Best practices for arabic OCR

Amro Ghoneim 116 Reputation points
2021-06-20T07:44:16.277+00:00

I am trying to extract all the information given in an Egyptian national ID which mainly contains Arabic letters and digits. I am doing this using Azure's OCR API. The API is working but so far it is inaccurate. What are the best practices that I can use to enhance my results when doing Arabic OCR?

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

1 answer

Sort by: Most helpful
Most helpful Newest Oldest
  1. romungi-MSFT 45,961 Reputation points Microsoft Employee
    2021-06-21T09:04:36.637+00:00

    @Amro Ghoneim Since you are using arabic language the only available option is the OCR API. The results of the OCR API as mostly based on the quality of the image and the requirements should confer to these pre-requisites. Is there a sample image to replicate the issue?

    While, most other languages support the Read API you can try to use it if your requirement is to only extract the numbers from your input image.

    1 person found this answer helpful.

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.