I am using skimage to perfom some random noise to my images in order to perform data augmentation, but while im doing it im adding noise to the white background. How could I exclude the background from the computation?
The following lines of code are used for gaussian noise
def save_noisy_image(img, name):
img = img.view(img.size(0), 3, 180, 180)
save_image(img, name)
def gaussian_noise():
for data in dataloader:
newuuid = str(uuid.uuid4())
img, _ = data['image'], data['labels']
gauss_img = torch.tensor(random_noise(img, mode='gaussian', mean=0, var=0.05, clip=True))
save_noisy_image(gauss_img, "/tmp/tests/"+newuuid+".png")
break
gaussian_noise()
Here is an example of a result image