Microsoft’s Custom Vision can build computer vision AI models in minutes.
Microsoft cognitive services have taken incredibly sophisticated Artificial Intelligence and machine learning and turned it into something that is easy. The latest addition to Microsoft’s Cognitive Service is Custom Vision. It lets you create complicated computer vision applications. However, it takes little to no effort and time.
Cornelia Carapcea, the Senior Project Manager at Microsoft, demonstrated the technology on stage at Microsoft’s Build conference in Seattle earlier today.
Creating your own Custom Vision API just requires a sample of training data set. This consists of a little over a dozen photographic sample and it does the rest.
After that Microsoft creates the Custom model which takes a few minutes. Then you can access it via a RESAT API. Also, the REST API is hosted by Microsoft servers. Carapcea said that it can be used in identifying food landmarks even in the retail environment.
The Custom Vision Models improve automatically. this selects images that are most likely to add the most gain to your model. Which allows for you to manually tag the images which then improves the overall accuracy and reliability