Foundry Tool for analysing images, reading text from them (OCR) and detecting faces. Image Analysis API versions 3.2 and 4.0 are both deprecated, with retirement set for 25 September 2028.
Also called Azure AI Vision, Computer Vision, Azure AI Vision.
Read more: Microsoft Learn
In the Ultra Transcenders books
Each book explains Azure Vision in Foundry Tools in context, with comparison tables and the common traps.
Terms in this definition
- Chat message roles
Labels on chat messages: instructions go under system, the person's input under user, the model's previous answers under assistant, and results returned by a called tool under tool (or function).
- OCR
Optical character recognition. It reads handwritten or printed text from documents and images, making it available for analysis, something Azure Language cannot do with scanned images by itself.
- Image Analysis
Azure Vision API that returns several visual features in a single request: for instance tags, a caption, text recognised by Read OCR and the bounding boxes of detected objects.
- API
Short for application programming interface: a contract that client code calls programmatically, for example a web API secured with tokens or the Files, Images or Responses APIs.
- Set
Secret permission in Key Vault for writing secrets; some older material refers to it as Create.
Related terms
- Image classification
A computer vision technique that gives the whole image one or more labels without locating anything, for example distinguishing benign from malignant or identifying a bear's species.
- S0 pricing tier (Foundry Tools)
Name of the standard paid tier for Foundry, Azure OpenAI and most Foundry Tools. Exceptions: Computer Vision calls its standard tier S1, and Document Intelligence offers nothing beyond F0 and S0.
- Semantic segmentation
A computer vision method that assigns a class to each pixel, yielding a mask of an object's precise outline rather than just a bounding box.