The following exercises are designed to provide you with a hands-on learning experience in which you’ll explore common tasks that developers perform when creating computer vision solutions on Microsoft Azure.

Note: To complete the exercises, you’ll need an Azure subscription in which you have sufficient permissions and quota to provision the necessary Azure resources and generative AI models. If you don’t already have one, you can sign up for an Azure account. There’s a free trial option for new users that includes credits for the first 30 days.

Exercises

Analyze images

Use Azure AI Vision Image Analysis to analyze images, suggest captions and tags, and detect objects and people.

Read text in images

Use optical character recognition (OCR) in the Azure AI Vision Image Analysis service to locate and extract text in images.

Detect and analyze faces

Use the Azure AI Vision Face service to implement face detection and analysis solutions.

Classify images

Use the Azure AI Custom Vision service to train an image classification model.

Detect objects in images

Use the Azure AI Custom Vision service to train an object detection model.

Analyze video

Use Azure AI Video Indexer to analyze a video.

Develop a vision-enabled chat app

Use Azure AI Foundry to build a generative AI app that supports image input.

Generate images with AI

Use an OpenAI a DALL-E model in Azure AI Foundry to generate images.

Note: While you can complete these exercises on their own, they’re designed to complement modules on Microsoft Learn; in which you’ll find a deeper dive into some of the underlying concepts on which these exercises are based.