Segmenting images

[haesleinhuepf]

I have an RGB image that looks like this:

I would like to segment and count the objects in the blue channel. I need Python code for this, ideally using scikit-image.

[haesleinhuepf]

^{This message was generated by git-bob (version: 0.3.0, model: gpt-4o-2024-08-06), an experimental AI-based assistant. It can make mistakes and has limitations. Check its messages carefully.}

To segment and count the objects in the blue channel, you can use the following Python code leveraging the scikit-image library:

import matplotlib.pyplot as plt
from skimage import io, filters, measure, morphology
from skimage.color import rgb2gray
from skimage.filters import threshold_otsu

# Load the image
image = io.imread('https://github.com/haesleinhuepf/git-bob-bioimage-analysis-example/blob/main/data/hela-cells-8bit.png?raw=true')

# Extract the blue channel
blue_channel = image[:, :, 2]

# Apply a threshold to separate the objects from the background
threshold_value = threshold_otsu(blue_channel)
binary_image = blue_channel > threshold_value

# Remove small objects and fill holes
cleaned_image = morphology.remove_small_objects(binary_image, min_size=30)
cleaned_image = morphology.remove_small_holes(cleaned_image, area_threshold=30)

# Label connected components
label_image = measure.label(cleaned_image)

# Count the objects
num_objects = label_image.max()

# Display results
plt.figure(figsize=(10, 5))

plt.subplot(1, 2, 1)
plt.title('Blue Channel')
plt.imshow(blue_channel, cmap='gray')

plt.subplot(1, 2, 2)
plt.title('Segmented Objects')
plt.imshow(label_image, cmap='nipy_spectral')

plt.suptitle(f'Number of objects detected: {num_objects}')
plt.tight_layout()
plt.show()

This code reads the image, extracts the blue channel, applies Otsu's threshold to create a binary image, cleans it by removing small objects and filling holes, labels the connected components, and finally counts the objects in the image.

[haesleinhuepf]

Awesome, please create a notebook for this with explanatory markdown cells in between to explain the workflow. Assume I'm a Python beginner.