Did you try the tutorial at all? It's a pretty good guidance though you
might need help here and there.
2019年6月9日日曜日 15時27分23秒 UTC+9 Mox Betex:
>
> Can someone explain me how to create training data for tesseract 4.0?
> I read tutorial on web but I really don't understand.
> Is there some GUI
Do you know what font this is? Maybe you can train it.
2019年6月10日月曜日 14時33分12秒 UTC+9 Bhamare Harshal:
>
> Hi,
>
> In attached images, we applied fastNlDenosingColored, grayscaling,
> gaussian blue, mean thresholding, erosion, then black to white (black font
> on white background),
> but output
turns out this is a ubuntu server display issue. After adding -Y in ssh
command when connecting to ubuntu server it works! In general this commands
enables X11 Display in ubuntu server. The link below is helpful:
The above error seems to be solved, now the problem I have is:
Starting sh -c "trap 'kill %1' 0 1 2 ; java -Xms1024m -Xmx2048m -jar
/home/ubuntu/leptonica-1.78.0/tesserac\
t/java/ScrollView.jar & wait"
Socket started on port 8461
Created window Convolve of size 1997, 580
Client connected
I was going through the training turotial below
https://github.com/tesseract-ocr/tesseract/wiki/TrainingTesseract-4.00
In part training from scratch, I copied the command in the link above and
ran:
mkdir -p ~/tesstutorial/engoutput
lstmtraining --debug_interval 100 \
--traineddata
Than you are alone with your problems...
Zdenko
po 10. 6. 2019 o 19:24 Beck Olson napísal(a):
> Unfortunately I cannot because the images I'm working with contain
> confidential information. I'm working with Medical Images that have text
> overlays. Its sparse text and we have not done any
Unfortunately I cannot because the images I'm working with contain
confidential information. I'm working with Medical Images that have text
overlays. Its sparse text and we have not done any training, basically the
default options in tesseract has done well enough in the past. I was hoping
there
Can you provide testing case for your problem?
Zdenko
po 10. 6. 2019 o 19:00 Beck Olson napísal(a):
> Greetings!
> I just upgrade a system that I was using to parse spraces text out of
> images from tesseract 4.0 to 4.1. I was surprised to find a significant
> loss in accuracy. One of the
Greetings!
I just upgrade a system that I was using to parse spraces text out of
images from tesseract 4.0 to 4.1. I was surprised to find a significant
loss in accuracy. One of the main issues is that it was no longer identify
spaces between words. Does anyone have any ideas as to what
How much time does it take to finish "make leptonica tesseract" command in
ocr-d?
I have waited for half an hour and it still didn't finish, then I stopped.
--
You received this message because you are subscribed to the Google Groups
"tesseract-ocr" group.
To unsubscribe from this group and
Hello
please help me
I have a problem with OCRD-train when I train the Arabic language (RTL), the
traineddata resulted in inverse words
please help me !!!
--
You received this message because you are subscribed to the Google Groups
"tesseract-ocr" group.
To unsubscribe
11 matches
Mail list logo
