Description:

The Face detection step belongs to the Azure Cognitive Services category in FlowWright. Its XML definition identifies the step as clsazuremlgetfaces, with the label “Detect human faces within an image and generate the age, gender, and rectangle for each detected face.” and display name “Face detection.”

The step accepts an image file path, sends the image for face detection, and stores the resulting face-detection information in a specified workflow variable or global variable. The XML specifically describes the detected information as including age, gender, and a rectangle for each detected face.

Typical uses include:

• Detecting human faces in uploaded images
• Identifying the number and location of faces in an image
• Extracting age information associated with detected faces
• Extracting gender information associated with detected faces
• Processing images as part of automated business workflows
• Routing workflows based on image-analysis results
• Storing face-detection results for subsequent workflow processing
• Integrating image analysis into document, customer, or media-processing workflows

The step provides True and False execution paths, allowing the workflow to branch according to whether the face-detection operation succeeds or fails.

Usage:

The Face detection step is typically placed in a workflow after an image has been uploaded, retrieved, or otherwise made available to the process.

During execution:

1. Provide the Image file path.
2. Provide the Variable/Global to store the result.
3. Execute the step.
4. FlowWright processes the image for face detection.
5. The resulting face information is stored in the configured variable/global.
6. Continue through the True or False workflow path.

A typical workflow might look like:

Possible downstream processing includes:

• Counting detected faces
• Determining whether a face is present
• Recording face-related information
• Routing the workflow based on detection results
• Generating an image-analysis report
• Combining face detection with other image-analysis operations

The exact structure for iterating over individual detected faces is not defined in the XML and should be determined from the runtime result produced by the FlowWright implementation.

To use this step, you need to set up an Azure ML service in the FlowWright application. Go to the Status > Settings > Configuration page. Select the Azure ML category from the drop-down menu. Click here to learn more about the Azure ML and Cognitive Service subscription. 

A sample Azure ML configuration is provided here for reference. 

Example:

Let’s build and execute the “clsAzureMLGetFacesDef” example. 

• Create a new process definition named “clsAzureMLGetFacesDef” and open it in designer mode. 
• Drag a "clsAzureMLgetFaces" step to the canvas.
• Connect the dots between the “Start” and “clsAzureMLgetFaces” steps, as shown above. 
• Define a variable or a global to store the result.
• Click the "clsAzureMLgetFaces" step to configure its "Required" properties. Provide a name for the step. Provide the image file path on the app server. Provide a variable or global reference to store the result. Click the Save button. Note: Click the "AI Predict" button to have the Copilot add new process steps that match your process description. 
   

• The “Logging” configuration is necessary for documentation and also measures workflow progress and percent complete. This is achieved by configuring the step state and percent fields individually, as shown below. Configure the “Logging” using the following properties.

• Save the process definition, create a new instance, and run it. Render the process instance. Click the process step to view its properties. The step should retrieve the age and gender of the faces in an image, and store the result in “variable.result” as configured. 

Tips:

• Always configure both required properties: Image file path and Variable/Global to store the result. 
• Verify that the configured image path points to an accessible image.
• Use workflow variables when the image path is generated dynamically.
• Store the result in a dedicated workflow variable/global when subsequent steps need to process it.
• Use the True path for successful face-detection execution.
• Use the False path for execution failures or appropriate error handling.
• Do not treat the True/False result as an indication that faces were or were not found.
• Use the stored result to make business decisions about detected faces.
• Test the workflow with images containing zero, one, and multiple faces.
• Test images with different resolutions and compositions to validate the workflow behavior.
• Ensure the FlowWright environment has access to the image path used by the process.
• Combine this step with other image-analysis steps when the workflow requires broader image understanding.

Notes:

• Face detection belongs to the Azure Cognitive Services category. 
• Its internal name is clsazuremlgetfaces. 
• Its namespace is FlowWright.Workflow.ClsAzureMLGetFaces. 
• Its DLL is FlowWright.Workflow.dll. 
• Its display name is Face detection. 
• The step has 2 input connections and 2 output connections. 
• Image file path is required. 
• Variable/Global to store the result is required. 
• Both configurable properties use the string data type. 
• The step provides True and False execution paths. 
• The step description states that detected faces can have age, gender, and rectangle information generated. 
• The XML does not define the exact structure or serialization format of the stored result.

clsAzureMLGetFaces vs. clsAzureMLGetObjects:

Both Face detection and Object detection are Azure Cognitive Services workflow steps designed to analyze an image. Their configuration models are almost identical, but they perform different types of image analysis.

clsAzureMLGetFaces focuses specifically on human faces, whereas clsAzureMLGetObjects focuses on common objects in an image.

When to Use Each Step

Use clsAzureMLGetFaces when:

• The workflow needs to detect human faces.
• Face location information is required.
• Age information from detected faces is required.
• Gender information from detected faces is required.
• The workflow needs to process images containing people.
• Subsequent workflow logic depends on face-detection information.

Use clsAzureMLGetObjects when:

• The workflow needs to detect common objects.
• The workflow needs to identify objects present in an image.
• Image contents need to be categorized by detected objects.
• Subsequent workflow logic depends on object-detection information.

Use both when:

• The workflow needs both people and object information.
• An image requires multiple independent analyses.
• Face and object results need to be combined for a business decision.

Key Distinction

The simplest way to distinguish the two steps is:

clsAzureMLGetFaces: “Find human faces in this image and generate face-related information.”

clsAzureMLGetObjects: “Find common objects in this image.”

In short:

• GetFaces = people/face analysis
• GetObjects = common-object analysis
• Both require an image file path.
• Both require a variable/global for the result.
• Both have True and False execution paths.
• Both use string-based configuration properties.
• GetFaces specifically generates age, gender, and rectangle information for detected faces according to its XML definition. 
• GetObjects is specifically intended for common object detection.

Definition Sample:

You may download the sample definition(s) from the provided link and later import them by drag-and-drop into the FlowWright Process Definition (XML file) page.

Note: After importing the sample, verify and complete any missing configuration, including:

• Image file path
• Result variable/global
• Image accessibility and permissions
• Azure Cognitive Services environment configuration
• Environment-specific settings

After verifying the configuration, save the Process Definition before execution.

Click here to download the sample file.