Jan-26-2018, 10:17 PM
Hello Forum :)
this is my first post in the forum and my first day with python.
Searched the internet for my problem but could not find a good solution so i thought i try my luck with you.
Situation:
I experimented a little bit with OCR in python3 and it works pretty well with pytesser.
Since the text in the image has multiple colors, I basically create 6 copies of the image with different color channel setups.
So three images have just one channel (red, green or blue) and three images have two channels (red/green, red/blue or blue/green). This results in 6 different strings extracted from the images with slight variations.
Question:
Is there a good way to compare these 6 strings not necessarily line by line but in a more dynamic way? Some images miss some wordwraps or whole lines.
Maybe even with a way to weigh certain results in certain situations more than others? I.e: The no-green-image captures text no other image does, but is still right, even if it is the outlier.
Thanks for your help
this is my first post in the forum and my first day with python.
Searched the internet for my problem but could not find a good solution so i thought i try my luck with you.
Situation:
I experimented a little bit with OCR in python3 and it works pretty well with pytesser.
Since the text in the image has multiple colors, I basically create 6 copies of the image with different color channel setups.
So three images have just one channel (red, green or blue) and three images have two channels (red/green, red/blue or blue/green). This results in 6 different strings extracted from the images with slight variations.
Question:
Is there a good way to compare these 6 strings not necessarily line by line but in a more dynamic way? Some images miss some wordwraps or whole lines.
Maybe even with a way to weigh certain results in certain situations more than others? I.e: The no-green-image captures text no other image does, but is still right, even if it is the outlier.
Thanks for your help