Computer Vision | Microsoft Azure

Support us by sharing

An AI service that analyzes content in images

Extract rich information from images

Boost content discoverability, accelerate text extraction, and create products that more people can use by embedding vision capabilities in your apps. Use visual data processing to label content, from objects to concepts, extract printed and handwritten text, recognize familiar subjects like brands and landmarks, and moderate content. No machine learning expertise is required.

Innovation within reach

Transform your app with computer vision—all through an API call.

Powerful content extraction

Pull from a deep index of more than 10,000 objects and 25 languages that collects insights at scale.

Vision for all users

Extend capabilities to more users, with the image description feature.

Flexible deployment

Run Computer Vision in the cloud or on the edge, in containers.

Easily apply breakthrough computer vision

Add leading-edge computer vision technology to your own apps with a simple API call.

See it in action

Feature Name: Value
Objects [
“rectangle”: {
“x”: 93,
“y”: 178,
“w”: 115,
“h”: 237
“object”: “person”,
“confidence”: 0.764
“rectangle”: {
“x”: 0,
“y”: 229,
“w”: 101,
“h”: 206
“object”: “person”,
“confidence”: 0.624
“rectangle”: {
“x”: 161,
“y”: 31,
“w”: 439,
“h”: 423
“object”: “subway train”,
“parent”: {
“object”: “train”,
“parent”: {
“object”: “Land vehicle”,
“parent”: {
“object”: “Vehicle”,
“confidence”: 0.926
“confidence”: 0.923
“confidence”: 0.917
“confidence”: 0.801
Tags [
“name”: “train”,
“confidence”: 0.9975446
“name”: “platform”,
“confidence”: 0.9955431
“name”: “station”,
“confidence”: 0.979800761
“name”: “indoor”,
“confidence”: 0.9277198
“name”: “subway”,
“confidence”: 0.8389395
“name”: “clothing”,
“confidence”: 0.5043765
“name”: “pulling”,
“confidence”: 0.4317162
Description {
“tags”: [
“captions”: [
“text”: “people waiting at a train station”,
“confidence”: 0.8330992
Image format “Jpeg”
Image dimensions 462 x 600
Clip art type 0
Line drawing type 0
Black and white false
Adult content false
Adult score 0.009112834
Racy false
Racy score 0.0143244695
Categories [
“name”: “trans_trainstation”,
“score”: 0.98828125
Faces []
Dominant color background “Black”
Dominant color foreground “Black”
Accent Color #484C83

Transform your processes

Automatically identify more than 10,000 objects and 25 languages. Streamline processes across multiple scenarios, such as robotic process automation and digital asset management, with rich data extraction from images.

Extend your apps to more users

Empower users with low vision by providing descriptions of images. Learn how Microsoft applies Computer Vision to PowerPoint, Word, Outlook, and Excel for auto-captioning of images for low-vision users. And help users navigate the world around them by pairing Computer Vision with Immersive Reader to turn pictures of text into words read aloud.

Turn your camera into an inclusivity tool

Deploy anywhere, from the cloud to the edge

Run Computer Vision in the cloud or on-premises with containers. Apply it to diverse scenarios, like healthcare record image analysis, where data security and low latency are paramount.

Learn about Computer Vision in containers

Build on industry-leading Azure security

World-class computer vision at competitive prices

Pay only for what you use with no upfront costs. With Computer Vision, you pay as you go based on number of transactions.

Get started with Computer Vision in 3 steps

Get instant access and


credit by signing up for your Azure

free account


Sign in

to the Azure portal and add Computer Vision.


how to embed Computer Vision with quickstarts and documentation.

Developer resources

Documentation and quickstarts

Get up and running with Computer Vision.

Start coding

Visual Studio for Computer Vision

Learn how to use the Visual Studio Connected Services feature to embed Computer Vision.

Read the article

Frequently asked questions about Computer Vision

  • Computer Vision and other Cognitive Services offerings guarantee 99.9-percent availability. No SLA is provided for the Free pricing tier. See

    SLA details


  • Your images are automatically deleted after processing. Microsoft does not train on your data to enhance the underlying models. Learn more about


    and terms of usage.

  • Yes, you can extract one-off images from video content.

Ready when you are—let’s set up your Azure free account

Start free


Support us by sharing

Leave a Reply