Azure OCR Line Concatenation Issue Leading to Incorrect Text Recognition

Adam Mucha 10 Reputation points
2024-11-19T15:31:59.4033333+00:00

Hello,

We've consistently noticed an issue with Azure OCR in which the service returns a JSON that concatenates words from two separate document lines. It's extremely unpredictable and leads to a lot of issues that we can't fix or foresee and repair.

User's image

For example, on the image of a PDF scan there are 3 lines in three different languages. Azure OCR on one occasion returned the text "FRACHTBRIEF SAMOCHODY" as a valid read in the JSON, on a different occasion it returned "CONSIGNEMENT SAMOCHODOWY".

Is there a way to configure how will the lines be concatenated?

Azure Computer Vision
Azure Computer Vision
An Azure artificial intelligence service that analyzes content in images and video.
396 questions
{count} votes

1 answer

Sort by: Most helpful
  1. Deleted

    This answer has been deleted due to a violation of our Code of Conduct. The answer was manually reported or identified through automated detection before action was taken. Please refer to our Code of Conduct for more information.


    Comments have been turned off. Learn more

Your answer

Answers can be marked as Accepted Answers by the question author, which helps users to know the answer solved the author's problem.