source code.
On Tuesday, September 25, 2018 at 6:03:19 PM UTC+1, Vipin Tom Varghese
wrote:
>
> Hi James, my apologies to hit you up so randomly, but I had no ther
> options
9 matches
Mail list logo
