>
> Thanks @Lorenzo for making it clear that tesseract is not a server but a
>> library and for the link. I still want to know how to start calling
>> tesseract. In know this is not a place to ask about gitpot.io but do I need
>> to set the environment variable because in gitpot.io is a
I'm on ubuntu 18.04 and Tesseract 4 now, and can confirm the *-c
textonly_pdf=1* hack works.
--
You received this message because you are subscribed to the Google Groups
"tesseract-ocr" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to
Ok thanks for the share very nice interface
As Alex highlights tesseract allows further customization
I myself want to learn how to train tesseract for Tamil and Sanskrit using your
scripts and guides but haven’t got a good starting point yet
Sent from my iPhone
> On Sep 15, 2019, at 12:55 PM,
Don't know the details.
On Sun, Sep 15, 2019, 21:36 Ravi Annaswamy wrote:
> That is a beautiful app.
>
> Shree Devi Kumar, what service does the 'google' selection hit? Is it free?
>
> Ravi
>
>
> On Sun, Sep 15, 2019 at 11:34 AM Shree Devi Kumar
> wrote:
>
>> Try
Yeah, looks great, but still there are some mistakes by Google...
I'm not sure, as long as I heard, Tesseract could be trained, but I never
heard about that Google service, so not sure, is it possible to reduce such
problems via some more trainings?
I mean, does the Google service is trainable
I split the pages to left right pages and posted on the ocr with google
option and here are the results, I have not compared yet but couple of
observations,
1. yes google ocr captures diacritics!
2. tesseract retains line breaks but google ocr provides flowing text,
which is great
3. Tesseract is
That is a beautiful app.
Shree Devi Kumar, what service does the 'google' selection hit? Is it free?
Ravi
On Sun, Sep 15, 2019 at 11:34 AM Shree Devi Kumar
wrote:
> Try http://ocr.sanskritdictionary.com/
> For OCR of Devanagari + Diacritics + English
>
> It's Google option gives better
Alex
Here are the results and linked below is an example notebook for you to get
started with.
Code is self explanatory, and can be adapted by you. You will need to
improve on many things,
but here is a start. Please let me know if you have any questions.
Try http://ocr.sanskritdictionary.com/
For OCR of Devanagari + Diacritics + English
It's Google option gives better result than tesseract
On Sun, Sep 15, 2019, 19:43 Alexander Gribanov
wrote:
> Hello!
>
> Finally got real project for OCR.
> Could anybody please give some advice in the process
I recently was able to write a notebook to read a page of single column
Sanskrit and English and run through tesseract to OCR both languages
I will take a look at your file and create a colab notebook sometime today or
tomorrow
Sent from my iPhone
> On Sep 15, 2019, at 10:13 AM, Alexander
Hello!
Finally got real project for OCR.
Could anybody please give some advice in the process step by step, how do I
make OCR for such pages?
https://drive.google.com/file/d/1Wdm4_tZHWHeVFlF7ND83xtvL29OCdTY_/view?usp=sharing
Do I need to split pages manually before the OCR to different type of
11 matches
Mail list logo
