Azure AI Vision supports multiple image analysis capabilities, including:
- Optical character recognition (OCR) - Azure AI Vision service can use optical character recognition (OCR) capabilities to detect text in images (for example, text from Newspaper)
- Generating captions and descriptions of images - "A man jumping on a skateboard"
- Detection of thousands of common objects in images - "Skateboard (90.40%), Person (95.5%)"
- Tagging visual features in images - sport (99.60%), person (99.56%), footwear (98.05%), skating (96.27%), boardsport (95.58%)
- Object Detection - detect objects presented on the image
- Azure AI Face can detect faces that are partially obscured. But it works not ideally:
![image](https://private-user-images.githubusercontent.com/4239376/302094720-23d8277f-51fa-447b-b1f8-2a6bb676262f.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.OXM1OzXsxDm5HzapAiNL0ZKQEbIEeasjgNpXrrU2wp8)
Lab. Build an object detector with Custom Vision
https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/get-started-build-detector