ThingWorx Flow > Connectors Overview > System Connectors > Azure > Face Recognition
  
Face Recognition
Use this action to detect human faces in an image, and then return face locations. Optionally, you can include with faceIds, landmarks, and attributes.
The Face Recognition action supports images that meet the following requirements:
Format is PEG, PNG, GIF (the first frame), or BMP.
File size is from 1KB to 6MB.
Image size is from 36x36 to 4096x4096
Faces are detectable when the image size is 36x36 to 4096x4096 pixels. To detect minute but clear faces, try to enlarge the input image.
Up to 64 faces can be returned for an image. Faces are ranked by face rectangle size from large to small.
Using the Face Recognition Action
To use this action in your workflow, connect it to ThingWorx Flow. To connect to the flow, do the following:
1. Drag the Face Recognition action under the Azure connector to the canvas, place the pointer on the action, and then click or double-click the action. The Face Recognition action window opens.
2. Edit the label name, if needed. By default, the label name is same as the action name.
3. To add a new authorization, refer to the section Authorize Azure in the topic Azure connector.
* 
If you previously added an authorization for Azure, select an authorization from the list.
4. Select the resource group defined in the subscription.
5. Select a Face API Account defined in the resource group.
6. Select an option to provide an image format:
URL—Specify publicly accessible image URL.
Upload File—Specify the path of the file stored in the local storage of the ThingWorx Flow engine that you want to upload.
7. In the Parameters section, select an option:
Should Face IDs be Returned—Select true to return face IDs of the detected face or select false.
Should Face Landmarks be Returned—Select true to return landmarks of the detected faces or select false.
Face Attributes to be Returned—Click Add to analyze and return one or more specified face attributes from the Face Attribute list.
Click Add to analyze and return multiple face attributes.
8. Click Done.
Output Schema
The Face Recognition action returns an output schema as shown in the figure that follows: