Understanding Computer Vision API In Azure

Introduction

This article will cover the following -

  • Brief Concepts and Prerequisites
  • Implementation – Create a new Computer Vision API
  • Implementation – Access the Computer Vision API

Computer Vision API

The Computer Vision API gives you the tools to understand the contents of an image. Create tags identifying objects, beings, or actions present in the image, and then craft coherent sentences to describe it.

Use Computer Vision API to,

  • Generate tags as well as coherent full-sentence descriptions of images
  • Read printed text from images
  • Read handwritten text from images
  • Recognize celebrities and landmarks
  • Analyze video in near real-time
  • Generate a thumbnail

Pre-requisites

Implementation – Create a new Computer Vision API

Steps to be followed

  • Open the Azure portal and click on Add, choose category “AI + Cognitive Services”, and then select an option of “Computer Vision API”.
  • Fill-in the details and create a new resource-group and click on “Create”.
  • Go the “All resources” section and see the newly created “Computer Vision API” named as “computer-vision-api-10-10”.
  • Open the particular Computer Vision API there and see the different options present there.

Implementation – Access the Computer Vision API

Steps to be followed

  • In the opened section of the Computer Vision API, click on the “quick start option”.
  • Click on the “Grab Keys” and copy and paste the “KEY-1” into the Notepad file from here.
  • Then, go to “Make an API call” and click on the Computer Vision API reference.
  • Then, copy the “South Central URL” from there as we have created the API in that region only and copy and paste into the Postman.
  • Then, select any image file from the file-system.
  • Put the Content-type and Ocp-Apim-Subscription-Key’s value into the headers.
  • Click on Send and see the response with the following details.

Happy Learning!