0

I’m looking for help to implement - using google AÍ tools ( Vision AutoML and others - s tep by step , an aplication on line / API to read Product labels, including Nutrition facts table : 1- Pre-processing images to resize and rotation if necessary ; 2- Identify the nutrition facts at image; 3- Extract text 4- Make corrections on output text

I’m today using Vision API and it is not working well!

Perhaps using the AÍ tools the issues may be fixed bad Results. I received informations that it has ways to use AutoML for this case , but all I know is that API only classify images ! And the hole process ? How obtain and pos processing texts ?

Help !!

Infinite Loops
  • 671
  • 3
  • 11
  • 23
RALPH ARAUJO
  • 11
  • 1

1 Answers1

1

As far as we all concerned Vision API is one of the early adoption inside Cloud AutoML. You should read through the whole documentation what these APIs are capable of doing.

AutoML can do 3 things as we speak now that are Natural Language, Translation, and Vision. introduction

Check out the beginner's guide here beginner's guide

Infinite Loops
  • 671
  • 3
  • 11
  • 23