Label Visualization¶

Draw text labels on detected objects with customizable content, position, styling, and background colors to display information like class names, confidence scores, tracking IDs, or other detection metadata.

How This Block Works¶

This block takes an image and detection predictions and draws text labels on each detected object. The block:

1. Takes an image and predictions as input
2. Extracts label text for each detection based on the selected text option (class name, confidence, tracker ID, dimensions, area, time in zone, or index)
3. Determines label position based on the selected anchor point (center, corners, edges, or center of mass)
4. Applies background color styling based on the selected color palette, with colors assigned by class, index, or track ID
5. Renders text labels with customizable text color, scale, thickness, padding, and border radius using Supervision's LabelAnnotator
6. Returns an annotated image with text labels overlaid on the original image

The block supports various text content options including class names, confidence scores, combination of class and confidence, tracker IDs (for tracked objects), time in zone (for zone analysis), object dimensions (center coordinates and width/height), area, or detection index. Labels are rendered with colored backgrounds that match the object's assigned color from the palette, and text styling (color, size, thickness) can be customized for optimal visibility. The labels can be positioned at any anchor point relative to each detection, allowing flexible placement for different visualization needs.

Common Use Cases¶

• Information Display on Detections: Add informative text labels showing class names, confidence scores, or other metadata directly on detected objects for quick identification and validation
• Model Performance Visualization: Display confidence scores or class predictions on detected objects to visualize model certainty, identify low-confidence detections, and validate model performance
• Object Tracking Visualization: Show tracker IDs on tracked objects to visualize object tracking across frames, monitor persistent object identities, or debug tracking algorithms
• Zone Analysis and Monitoring: Display "Time In Zone" labels on objects to visualize how long objects have been in specific zones for occupancy monitoring, dwell time analysis, or compliance tracking
• Spatial Information Display: Show object dimensions (center coordinates, width, height) or area measurements directly on detections for spatial analysis, measurement workflows, or quality control
• Professional Presentation and Reporting: Create clean, informative visualizations with labeled detections for reports, dashboards, or presentations that combine visual results with textual information

Connecting to Other Blocks¶

The annotated image from this block can be connected to:

• Other visualization blocks (e.g., Bounding Box Visualization, Polygon Visualization, Dot Visualization) to combine text labels with geometric annotations for comprehensive visualization
• Data storage blocks (e.g., Local File Sink, CSV Formatter, Roboflow Dataset Upload) to save annotated images with labels for documentation, reporting, or analysis
• Webhook blocks to send visualized results with labels to external systems, APIs, or web applications for display in dashboards or monitoring tools
• Notification blocks (e.g., Email Notification, Slack Notification) to send annotated images with labels as visual evidence in alerts or reports
• Video output blocks to create annotated video streams or recordings with labels for live monitoring, tracking visualization, or post-processing analysis

Type identifier¶

Use the following identifier in step "type" field: roboflow_core/label_visualization@v1to add the block as as step in your workflow.

Properties¶

The Refs column marks possibility to parametrise the property with dynamic values available in workflow runtime. See Bindings for more info.

Available Connections¶

Input and Output Bindings¶

The available connections depend on its binding kinds. Check what binding kinds Label Visualization in version v1 has.

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/label_visualization@v1",
    "image": "$inputs.image",
    "copy_image": true,
    "predictions": "$steps.object_detection_model.predictions",
    "color_palette": "DEFAULT",
    "palette_size": 10,
    "custom_colors": [
        "#FF0000",
        "#00FF00",
        "#0000FF"
    ],
    "color_axis": "CLASS",
    "text": "LABEL",
    "text_position": "CENTER",
    "text_color": "WHITE",
    "text_scale": 1.0,
    "text_thickness": 1,
    "text_padding": 10,
    "border_radius": 0
}