def test_integral_descriptors():
np.random.seed(22)
f = np.random.rand(16,16)*230
f = f.astype(np.uint8)
f = surf.integral(f)
points = surf.interest_points(f, is_integral=True)
surf.descriptors(f.astype(np.int32), points, is_integral=True)
def test_integral_descriptors():
np.random.seed(22)
f = np.random.rand(16, 16) * 230
f = f.astype(np.uint8)
f = surf.integral(f)
points = surf.interest_points(f, is_integral=True)
surf.descriptors(f.astype(np.int32), points, is_integral=True)
def test_descriptors_descriptor_only():
np.random.seed(22)
f = np.random.rand(256, 256) * 230
f = f.astype(np.uint8)
points = surf.interest_points(f, 6, 24, 1)
full = surf.descriptors(f, points)
only = surf.descriptors(f, points, descriptor_only=True)
assert full.size > only.size
def test_descriptors_descriptor_only():
np.random.seed(22)
f = np.random.rand(256,256)*230
f = f.astype(np.uint8)
points = surf.interest_points(f, 6, 24, 1)
full = surf.descriptors(f, points)
only = surf.descriptors(f, points, descriptor_only=True)
assert full.size > only.size
def surf_ref(f, ref):
fi = surf.integral(f.copy())
points = surf.interest_points(fi, 6, 24, 1, max_points=1024, is_integral=True)
descs = surf.descriptors(fi, points, is_integral=True, descriptor_only=True)
if ref is None:
return descs
ri = surf.integral(ref.copy())
descsref = surf.descriptors(ri, points, is_integral=True, descriptor_only=True)
return np.hstack( (descs, descsref) )
def surfref(im):
from mahotas.features import surf
import numpy as np
spoints = surf.interest_points(im.get('protein'), max_points=1024)
return np.hstack([
surf.descriptors(im.get('protein'), spoints, descriptor_only=True),
surf.descriptors(im.get('dna'), spoints, descriptor_only=True),
surf.descriptors(im.get('er'), spoints, descriptor_only=True),
surf.descriptors(im.get('tubulin'), spoints, descriptor_only=True),
])
def _extract_features(self, X, candidate):
y, x, radius = int(candidate[0]), int(candidate[1]), candidate[2]
padded_radius = int(self.padding * radius)
# compute the coordinate of the patch to select
x_min = x - padded_radius
x_min = x_min if x_min < 0 else 0
y_min = y - padded_radius
y_min = y_min if y_min < 0 else 0
x_max = x + padded_radius
x_max = x_max if x_max > X.shape[0] else X.shape[0] - 1
y_max = y + padded_radius
y_max = y_max if y_max > X.shape[1] else X.shape[1] - 1
patch = X[y_min:y_max, x_min:x_max]
# compute Zernike moments
zernike = zernike_moments(patch, radius)
# compute SURF descriptor
keypoint = np.array([[y, x, 1, 0.1, 1]])
surf_descriptor = surf.descriptors(patch, keypoint,
is_integral=False).ravel()
if not surf_descriptor.size:
surf_descriptor = np.zeros((70, ))
return np.hstack((zernike, surf_descriptor))
def _extract_features(self, X, candidate):
y, x, radius = int(candidate[0]), int(candidate[1]), candidate[2]
padded_radius = int(self.padding * radius)
# compute the coordinate of the patch to select
x_min = max(x - padded_radius, 0)
y_min = max(y - padded_radius, 0)
x_max = min(x + padded_radius, X.shape[0] - 1)
y_max = min(y + padded_radius, X.shape[1] - 1)
patch = X[y_min:y_max, x_min:x_max]
# compute Zernike moments
zernike = zernike_moments(patch, radius)
# compute SURF descriptor
scale_surf = radius / self.min_radius
keypoint = np.array([[y, x, scale_surf, 0.1, 1]])
surf_descriptor = surf.descriptors(X, keypoint,
is_integral=False).ravel()
if not surf_descriptor.size:
surf_descriptor = np.zeros((70, ))
return np.hstack((zernike, surf_descriptor))
def _extract_features(self, X, candidate):
row, col, radius = int(candidate[0]), int(candidate[1]), int(
candidate[2])
padded_radius = int(self.padding * radius)
# compute the coordinate of the patch to select
col_min = max(col - padded_radius, 0)
row_min = max(row - padded_radius, 0)
col_max = min(col + padded_radius, X.shape[0] - 1)
row_max = min(row + padded_radius, X.shape[1] - 1)
# extract patch
patch = X[row_min:row_max, col_min:col_max]
resized_patch = resize(patch, (self.resized, self.resized))
# compute Zernike moments
zernike = zernike_moments(patch, radius)
# compute surf descriptors
scale_surf = 2 * self.padding * radius / 20
keypoint = np.array([[row, col, scale_surf, 0.1, 1]])
surf_descriptor = surf.descriptors(X, keypoint,
is_integral=False).ravel()
if not surf_descriptor.size:
surf_descriptor = np.zeros((70,))
# compute haar-like features
haar_features = extract_feature_image(resized_patch, self.feature_type,
self.feature_coord)
return np.hstack((zernike, surf_descriptor, haar_features))
def test_interest_points_descriptors():
np.random.seed(22)
f = np.random.rand(256, 256) * 230
f = f.astype(np.uint8)
fi = surf.integral(f)
spoints = surf.surf(f, 6, 24, 1)
for arr, is_integral in zip([f, fi], [False, True]):
points = surf.interest_points(arr, 6, 24, 1, is_integral=is_integral)
points = list(points)
points.sort(key=(lambda p: -p[3]))
points = np.array(points, dtype=np.float64)
descs = surf.descriptors(arr, points, is_integral)
assert np.all(descs[:len(spoints)] == spoints)
def test_interest_points_descriptors():
np.random.seed(22)
f = np.random.rand(256,256)*230
f = f.astype(np.uint8)
fi = surf.integral(f)
spoints = surf.surf(f, 6, 24, 1)
for arr, is_integral in zip([f,fi], [False, True]):
points = surf.interest_points(arr, 6, 24, 1, is_integral=is_integral)
points = list(points)
points.sort(key=(lambda p: -p[3]))
points = np.array(points, dtype=np.float64)
descs = surf.descriptors(arr, points, is_integral)
assert np.all(descs[:len(spoints)] == spoints)
sigmaval = 30
blobs = feature.blob_doh(img, min_sigma=sigmaval, max_sigma=sigmaval)
passpoints = np.zeros((blobs.shape[0], 5))
for i in range(blobs.shape[0]):
passpoints[i,
0], passpoints[i,
1], passpoints[i,
2] = blobs[i,
0], blobs[i,
1], blobs[i,
2]
desc = surf.descriptors(img,
passpoints,
is_integral=False,
descriptor_only=False)
print passpoints
print desc
#print blobs
#print passpoints
for blob in blobs:
y, x, r = blob
scatter(x, y, c='r', s=sigmaval, marker='o')
implot = imshow(img)
show()
def surf(im):
from mahotas.features import surf
import numpy as np
spoints = surf.interest_points(im.get('protein'), max_points=1024)
return surf.descriptors(im.get('protein'), spoints, descriptor_only=True)
