Remove noise or outlier pixels from an image

Question

This is my example image:

You can see in the bottom left corner and on the edge of the main structure, there is a lot of noise and outlier green pixels. I'm looking for a way to remove them. Currently, I have tried the following:

dst = cv2.fastNlMeansDenoisingColored(img_denoise,None,10,10,7,21)

and

dst = cv2.GaussianBlur(img,(7,7),0,borderType=cv2.BORDER_CONSTANT)

None of these methods seem to be removing these noisy pixels, are there any other methods or libraries that can achieve the result of denoising and removing these noisy pixels properly?

Answer 1

Try this:

import matplotlib.pyplot as plt

from skimage.restoration import (denoise_tv_chambolle, denoise_bilateral,
                                 denoise_wavelet, estimate_sigma)
from skimage import data, img_as_float
from skimage.util import random_noise
from skimage import io

img =  io.imread('img.png')


original = img_as_float(img)

sigma = 0.155
noisy = random_noise(original, var=sigma**2)

fig, ax = plt.subplots(nrows=1, ncols=2, figsize=(8, 5),
                       sharex=True, sharey=True)

plt.gray()

sigma_est = estimate_sigma(noisy, average_sigmas=True)

ax[0].imshow(noisy)
ax[0].axis('off')
ax[0].set_title('Noisy')
ax[1].imshow(denoise_tv_chambolle(noisy, weight=0.1))
ax[1].axis('off')
ax[1].set_title('Noise-removed')


fig.tight_layout()

plt.show()