Binary Image Skeletonization

This notebook demonstrates basic binary image skeletonization using Python libraries.

Introduction

Skeletonization reduces binary objects in an image to their essential lines, preserving the structure and connectivity, allowing for further analysis of the shapes and structures.

# Import necessary libraries
import matplotlib.pyplot as plt
from skimage import data, filters, morphology, color

Load and preprocess the image

We’ll use a sample image from skimage.data and convert it to binary form for demonstration.

# Load sample image
image = data.horse()  # Sample binary image

# Apply threshold to convert to binary image
binary_image = image < filters.threshold_otsu(image)

# Plot original and binary images
fig, ax = plt.subplots(1, 2, figsize=(8, 4))
ax[0].imshow(image, cmap='gray')
ax[0].set_title('Original Image')
ax[1].imshow(binary_image, cmap='gray')
ax[1].set_title('Binary Image')
plt.show()

<__array_function__ internals>:180: RuntimeWarning: Converting input from bool to <class 'numpy.uint8'> for compatibility.

Perform Skeletonization

We’ll use the skeletonize function from skimage.morphology to perform skeletonization on the binary image.

# Perform skeletonization
skeleton = morphology.skeletonize(binary_image)

# Plot skeletonized image
plt.figure(figsize=(4, 4))
plt.imshow(skeleton, cmap='gray')
plt.title('Skeletonized Image')
plt.show()