def test_richardson_lucy_filtered():
test_img_astro = rgb2gray(astronaut())
psf = np.ones((5, 5)) / 25
data = convolve2d(test_img_astro, psf, 'same')
deconvolved = restoration.richardson_lucy(data,
psf,
5,
filter_epsilon=1e-6)
path = image_fetcher.fetch('restoration/tests/astronaut_rl.npy')
np.testing.assert_allclose(deconvolved,
np.load(path),
rtol=1e-3,
atol=1e-8)
def test_richardson_lucy_filtered():
from skimage.data import image_fetcher
test_img_astro = rgb2gray(astronaut())
psf = cp.ones((5, 5)) / 25
data = cp.asarray(convolve2d(test_img_astro.get(), psf.get(), "same"))
deconvolved = restoration.richardson_lucy(data,
psf,
5,
filter_epsilon=1e-6)
path = image_fetcher.fetch("restoration/tests/astronaut_rl.npy")
cp.testing.assert_allclose(deconvolved,
np.load(path),
rtol=1e-3,
atol=1e-6)
def test_richardson_lucy_filtered(dtype_image, dtype_psf):
if dtype_image == np.float64:
atol = 1e-8
else:
atol = 1e-5
test_img_astro = rgb2gray(astronaut())
psf = np.ones((5, 5), dtype=dtype_psf) / 25
data = convolve2d(test_img_astro, psf, 'same')
data = data.astype(dtype_image, copy=False)
deconvolved = restoration.richardson_lucy(data,
psf,
5,
filter_epsilon=1e-6)
assert deconvolved.dtype == data.dtype
path = image_fetcher.fetch('restoration/tests/astronaut_rl.npy')
np.testing.assert_allclose(deconvolved,
np.load(path),
rtol=1e-3,
atol=atol)
def single_tiff():
return [image_fetcher.fetch('data/multipage.tif')]
def irregular_images():
return [image_fetcher.fetch(f'data/{n}.png') for n in ('camera', 'coins')]
def single_png():
return [image_fetcher.fetch('data/camera.png')]
def rgb_png():
return [image_fetcher.fetch('data/astronaut.png')]
def two_pngs():
return [image_fetcher.fetch(f'data/{n}.png') for n in ('moon', 'camera')]
import matplotlib.pyplot as plt
import matplotlib.patches as patches
from matplotlib import cm, colors
from mpl_toolkits.mplot3d import Axes3D
import numpy as np
from skimage import exposure
import imageio as io
# Prepare data and apply histogram equalization
# Try using skimage.data.image_fetcher for cached data loading,
# otherwise fall back to reading the data from url
from skimage.data import image_fetcher
try:
path = image_fetcher.fetch('data/cells.tif')
im_orig = io.volread(path)
except:
im_orig = io.volread('https://github.com/scikit-image/'
'skimage-tutorials/blob/master/'
'images/cells.tif?raw=True')
# Reorder axis order from (z, y, x) to (x, y, z)
im_orig = im_orig.transpose()
# Rescale image data to range [0, 1]
im_orig = np.clip(im_orig, np.percentile(im_orig, 5),
np.percentile(im_orig, 95))
im_orig = (im_orig - im_orig.min()) / (im_orig.max() - im_orig.min())
# Degrade image by applying exponential intensity decay along x
(2006) "A lentiviral RNAi library for human and mouse genes applied to
an arrayed viral high-content screen" Cell, 124(6):1283-98.
PMID: 16564017
:DOI:`10.1016/j.cell.2006.01.040`
"""
import matplotlib.pyplot as plt
import numpy as np
from scipy import ndimage as ndi
from skimage import (color, feature, filters, io, measure, morphology,
segmentation, util)
from skimage.data import image_fetcher
path = image_fetcher.fetch('data/mitosis.tif')
image = io.imread(path)
fig, ax = plt.subplots()
ax.imshow(image, cmap='gray')
ax.set_title('Microscopy image of human cells stained for nuclear DNA')
plt.show()
#####################################################################
# We can see many cell nuclei on a dark background. Most of them are smooth
# and have an elliptical shape. However, we can distinguish some brighter
# spots corresponding to nuclei undergoing
# `mitosis <https://en.wikipedia.org/wiki/Mitosis>`_ (cell division).
#####################################################################
# Another way of visualizing a greyscale image is contour plotting:
