The traineddata files can hold both types of models. The OCR Engine mode
chooses which ones get used.
https://github.com/tesseract-ocr/tesseract/wiki/Data-Files#format-of-traineddata-files
On Fri, Jul 13, 2018 at 9:31 AM 于洋 wrote:
> Tesseract 4 introduced new LSTM engine. The LSTM engine needs
Tesseract 4 introduced new LSTM engine. The LSTM engine needs LSTM trained
data, and the legacy engine needs old trained data. Two types of trained
data are incompatiable with each other.
When I set OCR Engine to 2, it will use Legacy and LSTM engines. But how
can i provide two types(LSTM and
Thank you for your feedback of eng+
I will try training for this and get back.
On Thu, Jul 12, 2018 at 2:18 PM yajva wrote:
> eng+iast-plus-3600 => no diacritics at all
> Latin+iast-plus-3600 => only macrons none other
>
>
>
> On Thursday, July 12, 2018 at 1:12:25 AM UTC+5:30, shree wrote:
>>
Try traineddata from tessdata_best and tessdata_fast
On Thu 12 Jul, 2018, 6:45 PM mahendrag gajera,
wrote:
> Hello all
>
> I am try to ocr japanese images via below code. But it give junk character.
> My tesseract version is 4.0
>
> Please let me know what is missing here.
>
> void Test(char*
I tried training tesseract in windows using jTessBoxEditor. It created
eng.traineddata but while creating it gave several errors like: so when i
tried using that trained file i am not getting newly improved result
i also tried similar way serak-tesseract-trainer-master i tried box
Hello all
I am try to ocr japanese images via below code. But it give junk character.
My tesseract version is 4.0
Please let me know what is missing here.
void Test(char* imagePath)
{
char *outText;
tesseract::TessBaseAPI *api = new tesseract::TessBaseAPI();
// Initialize tesseract-ocr with
Any ideas about this? I'm encountering this problem quite often, even with
custom training.
I tried to do some data augmentation during training varying the number of
pixels on the left but did not help.
Should I report it as an issue on github and discuss it there?
Thanks, bye
Lorenzo
eng+iast-plus-3600 => no diacritics at all
Latin+iast-plus-3600 => only macrons none other
On Thursday, July 12, 2018 at 1:12:25 AM UTC+5:30, shree wrote:
>
> What about ocr with
>
> eng+iast
>
>
>
> On Wed 11 Jul, 2018, 7:44 PM yajva, >
> wrote:
>
>> shree
>> namaste
>>
>> I am trying to OCR
8 matches
Mail list logo