0

I am using Firebase ML Vision to recognize text from images. I am getting pretty decent output. For this image, Here is the output. I want to structure this output in a table format, like it is displayed in the image, there are things like bounding box, rect. But I am not sure how to do that. Can someone help me to achieve this?

Akanksha Singh
  • 79
  • 1
  • 11
  • ML vision return only what you have put it. for table format you have to create view and maintain string return by ML vision. – Hemant Parmar Aug 16 '19 at 08:18
  • Yeah but like how do i identify which specific value belongs to which one, as in this result it has given numeric values after two values, so how can we actually differentiate as there would be a different image every time. – Akanksha Singh Aug 16 '19 at 08:33
  • compare with last one image data. well you can't get accurate value every time even capture same image. – Hemant Parmar Aug 16 '19 at 09:23

0 Answers0