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.
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.