
Explore Azure AI Vision image analysis for caption generation, OCR, and object and face detection with bounding boxes. Learn how to use the service via portal, API, or code.
Explore image analysis with Azure AI Vision Studio by creating a vision resource in portal and detecting objects, captions, and bounding boxes via Visual Studio, REST API, Python, or .NET.
Explore the image analysis 4.0 REST API to generate captions and read text from images using PowerShell, with keys and endpoint from the Azure AI Vision resource.
Compare regional api endpoint and custom subdomain api for image analysis. Note domain and authentication: custom subdomain supports Microsoft Entra ID, while both rely on key-based authentication.
Learn Azure AI Vision image analysis to detect clipart or line drawings with the image type feature via a post request, and apply OCR for PDFs.
Explore the difference between Azure AI Vision and Custom Vision, and learn to train on your own images by labeling, training, and querying for image classification or object detection.
Create and configure an Azure Custom Vision resource, connect to the Custom Vision portal, and train an image classification model with apples and bananas, then publish for the prediction API.
Learn how to quickly boost your custom vision model by uploading untagged images and using get suggested tags to tag apples and bananas, improving performance.
Learn how to improve a published Azure Custom Vision image classification model by uploading 900 unlabeled images, generating suggested tags, and reviewing and confirming tags to retrain quickly.
Learn how to export an Azure AI Custom Vision model for offline use by switching from a journal domain to the compact general domain, retraining, and exporting.
Learn how Azure Video Indexer analyzes videos to extract information, including facial recognition (with approval), OCR, speech transcription, topics, sentiment, labels, objects, content moderation, and scene segmentation.
Create and configure an Azure Video Indexer resource, upload media, and run indexing to extract ocr, object detection, key frames, closed captions, and brand detection with model customization.
Discover how Azure Video Indexer extracts video information, including facial recognition (with limited access approval), OCR, speech transcripts, topics, sentiment, object labels, content moderation, and scene segmentation.
Learn to use Azure Video Indexer to identify brand mentions in video content by configuring brand inclusion in the content model customization.
Create an Azure AI Foundry resource and deploy a multi model instruct from the model catalog. Test in playground with image and text input to see mango health benefits.
Unlock the power of computer vision using Microsoft Azure! In this hands-on course, you'll learn to build intelligent vision-based applications using Azure AI Vision services. Whether you're working with images or videos, you'll gain practical skills to analyze, classify, detect, and extract insights from visual content.
This course is perfect for developers, AI enthusiasts, and professionals looking to integrate vision capabilities into their solutions using Azure AI Services. By the end of this course, you'll be equipped to design and implement real-world computer vision applications in the cloud.
What You Will Learn:
Understand Azure AI Vision architecture and its key components
Analyze and classify images using pre-trained models
Perform object detection and facial recognition
Use Optical Character Recognition (OCR) to extract text from images
Generate image descriptions and tags automatically
Work with the Video Indexer for extracting insights from videos
Implement custom vision models for tailored business scenarios
Deploy vision solutions using REST APIs, SDKs, and Azure portal
How This Supports the AI-102 Exam:
This course maps directly to the “Develop Computer Vision Solutions” module in the AI-102: Designing and Implementing a Microsoft Azure AI Solution certification. Specifically, it helps you:
Gain practical experience using Cognitive Services – Vision APIs
Understand how to implement image classification and object detection
Prepare for real-world scenarios asked in the AI-102 case study questions
Learn how to integrate custom vision models for specific use cases
Master the deployment and monitoring of vision models on Azure
Prerequisites:
Basic understanding of Azure services
Familiarity with Python or C# (preferred, but not mandatory)
Enthusiasm to explore AI and computer vision use cases