Udemy
Turn what you know into an opportunity and reach millions around the world.
Learn More
Your cart is empty.
Keep shopping
Microsoft AI: Intro to Computer Vision AI with Labs & Sims
New
9 students

Microsoft AI: Intro to Computer Vision AI with Labs & Sims

Learn computer vision, image analysis and generation in Microsoft Foundry with a guided simulation and lab
Created byJames Dethwick
Last updated 10/2026
English
English

What you'll learn

  • Distinguish image classification, object detection, semantic segmentation, and contextual image analysis.
  • Explain how pixel values, color channels, filters, and kernels support image processing and feature extraction.
  • Describe how convolutional neural networks and vision transformers learn visual features from images.
  • Explain how multimodal models combine image and text inputs to analyze and describe visual content.
  • Describe diffusion-based image generation and identify image and video generation options in Microsoft Foundry.
  • Identify Azure vision capabilities, including image tagging, captions, OCR, face detection, and video analysis.
  • Explore image analysis and generation workflows through the course exercises and Microsoft Foundry lab.
  • Evaluate computer vision use cases and recognize fairness, privacy, consent, and model limitations in responsible AI.

Course content

3 sections • 19 lectures • 1h 56m total length
  • Introduction to Computer Vision3:23
  • Learning Exercise: Introduction to Computer Vision Concepts2:01
  • Defining Computer Vision10:17
  • Image Processing: How it works?11:04
  • Convolutional Neural Networks CNN2:32
  • Vision Transformer ViT9:51
  • Optional Exercise: Explore computer vision4:35
  • Quiz3:35

Requirements

  • No prior computer vision experience is required. The course introduces the concepts before exploring Azure tools.
  • Basic AI and cloud familiarity is helpful. Parts 1–4 of the eight-part Microsoft AI Fundamentals AI-901 series provide useful background.
  • A computer with internet access and a modern browser is needed to follow the online exercises and explore the tools.
  • An Azure subscription and access to the relevant models and services are needed to perform the live Microsoft Foundry lab. The optional browser exercise does not require an Azure subscription.
  • Basic Python familiarity is helpful for interpreting the code example, but programming experience is not required to follow the conceptual lessons.

Description

Discover how AI turns images into useful information with a focused beginner course based on Microsoft's official curriculum, enriched with additional explanations and practical guidance. Taught by a Microsoft Certified Trainer, this course includes a guided Microsoft Foundry computer vision simulation, a Foundry lab exercise, two learning exercises, an optional computer vision exercise, and two quiz walkthroughs. Whether you want to understand image analysis for business applications or strengthen your understanding of these AI-901 topics, you will build a clear foundation in Microsoft computer vision.


Begin with the main computer vision tasks: image classification, object detection, semantic segmentation, and contextual image analysis. Learn how computers represent images as arrays of pixels and how filters help extract visual features. Explore convolutional neural networks (CNNs) and vision transformers (ViTs), including the roles of feature maps, image patches, embeddings, and attention.


Explore how multimodal models combine images and language to interpret visual content. Examine image generation and the basic idea behind diffusion models, then connect these concepts to image analysis and generation in Microsoft Foundry. The course also introduces Azure vision capabilities such as image captions, visual tags, optical character recognition (OCR), face detection, and video analysis, along with an introduction to content understanding.


Connect the technology to business needs through examples in healthcare, manufacturing, and retail. Consider responsible AI and ethics in computer vision, including fairness, privacy, and the effects of bias. These lessons help you evaluate potential uses of vision systems alongside their limitations and impact.


Reinforce your understanding with learning exercises on computer vision concepts and computer vision in Azure. Explore the optional computer vision exercise, follow the guided simulation to get started with computer vision in Microsoft Foundry, and work through the Foundry lab exercise. Two quiz walkthroughs and a concluding summary support your review. The guided simulation offers a way to explore the workflow without an Azure subscription; the live cloud exercises require access to the relevant Azure or Microsoft Foundry environment. Review each activity's requirements before following along.


Across three sections and 19 video lessons, with approximately 1 hour and 57 minutes of video, this course provides a manageable introduction for beginners, students building foundational AI knowledge, and professionals exploring computer vision in business solutions. Basic computer skills are a useful starting point. By the end, you will be better prepared to explain common vision workloads, compare key model approaches, and recognize appropriate uses of computer vision in Azure and Microsoft Foundry.

Who this course is for:

  • Learners following the eight-part Microsoft AI Fundamentals AI-901 series who are ready for Part 5: Intro to Computer Vision AI.
  • Beginners and students who want to understand how AI interprets images and video and generates visual content.
  • Developers, IT professionals, and aspiring AI practitioners seeking an introduction to Azure vision services and Microsoft Foundry models.
  • Business and technical learners exploring image analysis, OCR, accessibility, and computer vision applications in manufacturing, retail, and other industries.