1

Firebase MLKit iOS Text recognition seems to work pretty well if text is formatted in a paragraph or long phrase. However, it fails to work if the numbers are just scattered around which is our case and if there is some line geometry going on around. Some digits are recognized correctly while other exact same digits are not.

I would like to know:

  1. Can MLKit team improve these cases? We are soo close to perfect results but something is causing 1-2 numbers each time to be missed.
  2. Is there any way to hint MLKit of what kind of text we are looking for in the scene? I guess this can increase performance especially on live video conversion and use a smaller size model.
  3. Any kind of image processing that can be done to improve results?

For this test, i have used the official MLKit quick-start project and in particular the MLVisionExample. Here are some cases:

enter image description here enter image description here enter image description here enter image description here enter image description here

Thank you very much!

Kerry
  • 1,015
  • 1
  • 9
  • 11

0 Answers0