def test_build_gaussian_pyramid_rgb():
rows, cols, dim = image.shape
pyramid = pyramids.pyramid_gaussian(image, downscale=2,
multichannel=True)
for layer, out in enumerate(pyramid):
layer_shape = (rows / 2 ** layer, cols / 2 ** layer, dim)
assert_array_equal(out.shape, layer_shape)
def test_build_gaussian_pyramid_gray():
rows, cols = image_gray.shape
pyramid = pyramids.pyramid_gaussian(image_gray, downscale=2,
multichannel=False)
for layer, out in enumerate(pyramid):
layer_shape = (rows / 2 ** layer, cols / 2 ** layer)
assert_array_equal(out.shape, layer_shape)
def test_build_gaussian_pyramid_gray():
rows, cols = image_gray.shape
with expected_warnings(['The default multichannel']):
pyramid = pyramids.pyramid_gaussian(image_gray, downscale=2)
for layer, out in enumerate(pyramid):
layer_shape = (rows / 2**layer, cols / 2**layer)
assert_array_equal(out.shape, layer_shape)
def test_build_gaussian_pyramid_rgb_deprecated_multichannel():
rows, cols, dim = image.shape
with expected_warnings(["`multichannel` is a deprecated argument"]):
pyramid = pyramids.pyramid_gaussian(image, downscale=2,
multichannel=True)
for layer, out in enumerate(pyramid):
layer_shape = (rows / 2 ** layer, cols / 2 ** layer, dim)
assert_array_equal(out.shape, layer_shape)
# repeat prior test, but check for positional multichannel warning
with expected_warnings(["Providing the `multichannel` argument"]):
pyramid = pyramids.pyramid_gaussian(image, -1, 2, None, 1, 'reflect',
0, True)
for layer, out in enumerate(pyramid):
layer_shape = (rows / 2 ** layer, cols / 2 ** layer, dim)
assert_array_equal(out.shape, layer_shape)
def test_build_gaussian_pyramid_gray():
rows, cols = image_gray.shape
with expected_warnings(['The default multichannel']):
pyramid = pyramids.pyramid_gaussian(image_gray, downscale=2)
for layer, out in enumerate(pyramid):
layer_shape = (rows / 2 ** layer, cols / 2 ** layer)
assert_array_equal(out.shape, layer_shape)
def test_build_gaussian_pyramid_nd():
for ndim in [1, 2, 3, 4]:
img = np.random.randn(*((8, ) * ndim))
original_shape = np.asarray(img.shape)
pyramid = pyramids.pyramid_gaussian(img, downscale=2,
multichannel=False)
for layer, out in enumerate(pyramid):
layer_shape = original_shape / 2 ** layer
assert_array_equal(out.shape, layer_shape)
def test_build_gaussian_pyramid_nd():
for ndim in [1, 2, 3, 4]:
img = np.random.randn(*((8, ) * ndim))
original_shape = np.asarray(img.shape)
pyramid = pyramids.pyramid_gaussian(img, downscale=2,
multichannel=False)
for layer, out in enumerate(pyramid):
layer_shape = original_shape / 2 ** layer
assert_array_equal(out.shape, layer_shape)
def test_build_gaussian_pyramid_rgb(channel_axis):
image = data.astronaut()
rows, cols, dim = image.shape
image = np.moveaxis(image, source=-1, destination=channel_axis)
pyramid = pyramids.pyramid_gaussian(image,
downscale=2,
channel_axis=channel_axis)
for layer, out in enumerate(pyramid):
layer_shape = [rows / 2**layer, cols / 2**layer]
layer_shape.insert(channel_axis % image.ndim, dim)
assert out.shape == tuple(layer_shape)
def test_build_gaussian_pyramid_gray():
rows, cols = image_gray.shape
pyramid = pyramids.pyramid_gaussian(image_gray, downscale=2)
for layer, out in enumerate(pyramid):
layer_shape = (rows / 2 ** layer, cols / 2 ** layer)
assert_array_equal(out.shape, layer_shape)
def test_build_gaussian_pyramid_gray_defaults():
rows, cols = image_gray.shape
pyramid = pyramids.pyramid_gaussian(image_gray)
for layer, out in enumerate(pyramid):
layer_shape = (rows / 2**layer, cols / 2**layer)
assert_array_equal(out.shape, layer_shape)
def test_pyramid_gaussian_dtype_support(dtype, expected):
img = np.random.randn(32, 8).astype(dtype)
pyramid = pyramids.pyramid_gaussian(img)
assert np.all([im.dtype == expected for im in pyramid])
# Main function
if __name__ == "__main__":
# Load image and convert to grayscale
visual_attention = imread(
"C:/Users/Moritz Lahann/Desktop/STUDIUM/Module IAS/Computer Vision/cv_exercises/cv_ex02_03/visual_attention.png",
as_gray=True,
)
fig, ax = plt.subplots()
ax.imshow(visual_attention)
plt.title("Input image")
plt.show()
# Calculate center pyramid
center_pyramid = tuple(pyramid_gaussian(visual_attention, max_layer=4, sigma=9))
# Visualize center pyramid
fig = show_pyramid(center_pyramid)
fig.suptitle("Center Pyramid")
plt.show()
# Calculate surround pyramid
surround_pyramid = tuple(pyramid_gaussian(visual_attention, max_layer=4, sigma=16))
# Visualize surround pyramid
fig = show_pyramid(surround_pyramid)
fig.suptitle("Surround Pyramid")
plt.show()
# Calculate on-off contrast pyramid
