Skip to content

Mask Visualization

Class: MaskVisualizationBlockV1

Source: inference.core.workflows.core_steps.visualizations.mask.v1.MaskVisualizationBlockV1

Fill segmentation masks with semi-transparent color overlays, creating solid color fills that precisely follow the shape of detected objects from instance segmentation predictions.

How This Block Works

This block takes an image and instance segmentation predictions (with masks) and fills the mask regions with colored overlays. The block:

  1. Takes an image and instance segmentation predictions (with masks) as input
  2. Extracts segmentation masks for each detected object from the predictions
  3. Applies color styling to each mask based on the selected color palette, with colors assigned by class, index, or track ID
  4. Fills the mask regions with solid colors using Supervision's MaskAnnotator
  5. Blends the colored mask overlays with the original image using the specified opacity level
  6. Returns an annotated image where mask regions are filled with semi-transparent colors, while non-masked areas remain unchanged

The block fills the exact shape of each object's segmentation mask with colored overlays, creating solid color fills that precisely follow object boundaries. Unlike polygon visualization (which draws outlines) or bounding box visualizations (which use rectangular regions), mask visualization fills the entire mask area with color, providing clear visual indication of the segmented regions. The opacity parameter controls how transparent the mask overlay is, allowing you to see the original image details through the colored mask (lower opacity) or create more opaque fills (higher opacity) that better obscure background details. This block requires instance segmentation predictions with mask data, as it specifically works with segmentation masks to create precise, shape-following color fills.

Common Use Cases

  • Instance Segmentation Visualization: Visualize instance segmentation results by filling mask regions with colors to clearly show segmented objects, validate segmentation quality, or highlight detected regions in analysis workflows
  • Precise Shape-Following Overlays: Fill objects with colors that exactly match their segmented shapes, useful for applications requiring accurate region visualization such as medical imaging, quality control, or precise object identification
  • Mask-Based Object Highlighting: Highlight segmented objects with colored overlays that follow exact object boundaries, providing clear visual distinction between different objects or object classes
  • Segmentation Model Validation: Visualize segmentation predictions with colored mask fills to verify model performance, identify segmentation errors, or validate mask accuracy in model development and debugging workflows
  • Medical and Scientific Imaging: Display segmented regions in medical imaging, microscopy, or scientific analysis applications where colored mask overlays help visualize tissue boundaries, cell regions, or measured areas
  • Mask Quality Inspection: Use colored mask fills to inspect segmentation quality, verify mask boundaries, or identify areas where segmentation may need improvement in training data or model outputs

Connecting to Other Blocks

The annotated image from this block can be connected to:

  • Other visualization blocks (e.g., Label Visualization, Polygon Visualization, Bounding Box Visualization) to combine mask fills with additional annotations (labels, outlines) for comprehensive visualization
  • Data storage blocks (e.g., Local File Sink, CSV Formatter, Roboflow Dataset Upload) to save images with mask overlays for documentation, reporting, or analysis
  • Webhook blocks to send visualized results with mask fills 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 mask overlays as visual evidence in alerts or reports
  • Video output blocks to create annotated video streams or recordings with mask fills for live monitoring, segmentation visualization, or post-processing analysis

Type identifier

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

Properties

Name Type Description Refs
name str Enter a unique identifier for this step.. ❌
copy_image bool Enable this option to create a copy of the input image for visualization, preserving the original. Use this when stacking multiple visualizations.. ✅
color_palette str Select a color palette for the visualised elements.. ✅
palette_size int Specify the number of colors in the palette. This applies when using custom or Matplotlib palettes.. ✅
custom_colors List[str] Define a list of custom colors for bounding boxes in HEX format.. ✅
color_axis str Choose how bounding box colors are assigned.. ✅
opacity float Opacity of the mask overlay, ranging from 0.0 (fully transparent) to 1.0 (fully opaque). Controls the transparency of the colored mask fill. Lower values (e.g., 0.3-0.5) create semi-transparent overlays that allow original image details to show through, while higher values (e.g., 0.7-1.0) create more opaque fills that better obscure background details. Typical values range from 0.4 to 0.7 for balanced visualization where both the mask and underlying image are visible.. ✅

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

Available Connections

Compatible Blocks

Check what blocks you can connect to Mask Visualization in version v1.

Input and Output Bindings

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

Bindings

  • input

    • image (image): The image to visualize on..
    • copy_image (boolean): Enable this option to create a copy of the input image for visualization, preserving the original. Use this when stacking multiple visualizations..
    • predictions (Union[instance_segmentation_prediction, rle_instance_segmentation_prediction]): Instance segmentation predictions containing masks for detected objects. The block uses segmentation masks to create colored fills that precisely follow object boundaries. Requires instance segmentation model outputs with mask data..
    • color_palette (string): Select a color palette for the visualised elements..
    • palette_size (integer): Specify the number of colors in the palette. This applies when using custom or Matplotlib palettes..
    • custom_colors (list_of_values): Define a list of custom colors for bounding boxes in HEX format..
    • color_axis (string): Choose how bounding box colors are assigned..
    • opacity (float_zero_to_one): Opacity of the mask overlay, ranging from 0.0 (fully transparent) to 1.0 (fully opaque). Controls the transparency of the colored mask fill. Lower values (e.g., 0.3-0.5) create semi-transparent overlays that allow original image details to show through, while higher values (e.g., 0.7-1.0) create more opaque fills that better obscure background details. Typical values range from 0.4 to 0.7 for balanced visualization where both the mask and underlying image are visible..

  • output

    • image (image): Image in workflows.
Example JSON definition of step Mask Visualization in version v1 
{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/mask_visualization@v1",
    "image": "$inputs.image",
    "copy_image": true,
    "predictions": "$steps.instance_segmentation_model.predictions",
    "color_palette": "DEFAULT",
    "palette_size": 10,
    "custom_colors": [
        "#FF0000",
        "#00FF00",
        "#0000FF"
    ],
    "color_axis": "CLASS",
    "opacity": 0.5
}