Azure Computer Vision Cognitive Services - GetReadResultAsync returning duplicated lines when the read document has handwritting and printed text.

Maie 6 Reputation points
2021-01-06T20:54:41.18+00:00

I am testing the Azure Computer Vision Cognitive Services with the sample code that the Azure website provides. It works fine when the text is all printed in the image being analyzed, however, when I try to get the results for a mixed document, the results are duplicated by line and the handwritten text is fine in one of the lines, and a mess on the duplicated lines.
54090-image.png

I can't find any setting that would return only one line of each. Is this a bug? How can I filter the results?

Thanks!

Azure Computer Vision
Azure Computer Vision
An Azure artificial intelligence service that analyzes content in images and video.
371 questions

2 answers

Sort by: Most helpful
Most helpful Newest Oldest
  1. Maie 6 Reputation points
    2021-01-07T13:30:50.083+00:00

    Nothing is confidential because it is dummy data for testing. Here is the image:
    54319-image.png

    Thank you!

    0 comments
  2. YutongTie-MSFT 51,696 Reputation points
    2021-01-20T09:10:07.803+00:00

    Hello,
    58543-test.txt
    I just tried with Read API and there was no issue/ no duplicate content. https://westus.dev.cognitive.microsoft.com/docs/services/computer-vision-v3-1-ga/operations/5d986960601faab4bf452005/console

    Please try to see if this works for you. I have uploaded the Read API result for reference as well.

    Regards,
    Yutong

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.