SyedAanif/object-detection

Object Detection using Azure Cognitive Service for Computer Vision

object-detection

Object Detection using Azure Cognitive Service for Computer Vision

Introduction

Object detection is a form of machine learning based computer vision in which a model is trained to recognize individual types of objects in an image, and to identify their location in the image.

An object detection model returns the following information:

• The class of each object identified in the image.
• The probability score of the object classification (which you can interpret as the confidence of the predicted class being correct).
• The coordinates of a bounding box for each object.

Object Detection belongs to advanced computer vision and can be performed in the following ways:

• Azure Cognitive Services for Vision
  • Computer Vision
  • Custom Vision
• Build own advanced computer vision models.

In this project we will be utilising Azure Computer Vision service to process images for object-detection.

Pre-requisites

• Python 3.X version:
  • Installation using Anaconda distribution
  • Python Website
• Microsoft Azure Account
• Editor of choice:
  • Jupyter Notebook comes packaged with Conda distribution
  • Google Colab

Steps to perform Object-Detection

1. Sign-in to your Microsoft Azure account.

2. Create a Resource Group (in a region closest to your location) to logically contain your Azure Resources.

   

3. Create a Computer Vision service inside the resource group created above.

   

4. Copy the Keys and Endpoint from the Computer Vision resource and substitute them for subscription_key and endpoint respectively. This will be used to authenticate the computer-vision-client to the computer vision resource.

   

   

5. Run the provided notebook for performing object-detection.