What is Azure Vision?
Azure Vision is an AI service for computer vision that automatically analyzes images and video. Since the introduction of Microsoft Foundry, the service belongs to the Foundry Tools, detects objects, reads text, and can be customized for specific recognition tasks with Custom Vision. Face recognition is split out as its own service (Azure Face).
Core Features
- Image Analysis: Detects objects, scenes, brands, and generates image descriptions
- OCR: Extracts printed and handwritten text from images and documents
- Custom Vision: Train your own classification and object detection models with a small number of example images
- Video Retrieval: Creates searchable media indexes for image- and text-based search across videos
- Image Embeddings: Generates vectors for image-based similarity search
- Azure Face (separate service): Face detection and analysis with restricted access for sensitive features
Typical Use Cases
Document Processing: Companies digitize paper archives with OCR. Text from invoices, contracts, and handwritten notes is extracted for automated workflows.
Quality Control in Manufacturing: Production lines use Custom Vision for defect detection. The system recognizes scratches, deformations, or missing parts.
Digital Asset Management: Companies organize large image and video archives. Automatic tagging by objects, brands, and colors makes content searchable.
Benefits
- Pre-built models for immediate use without training your own model
- Custom Vision for industry-specific recognition without ML expertise
- Video Retrieval for searchable media libraries
- Container deployment for edge and on-premises scenarios for select features
Integration with innFactory
As a Microsoft Solutions Partner, innFactory supports you with Azure Vision: we implement OCR pipelines for document processing, train Custom Vision models for your specific requirements, and integrate image analysis into your business processes.
Typical Use Cases
Frequently Asked Questions
What is Azure Vision in Foundry Tools?
Azure Vision is Microsoft's computer vision service for analyzing images and video. The former name 'Azure AI Vision' was updated to 'Azure Vision in Foundry Tools' with the introduction of Microsoft Foundry; the feature set and APIs remain largely compatible.
What can Azure Vision detect?
Azure Vision detects objects, scenes, text (OCR), brands, logos, and image quality, and generates image descriptions. Custom Vision enables training your own classification and detection models.
Is face recognition part of Azure Vision?
Face recognition is split out as its own service, Azure Face. Access to sensitive Face features such as identification and verification is classified as Limited Access and requires registration and approval from Microsoft.
Can I train custom recognition models?
Yes, Custom Vision enables training classification and object detection models with a small number of example images, without deep ML expertise.
Does Azure Vision support video analysis?
Yes, Video Retrieval enables creating searchable media indexes and image- or text-based search across videos. The formerly separate 'Spatial Analysis' feature for people counting and motion analysis in video streams was retired in March 2025.
Note: All product information on this page has been compiled with care, but is provided without guarantee and may be outdated or incomplete. Cloud services evolve rapidly — features, pricing, SLAs, and availability change frequently. Authoritative and up-to-date information can only be found on the official product page of Azure (official documentation). This page does not represent an offer by Azure.
