def smoothing_bilateral(data,
sigma_space=15,
sigma_color=0.05,
pseudo_3D='True',
sliceId=2):
if data.ndim == 3 and pseudo_3D:
if sliceId == 2:
for idx in range(data.shape[2]):
temp = skifil.denoise_bilateral(data[:, :, idx],
sigma_range=sigma_color,
sigma_spatial=sigma_space)
# temp = skires.denoise_bilateral(data[:, :, idx], sigma_range=sigma_color, sigma_spatial=sigma_space)
data[:, :, idx] = (255 * temp).astype(np.uint8)
elif sliceId == 0:
for idx in range(data.shape[0]):
temp = skifil.denoise_bilateral(data[idx, :, :],
sigma_range=sigma_color,
sigma_spatial=sigma_space)
# temp = skires.denoise_bilateral(data[idx, :, :], sigma_range=sigma_color, sigma_spatial=sigma_space)
data[idx, :, :] = (255 * temp).astype(np.uint8)
else:
data = skifil.denoise_bilateral(data,
sigma_range=sigma_color,
sigma_spatial=sigma_space)
# data = skires.denoise_bilateral(data, sigma_range=sigma_color, sigma_spatial=sigma_space)
data = (255 * data).astype(np.uint8)
return data
def smoothing_bilateral(data, sigma_space=15, sigma_color=0.05, pseudo_3D='True', sliceId=2):
if data.ndim == 3 and pseudo_3D:
if sliceId == 2:
for idx in range(data.shape[2]):
temp = skifil.denoise_bilateral(data[:, :, idx], sigma_range=sigma_color, sigma_spatial=sigma_space)
data[idx, :, :] = (255 * temp).astype(np.uint8)
elif sliceId == 0:
for idx in range(data.shape[0]):
temp = skifil.denoise_bilateral(data[idx, :, :], sigma_range=sigma_color, sigma_spatial=sigma_space)
data[idx, :, :] = (255 * temp).astype(np.uint8)
else:
data = skifil.denoise_bilateral(data, sigma_range=sigma_color, sigma_spatial=sigma_space)
data = (255 * data).astype(np.uint8)
return data
def bilateral_blur_gray_image_nz(image_nz, image_shape, mask_nz, sigma_range, sigma_spatial):
""" Blur a masked grayscale image """
# deal with the mask -- set the unmasked entries to the average
orig_mean = np.mean(image_nz)
image = np.empty(image_shape[0:2])
image.fill(orig_mean)
image[mask_nz] = image_nz
blurred = denoise_bilateral(
image,
sigma_range=sigma_range,
sigma_spatial=sigma_spatial,
win_size=max(int(sigma_spatial * 2), 3),
mode='reflect',
)
blurred_nz = blurred[mask_nz]
# adjust to keep the mean the same
new_mean = np.mean(blurred_nz)
blurred_nz *= orig_mean / new_mean
return blurred_nz
