胎盘低要注意什么
Easily customize your own state-of-the-art computer vision models for your unique use case
Overview
Create a custom computer vision model in minutes
Customize and embed state-of-the-art computer vision image analysis for specific domains with AI Custom Vision, part of Azure AI services. Build frictionless customer experiences, optimize manufacturing processes, and accelerate digital marketing campaigns. No machine learning expertise is required.
- Start training your computer vision model by simply uploading and labeling a few images. The model tests itself on these and continually improves precision through a feedback loop as you add images. To speed development, use customizable, built-in models for retail, manufacturing, and food.
- A user-friendly interface walks you through developing and deploying custom computer vision models. Then either ping the API to quickly tag images with your new computer vision model or export the model to a device to run real-time image recognition.
- Run your models wherever you need them and according to your unique scenario and requirements. Easily export your trained models to devices or to containers for low-latency scenarios.
Features
Key features
Customization to your scenario
Set your model to perceive a particular object for your use case.
Intuitive model creation
Easily build your image identifier model using the simple interface.
Flexible deployment
Run Custom Vision in the cloud or at the edge in containers.
Built-in security
Rely on enterprise-grade security and privacy for your data and any trained models.
Security
Embedded security and compliance
34,000
Full-time equivalent engineers dedicated to security initiatives at Microsoft.
15,000?
Partners with specialized security expertise.
?
>100
Compliance certifications, including over 50 specific to global regions and countries.
Pricing
World-class custom computer vision at competitive prices
Pay only for what you use with no upfront costs. With Azure AI Custom Vision, you pay as you go based on the number of transactions, training hours, and image storage.
Frequently asked questions
- Azure AI services, including Custom Vision, guarantee 99.9% availability.
- Yes. Because Azure AI Custom Vision is designed to be customized for your scenario, you need to provide the data to train your model.
- Azure AI Custom Vision is optimized to quickly recognize major differences between images, so you can start prototyping your model with a small amount of data. Microsoft recommends starting with 50 images per label. Depending on the complexity of the problem and degree of accuracy required, hundreds or thousands of samples might be required for your final model.
- It’s both. Use the site to access a graphical interface for labeling data and training models. Or use the Custom Vision SDKs to do these things.
- Azure AI services offer several capabilities depending on your use case. The?Azure AI Vision?video- and image-recognition model is a good starting point if you don’t want to build your own model.?Azure AI Document Intelligence?is optimized for document processing,?Azure AI Video Indexer?for extracting advanced metadata from audio and video files,?Azure AI Vision?for facial recognition and detection, and?Azure AI Content Safety?for detecting unwanted text or images.
Next steps
Choose the Azure account that’s right for you
Pay as you go or try Azure free for up to 30 days.
Azure Solutions
Azure cloud solutions
Solve your business problems with proven combinations of Azure cloud services, as well as sample architectures and documentation.
Business Solution Hub
Find the right Microsoft Cloud solution
Browse the Microsoft Business Solutions Hub to find the products and solutions that can help your organization reach its goals.
Get the Azure mobile app 
