AI-3004: Develop computer vision solutions in Azure

Course Description

Accelerate your AI journey by mastering computer vision solutions in Azure. In this one-day, intermediate instructorled course, developers and AI engineers will learn to design, implement, and optimize image and video processing applications using Azure AI Vision, Custom Vision, Face API, OCR, Video Indexer, and multimodal generative AI. Gain the ability to analyze images, read text, detect objects and faces, index video content, and build vision-enabled generative applications—all through practical implementation using SDKs and REST APIs.

Target Audience

This course is ideal for:

• AI Engineers, Software Developers, and Cloud Engineers aiming to build computer vision applications in Azure

• Professionals proficient in C# or Python, with working knowledge of the Azure portal and cloud fundamentals

Prerequisites:

• Experience with C# or Python

• Basic familiarity with Azure and AI concepts

Course Outline

Module 1: Analyze Images with Azure AI Vision

• Provision Azure AI Vision services

• Use prebuilt models for image analysis, object identification, color analysis, and thumbnail generation 

Module 2: Read Text—OCR and Read API

• Extract printed and handwritten text using OCR

• Integrate the Read API for document digitization and accessibility 

Module 3: Detect, Analyze, and Recognize Faces

• Implement face detection, emotion and attribute analysis, and facial verification

• Train and deploy face identification workflows using Face API

Module 4: Classify Images with Custom Vision

• Build and train custom image classifiers using Azure Custom Vision

• Utilize Vision Studio to label data and deploy classification models 

Module 5: Detect Objects in Images

• Train a custom object detection model to locate and label items using bounding boxes

• Incorporate object detection into web and mobile applications

Module 6: Analyze Video with Azure Video Indexer

• Use Azure Video Indexer to extract insights—transcripts, face recognition, labels, scenes—from videos

• Integrate video analysis workflows in your application stack 

Module 7: Develop Vision-Enabled Generative AI Apps

• Build multimodal chat apps that interpret visual inputs

• Combine image understanding with generative AI responses 

Module 8: Generate Images with Azure Image Generation

• Explore text-to-image generation using AI Foundry or DALL·E-powered services

• Implement prompt-engineered image synthesis within apps 

HandsOn Experience

Expect 40–50% of class time dedicated to handson coding—live demos, guided examples, and real-world exercises to reinforce computer vision solutions in Azure.

What You’ll Learn

By the end of AI3004, you will be able to:

• Deploy and configure Azure AI Vision and Custom Vision resources

• Analyze images and extract text using OCR

• Detect faces, objects, and emotions

• Perform video analysis and indexing

• Build vision-enabled generative AI applications

• Integrate REST/SDK-based computer vision features into production systems