Description:

The Object Detection step enables a FlowWright workflow to detect common objects contained in an image.

The step belongs to the Azure Cognitive Services category and is exposed in FlowWright with the display name Object detection. Its XML definition describes the capability as “Detect common objects in images.”

The step accepts an image file path and stores the resulting object-detection information in a workflow variable or global variable. This allows image analysis to become part of an automated business process and enables subsequent workflow steps to use the result for classification, routing, reporting, or other processing.

Typical uses include:

• Detecting common objects in uploaded images
• Classifying images according to detected objects
• Enriching image-related business records
• Routing images based on their contents
• Supporting automated image-processing workflows
• Organizing image collections
• Capturing object information as workflow data
• Applying business rules based on detected objects

This step allows FlowWright workflows to incorporate object-based image analysis without requiring users to manually inspect each image.

Usage:

The Object Detection step is typically used after a workflow receives or generates an image that needs to be analyzed for objects.

During execution:

1. Provide the image file path.
2. Execute the Object Detection step.
3. The image is analyzed for common objects.
4. The resulting information is stored in the configured workflow variable or global variable.
5. Continue workflow processing through the True or False execution path.

A typical workflow might look like this:

Typical workflow scenarios include:

• Product-image processing
• Photograph analysis
• Automated image classification
• Image-based routing
• Inventory or asset-image processing
• Image metadata enrichment
• Visual-content processing
• Automated object-based business rules

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 “clsAzureMLGetObjectsDef” example. 

• Create a new process definition named “clsAzureMLGetObjectsDef” and open it in designer mode. 
• Drag a "clsAzureMLgetObjects" step to the canvas.
• Connect the dots between the “Start” and “clsAzureMLgetObjects” steps, as shown above. 
• Define a variable or a global to store the result.
• Click the "clsAzureMLgetObjects" 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 object property and confidence details of an image, and store the result in “variable.Result” as configured. 

Tips:

• Ensure that the configured Image file path points to an accessible image before executing the step.
• Store the result in a workflow variable when it is needed by subsequent workflow steps.
• Use a global variable when the result needs to be referenced more broadly within the workflow.
• Validate the returned object information before using it for business-critical decisions.
• Use the False path to handle image-processing failures or unexpected input conditions.
• Test representative images before deploying object-detection workflows into production.
• Combine this step with Decision, Business Rule, database, file-management, notification, and reporting steps to create complete image-processing workflows.
• Where both object and color information are relevant, use Object Detection together with Color Detection.

Notes:

• The step belongs to the Azure Cognitive Services category. 
• Its display name is Object detection. 
• Image file path is required. 
• Variable/Global to store the result is required. 
• Both configured properties use the string data type. 
• The step provides True and False execution paths. 
• The XML defines two input connections and two output connections. 
• The XML does not define the detailed structure, format, number of detected objects, object-confidence values, or other metadata contained in the stored result. Those details should not be assumed from the XML alone.

Object Detection vs. Color Detection:

Both Object Detection (clsAzureMLGetObjects) and Color Detection (clsAzureMLGetColors) are FlowWright image-analysis steps in the Azure Cognitive Services category. Their configuration model is essentially identical, but they analyze different characteristics of an image.

When to use each step:

Use Object Detection when the workflow needs to determine what objects are present in an image.

Typical examples include:

• Identifying objects in photographs
• Processing product images
• Classifying images based on detected objects
• Routing images according to their contents
• Enriching image records with object information
• Supporting object-oriented business rules

Use Color Detection when the workflow needs information about an image's color characteristics.

Typical examples include:

• Analyzing product-image color schemes
• Capturing color information as metadata
• Classifying images according to visual characteristics
• Supporting color-based business rules
• Routing images using color information

Key Distinction:

The simplest way to distinguish the two is:

Object Detection: “What common objects are present in this image?”

Color Detection: “What color scheme does this image contain?”

The XML definitions explicitly describe the capabilities as “Detect common objects in images” and “Detect color schemes in images.” 

In short: use Object Detection when the workflow needs object-related image information, and use Color Detection when it needs color-related image information.

Definition Sample:

You may download the sample definition from the link provided and import it into your FlowWright environment.

Note: Verify and complete any missing configuration after importing the sample, including:

• Image file path
• Variable/Global to store the result
• Image availability and accessibility
• Success and failure workflow branches
• Any downstream processing that consumes the object-detection result

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

Click here to download the sample file.