I am aware that I can use ;pivots=programming-language-csharp to get information about a specific image.

Is Azure Content Safety able to 'block out' specific text sections on an image? or does it just detect them but not be able to save the image again without some specific offensive content/pii info/words etc?

What I'm looking for is to be able to not only detect but also reduct the PII info on an image/pdf/word doc

I am aware that I can use https://learn.microsoft/en-us/azure/ai-services/content-safety/quickstart-image?tabs=visual-studio%2Cwindows&pivots=programming-language-csharp to get information about a specific image.

Is Azure Content Safety able to 'block out' specific text sections on an image? or does it just detect them but not be able to save the image again without some specific offensive content/pii info/words etc?

What I'm looking for is to be able to not only detect but also reduct the PII info on an image/pdf/word doc

• c#
• azure-ai
• pii

Share Improve this question Follow asked Nov 20, 2024 at 17:19 ShaneKmShaneKm 21.4k4646 gold badges176176 silver badges307307 bronze badges

Add a comment  | 

1 Answer 1

Sorted by: Reset to default 0

Azure Content Safety can't directly block out or redact text sections of an image. It only detects sensitive content and provides metadata about it.

If you want to perform redaction for images, then you can use Azure OCR for text detection and Azure PII detection for identifying sensitive information. For redacting you will need an additional library like OpenCV.

For PDFs you can use the Azure AI Language service, which supports native document processing to detect AND redact sensitive information. You may also use libraries like pdfplumber for the manipulation.

I hope this helps so far.