Hi Shree,
Thanks you replay, I will try it.
On Friday, July 6, 2018 at 10:34:10 PM UTC+8, shree wrote:
>
> You could try finetuning for the dotmatrix font.
>
> On Fri, Jul 6, 2018 at 3:43 PM Wenjie Chen > wrote:
>
>> Hi folks,
>>
>> Below is the dot-matrix digits picture, *tesseract *recognize i
> Problem resolved. Once I finally pointed to a valid eng.traineddata file,
> all was good.
>
Sorry for the false alarm. Case closed.
--
You received this message because you are subscribed to the Google Groups
"tesseract-ocr" group.
To unsubscribe from this group and stop receiving email
> I noticed that the --traindeddata path was erroneous. I corrected that to
> point to a good eng.traineddata file but the error is the same.
>
Segmentation Faul (core dumped)
--
You received this message because you are subscribed to the Google Groups
"tesseract-ocr" group.
To unsubscribe
I am trying to follow along the tessearct 4 training tutorial on github.
All is well until I try to run the lstmtraining.
I run this command on a tesseract 4.00 beta installation
lstmtraining --debug_interval 100 --traineddata
~/tesstutorial/engtrain/eng/eng.traineddata --net_spec '[1,36,0,
I am a newbie trying to get my head around tesseract. I discovered the
option to print all possible configuration file options. tesseract
--print-parameters
The first 14 parameters make reference to an editor.
editor_image_xpos 590 Editor image X Pos
editor_image_ypos 10 Editor image Y Pos
e
About the white border, maybe my suggestion was not so good.
I've seen that sometimes adding some generous white border during
recognition helps a lot (both with characters recognition and characters
splitting).
But I'm also seeing that training with a border and doing recognition with
a differen
6 matches
Mail list logo
