Skip to content

Classification Label Visualization

Class: ClassificationLabelVisualizationBlockV1

Source: inference.core.workflows.core_steps.visualizations.classification_label.v1.ClassificationLabelVisualizationBlockV1

Visualize classification predictions as text labels positioned on images, automatically handling both single-label and multi-label classification formats with customizable styling and positioning.

How This Block Works

This block takes an image and classification predictions (for entire image classification, not object detection) and displays text labels showing the predicted class names and confidence scores. The block:

  1. Takes an image and classification predictions as input
  2. Automatically detects whether predictions are single-label (one class per image) or multi-label (multiple classes per image)
  3. For single-label predictions: selects the highest confidence prediction to display
  4. For multi-label predictions: formats and sorts all predicted classes by confidence score (highest first)
  5. Extracts label text based on the selected text option (class name, confidence score, or both)
  6. Positions labels on the image at the specified location (top, center, or bottom edges, with left/center/right alignment)
  7. Applies background color styling based on the selected color palette, with colors assigned by class
  8. Renders text labels with customizable text color, scale, thickness, padding, and border radius
  9. Returns an annotated image with classification labels overlaid on the original image

Unlike the regular Label Visualization block (which labels detected objects with bounding boxes), this block is designed for image-level classification where the entire image is classified into one or more categories. Labels are positioned at the edges or center of the image itself, not relative to object locations. For multi-label predictions, multiple labels are stacked vertically at the chosen position, making it easy to see all predicted classes and their confidence scores.

Common Use Cases

  • Image Classification Results Display: Visualize the predicted class and confidence score for classified images in applications like content moderation, product categorization, or medical image analysis
  • Multi-Class Probability Visualization: Display multiple predicted classes with their confidence scores for multi-label classification tasks, such as tagging images with multiple attributes, detecting multiple defects, or identifying multiple objects in scene classification
  • Model Performance Validation: Show classification predictions directly on images to validate model performance, verify correct classifications, and identify misclassifications during model development or testing
  • User Interface Integration: Create clean, professional displays of classification results for applications, dashboards, or mobile apps where users need to see what an image was classified as
  • Documentation and Reporting: Generate annotated images showing classification results for reports, documentation, or training data review to demonstrate model predictions
  • Quality Control Workflows: Display classification results on production images for quality control, content filtering, or automated categorization workflows where visual confirmation of predictions is needed

Connecting to Other Blocks

The annotated image from this block can be connected to:

  • Data storage blocks (e.g., Local File Sink, CSV Formatter, Roboflow Dataset Upload) to save annotated images with classification labels for documentation, reporting, or analysis
  • Webhook blocks to send visualized results with classification labels to external systems, APIs, or web applications for display in dashboards or classification monitoring tools
  • Notification blocks (e.g., Email Notification, Slack Notification) to send annotated images with classification labels as visual evidence in alerts or reports when specific classes are detected
  • Video output blocks to create annotated video streams or recordings with classification labels for live monitoring, real-time classification display, or post-processing analysis
  • Conditional logic blocks (e.g., Continue If) to route workflow execution based on classification results or confidence scores displayed in the labels

Type identifier

Use the following identifier in step "type" field: roboflow_core/classification_label_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.. ✅
text str Content to display in text labels. Options: 'Class' (class name only), 'Confidence' (confidence score only, formatted as decimal), or 'Class and Confidence' (both class name and confidence score).. ✅
text_position str Position for placing labels on the image. Options include: TOP (TOP_LEFT, TOP_CENTER, TOP_RIGHT), CENTER (CENTER_LEFT, CENTER, CENTER_RIGHT), or BOTTOM (BOTTOM_LEFT, BOTTOM_CENTER, BOTTOM_RIGHT). For multi-label predictions, labels are stacked vertically at the chosen position.. ✅
text_color str Color of the label text. Can be a color name (e.g., 'WHITE', 'BLACK') or color code in HEX format (e.g., '#FFFFFF') or RGB format (e.g., 'rgb(255, 255, 255)').. ✅
text_scale float Scale factor for text size. Higher values create larger text. Default is 1.0.. ✅
text_thickness int Thickness of text characters in pixels. Higher values create bolder, thicker text for better visibility.. ✅
text_padding int Padding around the text in pixels. Controls the spacing between the text and the label background border, and the spacing between multiple labels in multi-label predictions.. ✅
border_radius int Border radius of the label background in pixels. Set to 0 for square corners. Higher values create more rounded corners for a softer appearance.. ✅

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 Classification Label Visualization in version v1.

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds Classification Label 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 (classification_prediction): Classification predictions from a single-label or multi-label classification model. The block automatically detects the prediction format and handles both types accordingly..
    • 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..
    • text (string): Content to display in text labels. Options: 'Class' (class name only), 'Confidence' (confidence score only, formatted as decimal), or 'Class and Confidence' (both class name and confidence score)..
    • text_position (string): Position for placing labels on the image. Options include: TOP (TOP_LEFT, TOP_CENTER, TOP_RIGHT), CENTER (CENTER_LEFT, CENTER, CENTER_RIGHT), or BOTTOM (BOTTOM_LEFT, BOTTOM_CENTER, BOTTOM_RIGHT). For multi-label predictions, labels are stacked vertically at the chosen position..
    • text_color (string): Color of the label text. Can be a color name (e.g., 'WHITE', 'BLACK') or color code in HEX format (e.g., '#FFFFFF') or RGB format (e.g., 'rgb(255, 255, 255)')..
    • text_scale (float): Scale factor for text size. Higher values create larger text. Default is 1.0..
    • text_thickness (integer): Thickness of text characters in pixels. Higher values create bolder, thicker text for better visibility..
    • text_padding (integer): Padding around the text in pixels. Controls the spacing between the text and the label background border, and the spacing between multiple labels in multi-label predictions..
    • border_radius (integer): Border radius of the label background in pixels. Set to 0 for square corners. Higher values create more rounded corners for a softer appearance..

  • output

    • image (image): Image in workflows.
Example JSON definition of step Classification Label Visualization in version v1 
{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/classification_label_visualization@v1",
    "image": "$inputs.image",
    "copy_image": true,
    "predictions": "$steps.classification_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
}