Handwritten text capture

(1) Share

Report

Posted on by MNorouzi

I have a form containing questions and then responses in handwirtten which are in a table format in 4 pages. I need to develope a flow to capture the handwritten text and then add them into an excel file. The scanned pdf files are in German language, and need to extract the text from them. Please let me know how and with which action in power automate should I do the text extraction.

Thanks in advance,

Categories:

AI Builder

I have the same question (0)

All responses (4)

Answers (0)

Sort by

Suggested answer

Valantis 5,267 on at

Like (2)

Report
Copy link

Link copied!
Hi @MNorouzi,

You can automate document processing in your flows using AI Builder's document processing model.

Add the "Process and save information from forms" action to your flow

Select your trained AI Builder model

Choose your document source (e.g., email attachment, SharePoint file)

Map the extracted fields to your desired outputs (Excel, Dataverse, etc.)

For detailed instructions and examples, check out the full documentation: https://learn.microsoft.com/en-us/ai-builder/form-processing-model-in-flow
Let me know if that help you :) have a nice day

1 people found this reply helpful.

Was this reply helpful? Yes No
Valantis 5,267 on at

Like (1)

Report
Copy link

Link copied!

Hi @MNorouzi,

Just wanted to check in and see if everything is working now. If you still need any help, feel free to let me know.

Also, if the issue is resolved, it would be great if you could mark the answer as solved so others with the same question can find it easily.

Thanks and have a great day!

1 people found this reply helpful.

Was this reply helpful? Yes No
CFernandes 8,504 Most Valuable Professional on at

Like (1)

Report
Copy link

Link copied!

Hey @MNorouzi
You will need to use the “Recognize text in image or document” action for OCR. However, when I tested this using your sample file, the extracted text included output such as “täglich im Umgang in d. Gemeinschaftsbräumen”, which indicates that the results may not be fully accurate.

As with most OCR solutions, the quality of the extracted text is highly dependent on the quality of the input document. Factors such as scan resolution, image clarity, contrast, and language can significantly impact the accuracy of the output.

If it helped you, please click "Does this answer your question?" and give it a like or mark it as Solution, it helps others in the community find answers more easily!
Connect With Me:
💼 LinkedIn: Clavin Fernandes
📺 YouTube: Clavin Fernandes
📝 Blog: clavinfernandes.wordpress.com
🌐 Community Website: PPUG.org
👥 Join our Community: Power Platform User Group

1 people found this reply helpful.

Was this reply helpful? Yes No
CU19050456-1 10 on at

Like (0)

Report
Copy link

Link copied!
Hi @CFernandes @Valantis ,

I am currently using a similar approach to address the invoice processing requirements. However, I am facing challenges with extraction accuracy, which is currently around 55% for the overall process in production.

The primary challenge is that we receive multiple types of documents and a large variety of invoice formats (approximately 100+ different formats). Due to these layout variations, OCR extraction quality and field mapping consistency are significantly impacted.

I would appreciate your suggestions or recommendations regarding:

Improving extraction accuracy in “Get text from document” or any similiar approach

Best practices for handling multiple document formats

Any available documentation, benchmarks, or references related to AI Builder OCR accuracy

Recommended approaches for scalable invoice-to-JSON extraction

Any guidance or production learnings would be very helpful.

Thanks in advance.

Was this reply helpful? Yes No