Identifying Landmarks with Vision API

45 minutes
  • 4 Learning Objectives

About this Hands-on Lab

Google Cloud Vision API is capable of recognizing a range of different types of objects in images, such as faces, text, and even handwriting. In this hands-on lab, you’ll use the API to detect and identify landmarks from around the globe in both a Cloud Storage bucket and via a remote URL.

Learning Objectives

Successfully complete this lab by achieving the following learning objectives:

Enable the API

Enable the Google Cloud Vision API, either through the GCP console or the Cloud Shell.

Create the Required Cloud Storage Bucket

Create the Cloud Storage bucket to hold the images being processed.

Retrieve Files from the Repo and Copy Them to the Bucket

Clone the GitHub repository to retrieve the example files and copy them to the Cloud Storage bucket.

Call Vision API

Execute the command to call the Cloud Vision API and process the specified file.

Additional Resources

Your team is looking to automate the identification of the landmarks in the photos they receive through their social network app so that they categorize them correctly. You’ve been asked to put the Google Cloud Vision API through its paces and evaluate whether it can be used to fill this need.

To accomplish this task, you’ll need to complete the following steps:

  1. Enable the Cloud Vision API
  2. Create a Cloud Storage bucket
  3. Move testing files into the bucket
  4. Execute the proper call to Cloud Vision API

The resource are located in this GitHub repository, in the vision-api-lab folder.

What are Hands-on Labs

Hands-on Labs are real environments created by industry experts to help you learn. These environments help you gain knowledge and experience, practice without compromising your system, test without risk, destroy without fear, and let you learn from your mistakes. Hands-on Labs: practice your skills before delivering in the real world.

Sign In
Welcome Back!

Psst…this one if you’ve been moved to ACG!

Get Started
Who’s going to be learning?