Azure Computer Vision - Detect objects

Use the Azure Computer Vision - Detect objects action A tool for building the processes, logic, and direction within workflows. Actions are the steps the workflow performs to complete a process. to analyze an image.

Object detection is similar to tagging, but Azure Computer Vision returns the bounding box coordinates (in pixels) for each object found. For example, if an image contains a dog, a cat, and a person, the Detect operation will list those objects together with their coordinates in the image. You can use this functionality to process the relationships between the objects in an image. It also lets you determine whether there are multiple instances of the same tag in an image.

Input requirements:

  • Supported image formats: JPEG, PNG, GIF, BMP.

  • Image file size must be less than 4MB.

  • Image dimensions must be at least 50 x 50.

For more information about the Azure Computer Vision connector, go to Azure Computer Vision.

Before you begin: 

Jump to:

Configure the Azure Computer Vision - Detect objects action

  1. Add the action to the workflow and open the action configuration panel. For more information, see Add an action to the workflow.

  2. Select a Connection. If you do not have a connection, see Add a connection.
  1. Insert a variable that contains the Image file.

Azure Computer Vision - Detect objects action fields and settings

Section Field Description Variable types

(unlabeled)

Connection Credentials and other settings that enables workflows to communicate with external systems, services, or applications. It's required to pass data between the workflow and the indicated service, which could be a cloud service, business application, or content store.

The Azure Computer Vision connection used to access the account for which you want to Detect objects.

To refresh the available connections, click .

 (n/a)

 

 Image

The variable containing the image file to be analyzed.

Note: Your tenancy's default file storage location must be configured to hold files for later reference by the workflow. This location is used for uploaded files and for files stored as output from actions.

File
Output Objects in image

Stores the result of the action as an object with the following variables:

  • Metadata: (Object) A list of details about the image.

    • Format: (Text) The format of the input image, such as JPEG.

    • Height: (Decimal) The height of the input image.

    • Width: (Decimal) The width of the input image.

  • Objects: (Collection) The list of objects found.

    • Confidence: (Decimal) The confidence score for the object prediction.

    • Object: (Text) The description of the object.

    • Parent: (Object) The description of the collective grouping of an object, such as computer to laptop.

      • Object: (Text) The description of the object group.

      • Confidence: (Decimal) The confidence score for the parent description prediction.

    • Rectangle: (Object) The coordinates in the image that define the object.

      • H: (Decimal) The height of the object area, in pixels.

      • W: (Decimal) The width of the object area, in pixels.

      • X: (Decimal) The pixel value on the x-axis (left to right) of the image where the object area starts.

      • Y: (Decimal) The pixel value on the y-axis (top to bottom) of the image where the object area starts.

  • Request ID: (Text) The unique identifying number for this object detection request.

 Object