Closed GoogleCodeExporter closed 9 years ago
This is not correct issue report:
1. we do not provide support for custom training.
2. if you use 3rd party tools - you should contact its authors.
3. It is not clear how your box file is related to your issue (No space in
output text for Hindi language)
Original comment by zde...@gmail.com
on 2 Mar 2014 at 2:47
I'd tried to run tesseract on some images through cmd earlier but it kept
showing the error 'Invalid TIFF directory; tags aren't sorted in ascending
order.' and 'unknown field with tag 20624 encountered.'
And for the image for which the output has been obtained there was no space in
it.
Original comment by sheekhaj...@gmail.com
on 2 Mar 2014 at 4:57
Hi.
I'm encountering somewhat same problem for Urdu recognition.
Urdu language has a ligature. Ligature totally changes the word's shape. Plus
urdu has uneven space gaps.
In middle of text the spaces are ignored almost every time. According to my
assumption there must be a flag that could set values for minimum "space gap".
If i'm correct please let me know what is that flag if there is some other way
to get around this problem please state that also.
Thank you in advance.
Muhammad Ali Shahzad
Assistant Software Architect
HPC & Computer Vision.
Original comment by sh.muham...@gmail.com
on 6 Jun 2014 at 5:31
Original issue reported on code.google.com by
sheekhaj...@gmail.com
on 22 Feb 2014 at 9:22Attachments: