Get startedGet started for free

Smoothing

Smoothing can improve the signal-to-noise ratio of your image by blurring out small variations in intensity. The Gaussian filter is excellent for this: it is a circular (or spherical) smoothing kernel that weights nearby pixels higher than distant ones.

The width of the distribution is controlled by the sigma argument, with higher values leading to larger smoothing effects.

For this exercise, test the effects of applying Gaussian filters to the foot x-ray before creating a bone mask.

This exercise is part of the course

Biomedical Image Analysis in Python

View Course

Exercise instructions

  • Convolve im with Gaussian filters of size sigma=1 and sigma=3.
  • Plot the "bone masks" of im, im_s1, and im_s3 (i.e., where intensities are greater than or equal to 145).

Hands-on interactive exercise

Have a go at this exercise by completing this sample code.

# Smooth "im" with Gaussian filters
im_s1 = ndi.gaussian_filter(____, sigma=____)
im_s3 = ____

# Draw bone masks of each image
fig, axes = plt.subplots(1,3)
axes[0].imshow(____ >= 145)
axes[1].imshow(____)
____
format_and_render_plot()
Edit and Run Code