UiPath Documentation
maestro-automate
latest
false
Maestro Automate user guide

Google Vision

Look up the Google Vision connector: its actions in alphabetical order, and the sign-in methods of a Google Vision connection.

The Google Vision connector lets a workflow detect labels, logos, faces, text, and handwriting in images. In the Add node panel, it's in the Connector category, under Google Vision. How connector nodes work describes how a connector node is set up.

This page lists what the connector can do in Maestro Automate. Select an action to see how to configure it.

Actions​

Each action is a node that does one thing in Google Vision.

ActionWhat it does
Annotate FilePerform vision analysis on files using Google Cloud Vision services.
Face DetectionDetect multiple faces and key facial attributes in an image using Google Vision.
Handwriting DetectionDetect and extract handwritten text from images and files using Google Vision, including language detection.
Label DetectionGenerate labels for images using Google Vision to identify objects, locations, activities, and more.
Logo DetectionDetect popular product logos within an image using Google Vision.
Text DetectionDetect and extract text from images and files using Google Vision, including language detection.
Web DetectionDetect web references and similar images using Google Vision.

Connection​

A Google Vision node signs in through a connection. Create a connection describes how to create one from the node. On the Connect to page, you sign in with this method:

Sign-in methodWhat you need
CredentialsService Account Configuration.

Google Vision authentication in the Integration Service guide describes the full connection setup, including prerequisites and advanced settings.

Next steps​

  • Actions​
  • Connection​
  • Next steps​

Was this page helpful?

Connect

Need help? Support(opens in new window)

Want to learn? UiPath Academy(opens in new window)

Have questions? UiPath Forum(opens in new window)

Stay updated