This website uses Cookies. Click Accept to agree to our website's cookie use as described in our Privacy Policy. Click Preferences to customize your cookie settings.
Accept
Reject
Preferences
Log in to ask a question
Get hands-on experience with 20+ free Google Cloud products and $300 in free credit for new customers.
Log in to ask a question

How to improve Document AI model that detects O as zero

Posted on 07-31-2024 11:10 PM
konradpsiuk
Bronze 2
Bronze 2
Reply posted on --/--/---- --:-- AM

Hi

I’m training a model that detects a value that is a mix of letters and number. It is struggling to differentiate O’s and zeros and I’s and one’s. I use >50 files for test and training but it still can’t detect them correctly. Is there any way to improve it?

Solved Solved
0 2 184
Topic Labels
Jump to Solution
0 Likes
1 ACCEPTED SOLUTION

Posted on --/--/---- --:-- AM
jaia
Staff
Reply posted on --/--/---- --:-- AM

Hi,

Thank you for contacting Google Cloud Community!

I would suggest you to do the following:

  1. Acquire more diverse data samples, including different fonts, sizes, styles, and image qualities. This will help the model learn to recognize these characters in various conditions.
  2. Apply techniques like rotation, scaling, noise addition, and cropping to increase the size of your dataset without collecting new data.

Regards,
Jai Ade

View solution in original post

Jump to Solution
2 REPLIES 2