Prerequisites

Before starting this lesson, you should be familiar with:

• Binarization

• Lookup tables

• Data types

Learning Objectives

After completing this lesson, learners should be able to:

• Understand how objects in images are represented as a label mask image.

• Apply connected component labeling to a binary image to create a label mask image.

Motivation

In bioimage analysis one very often wants to detect objects or specific regions in images. A typical workflow is to first categorise an image into in background and foreground regions, which can be represented as a binary image. The next step is a connected components labeling, where spatially connected regions of foreground pixels are assigned (labeled) as being part of one region (object).

Concept map

Example figure

Activity

1. 2D connected component labeling:
   • Open image xy_8bit_binary__nuclei.tif.
   • Create a label image by means of 4-connected connected components labeling.
   • Apply a multi-color LUT.
   • Repeat with 8-connected labeling and discuss the difference.
2. 3D connected component labeling:
   • Open image xyz_8bit_binary__spots.tif
   • Inspect the histogram of the label image and discuss what you can learn from it.

ImageJ MorpholibJ Macro & GUI

/**
 * 2D and 3D connected components labeling
 * 
 * Required update sites: 
 *   - IJPB-Plugins (MorpholibJ)
 */

run("Close All");

//  2D connected components labeling

// File › Open...
open("https://github.com/NEUBIAS/training-resources/raw/master/image_data/xy_8bit_binary__nuclei.tif");
// Image › Rename...
rename("binary");

// 4-connected

// Plugins › MorphoLibJ › Binary Images › Connected Components Labeling
run("Connected Components Labeling", "connectivity=4 type=[8 bits]");
// Image › Lookup Tables › glasbey_on_dark
run("glasbey_on_dark");
// Image › Adjust › Brightness/Contrast...
setMinAndMax(0, 20);

// 8-connected

selectWindow("binary");
run("Connected Components Labeling", "connectivity=8 type=[8 bits]");
run("glasbey_on_dark");
setMinAndMax(0, 20);

run("Tile");

// 3D connected components labeling (6-connected)

open("https://github.com/NEUBIAS/training-resources/raw/master/image_data/xyz_8bit_binary__spots.tif");
rename("binary");
run("Connected Components Labeling", "connectivity=6 type=[8 bits]");
run("glasbey_on_dark");
setMinAndMax(0, 255); // Note: surprisingly this determines the content of below histogram!
run("Histogram", "stack");

Exercises

ImageJ MorpholibJ Macro & GUI

• Open xy_8bit_binary__many_vesicles.tif
• Create a label mask image (beware the output data type, because there are quite many objects).
• Count the number of objects in the label mask image.

Solution

/**
 * Required update sites: 
 *   - IJPB-Plugins (MorpholibJ)
 */

run("Close All");

// File › Open...
open("https://github.com/NEUBIAS/training-resources/raw/master/image_data/xy_8bit_binary__many_vesicles.tif");
run("Connected Components Labeling", "connectivity=4 type=[16 bits]");
run("glasbey_on_dark");
run("Histogram");

Assessment

Fill in the blanks

Fill in the blanks, using these words: less, more, 6, 255, 4, more.

1. In 3D, pixels have _____ neighbors than in 2D.
2. 8-connected connectivity results in _____ objects than 4-connected connectivity.
3. In 3D, pixels have __ non-diagonal neighbors.
4. In 2D, pixels have __ non-diagonal neighbors.
5. A 8-bit label mask image can have maximally _____ objects.
6. The maximum value in a label mask image is equal to or _____ than the number of objects.

Solution

1. more
2. less
3. 6
4. 4
5. 255
6. less

Follow-up material

We recommend reading these modules next:

Learn more:

• Wikipedia: Connected components labeling