With Google Cloud Vision modules in Boost.space Integrator, you can run a localizer for object detection within an image and iterate the result array.
To use the Google Cloud Vision modules, you must have a Google Cloud Vision AI account with billing enabled. You can create an account at cloud.google.com/vision.
Refer to the Google Cloud Vision API documentation for a list of available endpoints.
To establish the connection, you must:
Before you establish the connection in Boost.space Integrator, you must create and configure a project in the Google Cloud Console to obtain your API key.
![[Note]](https://docs.boost.space/wp-content/themes/bsdocs/docs-parser/HTML/css/image/note.png) |
Cloud Billing |
|---|---|
|
Your Google account must have Cloud Billing set up in order to enable the required APIs in your project. For information regarding how to create and manage Cloud Billing, see Google’s Manage your Cloud Billing account guide. |
To create a Google Cloud Console project:
-
Log in to the Google Cloud Console using your Google credentials.
-
In the top menu, click Select a project > New project.
-
Enter a Project name and select the Location for your project.
-
Click Create.
-
In the top menu, check if your new project is selected in the Select a project dropdown. If not, select the project you just created.
To enable the required API:
To establish the connection in Boost.space Integrator:
-
Log in to your Boost.space Integrator account, add a Google Cloud Vision module to your scenario, and click Create a connection.
-
Optional: In the Connection name field, enter a name for the connection.
-
In the API Key field, enter the value you copied in the Obtain your Google Cloud Vision API key section above.
-
Click Save.
-
If prompted, authenticate your account and confirm access.
You have successfully established the connection. You can now edit your scenario and add more Google Cloud Vision modules. If your connection requires reauthorization at any point, follow the connection renewal steps here.
After connecting the app, you can perform the following action:
Images
-
Run Handwriting Detection within an Image
-
Run Label Detection within an Image
-
Run Text Detection (OCR) within an Image
-
Run Localizer for Object Detection within an Image and Iterate the Result Array
-
Run Landmark Detection within an Image and Iterate the Results
-
Run Face Detection within an Image and Iterate the Result Array
-
Compute Image Dominate Colors and Iterate the Result Array
-
Detect Potentially Unsafe or Undesirable Content within an Image
-
Run Text Detection (OCR) within a File and Iterate the Result Array