Detecting text in images with the Cloud Vision API

We’re going to begin with a very simple example to show you just how easy it is to start using AI/ML services on Google Cloud. In just a few short steps, you will be able to extract text and associated metadata from an image and save that text in a file. This process is called optical character recognition (OCR).

To begin this process, download the following image to your computer (the image can also be found in the Chapter04/images folder in the git repository you created above): https://github.com/PacktPublishing/Google-Machine-Learning-for-Solutions-Architects/blob/main/Chapter-04/images/poem.png.

The image is shown in Figure 4.4:

Figure 4.4: Sign to be used for OCR

Continue with the remaining steps to upload this image to your Cloud Shell environment:

1. Click the symbol with the three dots at the top-right corner of the Cloud Shell area (at the bottom of your Google Cloud console...