Image recognition with azure cognitive services

Hello all,
This blog is supposed to help you get started with Microsoft Azure cognitive services but the main focus will be on Computer Vision API.

So as we know, AI is all about amplifying human ingenuity with intelligent technology with the basic goal of reasoning, Understanding and Interacting back in a human-like manner. Building AI into programmes has always been known to be a very tough task that can only be done by a team of expert but thanks to Azure Cognitive Services incorporating AI into your systems has been made easier.

What is Azure Cognitive Services? Cognitive Services bring AI within reach of every developer — without requiring machine-learning expertise. All it takes is an API call to embed the ability to see, hear, speak, search, understand, and accelerate decision-making into your apps. I love to see it as AI in a box cause there are a lot of AI systems already created in it and you can just make use of any of them by just an API call.

What are the benefits of using Azure cognitive services?

1: You can apply AI to more scenarios with the most comprehensive portfolio of domain-specific AI capabilities on the market.

2: You can also build confidently with the first AI services to achieve human parity in computer vision, speech, and language.

3: Also, you can deploy Cognitive Services anywhere from the cloud to the edge with containers.

Check Azure page for more info about Azure Cognitive Services, let’s move to computer vision with azure cognitive services.

To get started with Azure computer vision you first need to create an Azure account and as a first user, you’ll get $200 for the first month on azure to use in playing around their services after that go to your portal which should look similar to this.

Click on the Menu icon then navigate to all services and then AI + Machine learning then Cognitive services or you can just search for cognitive services on the search bar

Then you’ll click on the create cognitive service or add button then search for computer vision in the cognitive services section and click on it then go on to create one by filling in the appropriate contents

Then click on create and wait for some mins for it to create then you should be given an API key and endpoint which is all you need to communicate with the computer vision system.

SO I tested it with this image and it gave this back, easy right?

That’s all, thank you.

I hope you learnt from the blog, feel free to drop any questions and feedback.