OCR for data extraction from a PDF File

(0) Share

Report

Posted on by Community Power Pla... Microsoft Employee

Hi,

I am trying to create a workflow for extracting particular data like invoice number from PDF file using OCR. which is the best OCR to use in this case.

Thanks in advance,

Kiran.

Categories:

General topics

I have the same question (0)

All responses (2)

Answers (0)

Sort by

PowerBack19 679 on at

Like (0)

Report
Copy link

Link copied!

@Anonymous - The Power Platform has an AI Builder option called "Forms Processing". It can reviews files and "parse" the data from the form and produce an output to be used in Power Automate. Currently, Microsoft has this flagged for General Availability in March 2020. Here are more details: https://docs.microsoft.com/en-us/power-platform-release-plan/2019wave2/ai-builder/use-form-processing-model-power-platform

Was this reply helpful? Yes No
Suggested answer

mathiaskjeldsen 224 on at

Like (0)

Report
Copy link

Link copied!

Hey

I recently did testing of both Microsoft and Tesseract engine, and I found Windows to actually outperform Tesseract. I believe you simply need to test the two engines in your scenario.

Extract text from PDF and images using OCR in Power Automate Desktop - 2024 guide

Best regards
Mathias Kjeldsen

---
If this has helped solve your problem, please mark it as an helpful answer.

Connect with me on social platforms by using the links below.
YouTube: https://www.youtube.com/@matkjeldsen
LinkedIn: https://www.linkedin.com/in/mathiaskjeldsen/

Was this reply helpful? Yes No