Using the Vision API

The Google Vision API is an advanced application API to perform image analysis. The salient features are:

• Safe search: Content moderation of an image
• Label detection: Reads the image and detects objects, events, locations, products and so on
• Face detection: Detects faces and facial features
•  Landmark detection: Detects natural and man-made landmarks
• OCR: Detects text within an image
• Logo detection: Detects popular products and corporate logos
•  Web entities: Detects the contents of the image and returns its information as related to the Google Knowledge Graph

We'll try a simple example of using the Vision API for uploading images to a photo field of a signup form.

Getting ready

The following are the initial setup verification steps for the creation of the network before the recipe can be executed:

1. Create or select a GCP project
2. Enable billing and enable the default APIs (some APIs like BigQuery, storage, monitoring, and a few others are enabled automatically)
3. Enable the Google Vision...