Training Overview

Developing Computer Vision Solutions with Azure AI Services

This One-Day intermediate-level custom training equips developers, Data & AI engineers, and app makers with the skills to build robust computer vision solutions using Azure AI Vision. Participants will learn to provision and configure Azure AI Vision resources, apply both prebuilt and custom models to analyze images and video, and integrate vision capabilities into generative AI applications. Through hands-on labs, learners will also prepare for the Microsoft Applied Skills assessment, gaining practical experience and confidence in deploying real-world vision solutions.

Before enrolling in this custom training, participants should ideally be familiar with navigating the Azure portal and possess hands-on experience programming in either Python or C#. This foundational knowledge ensures they can confidently provision resources, interact with APIs, and implement computer vision capabilities throughout the course.

Module Breakdown:

• Analyze Images: Learn to extract visual features like tags, descriptions, and image types using prebuilt models.

• Read Text in Images: Use OCR capabilities to detect and extract printed and handwritten text from images.

• Detect, Analyze, and Recognize Faces: Explore facial detection, emotion analysis, and identity recognition using Azure’s face APIs.

• Classify Images: Build and train custom image classification models to categorize visual content.

• Detect Objects in Images: Identify and locate multiple objects within images using object detection models.

• Analyze Video: Apply vision analysis to video streams, including object tracking and scene segmentation.

• Develop a Vision-Enabled Generative AI Application: Combine Azure AI Vision with generative AI to create intelligent, multimodal applications.

• Generate Images with AI: Use generative models to create synthetic images based on prompts or structured input.

Book This Class