*Current Behavior:*
I've followed the wiki and details given in the wiki/Training Tesseract - 
4.00. There were no errors in creation of the traineddata file. 

I wanted to create my own ara_custom.traineddata file specifically to read 
dates in arabic, so it has "٠١٢٣٤٥٦٧٨٩" (0-9 numeric characters in arabic) 
with a "/" forward slash only.

*The format for arabic date is:*
*٢٠١٩/٠٩/٢٥*
*yyyy/mm/dd*

*My ara.training_text file is: *attached as ara.training_text.txt (for 
uploading only else i use the file without txt extension)

*My ara.wordlist file is: * attached as ara.wordlist.txt (for uploading 
only else i use the file without txt extension)

*Text in image:* ٢٠٠٩/١١/١٢ *(32.jpg)*
*Tesseract reads:* ٢٤٠٩/١١/١٢ *(32.txt)*

*Text in image:* ١٩٧٩/٠١/٢٨ *(24.jpg)*
*Tesseract reads:* ١٦٩٧٦    //٠١//٧٢٨ *(24.txt)*

*Text in image:* ٢٠١٥/١١/٢٢ *(12.jpg)*
*Tesseract reads:* ٢٠١٥/١١/٧٢ *(12.txt)*

What i observed is I've issue in my training_text file. I've attached the 
file above. Please guide me for this error as i have failed to find any 
solution myself.

P.s. I've studied the Hallucination effect also which is given in the wiki 
and tried to implement it as i understood, but no luck.

-- 
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 tesseract-ocr+unsubscr...@googlegroups.com.
To view this discussion on the web visit 
https://groups.google.com/d/msgid/tesseract-ocr/6878322a-c591-481b-b0d8-0befd76cbd22%40googlegroups.com.

Reply via email to