We already saw how to to obtain the (approximate) original image from the blurred image (with a known blur kernel) using the inverse filter in the last section. Another important task in image processing is the removal of noise from a corrupted signal. This is also known as image restoration. The following code block shows how the scikit-image restoration module's unsupervised Wiener filter can be used for image denoising with deconvolution:
from skimage import color, data, restorationim = color.rgb2gray(imread('../images/elephant_g.jpg'))from scipy.signal import convolve2d as conv2n = 7psf = np.ones((n, n)) / n**2im1 = conv2(im, psf, 'same')im1 += 0.1 * astro.std() * np.random.standard_normal(im.shape) ...
