Hi,
I know tesseract4.0 used LTSM network to train a classification task.
Therefore, vector numbers in the last layer is equal to class numbers, e.g.
we have 100 characters to recognize, then the vector number is 100.
My question is when we add few characters for finetuning, lets say 3
charac
images are rescaled so that the text has always the same height,
> about 35/40px, with not border or a small (1/2px) border. Try with an
> evaluation set and see what works best for you.
>
>
> Bye
>
> Lorenzo
>
> Il giorno mer 3 apr 2019 alle ore 11:08 Du Kotomi
> ha scrit
; should be similar to what you will be using for OCR. It might be best to
> test with a small set of images and see what works best for you.
>
> On Wed, Apr 3, 2019 at 2:38 PM Du Kotomi wrote:
>
>> If we use text2image tool, there is no such problem.
>>
>> What about t
STM training we are using synthetic images created by
> text2image program using training text and fonts using tesstrain.sh or
> tesstrain.py. Hence there is no question of binarization or dpi as the
> program creates images as expected by tesseract training process.
>
> On Wed, Apr 3, 2
Anybody here?
On Wed, Apr 3, 2019 at 09:57 wrote:
> Sorry for disturb again. I have sent my issue befire, but no one gives the
> answer. I really need your help.
>
>
> I go through the source code and find tesseract do Otsu Thresholding and
> put the binary pix in the Thresholder object.
> But
can you help me answer the question. confuse whether Otsu Thresholding
affects lstm training
This topic has been submitted,but no one answers
On Tue, Apr 2, 2019 at 23:29 Shree Devi Kumar wrote:
> Tesseract is a standalone app and can be run locally.
>
> On Tue, Apr 2, 2019 at 7:26 PM Dave Wal
6 matches
Mail list logo
