def line_to_sparse(training_images,
sparse_shape,
rs,
group='PTS',
sd='draw_gaussian'):
ni, icp_transforms, reference_frame, n_landmarks, _n_align_points, _removed_transform, normalized_images, _rf_align, rs, [
align_t
] = rescale_images_to_reference_shape(training_images,
group,
rs,
sd='sample_gaussian')
path_to_db = '{}'.format(training_images[0].path.parent)
# Retrieve Results
mat = sio.loadmat('{}/result.mat'.format(path_to_db))
_u, _v = mat['u'], mat['v']
# Build Transforms
print(" - Build Transform")
transforms = []
for i in range(_u.shape[-1]):
transforms.append(OpticalFlowTransform(_u[:, :, i], _v[:, :, i]))
for i, n, t, norm, icpt, oft in zip(training_images, ni,
_removed_transform, normalized_images,
icp_transforms, transforms):
scale = AlignmentUniformScale(norm.landmarks[group].lms,
i.landmarks[group].lms)
pts = oft.apply(align_t.apply(sparse_shape))
i.landmarks['SPARSE'] = scale.apply(t.apply(_rf_align.apply(pts)))
return training_images
def holistic_sampling_from_scale(aam, scale=0.35):
r"""
Function that generates a sampling reference mask given a scale value.
Parameters
----------
aam : :map:`AAM` or subclass
The trained AAM.
scale : `float`, optional
The scale value.
Returns
-------
true_positions : `ndarray` of `bool`
The array that has ``True`` for the points of the reference shape that
belong to the new mask.
boolean_image : `menpo.image.BooleanImage`
The boolean image of the mask.
"""
reference = aam.appearance_models[0].mean()
scaled_reference = reference.rescale(scale)
t = AlignmentUniformScale(scaled_reference.landmarks['source'].lms,
reference.landmarks['source'].lms)
new_indices = np.require(np.round(t.apply(
scaled_reference.mask.true_indices())), dtype=np.int)
modified_mask = deepcopy(reference.mask.pixels)
modified_mask[:] = False
modified_mask[:, new_indices[:, 0], new_indices[:, 1]] = True
true_positions = np.nonzero(
modified_mask[:, reference.mask.mask].ravel())[0]
return true_positions, BooleanImage(modified_mask[0])
def holistic_sampling_from_scale(aam, scale=0.35):
reference = aam.appearance_models[0].mean()
scaled_reference = reference.rescale(scale)
t = AlignmentUniformScale(scaled_reference.landmarks['source'].lms,
reference.landmarks['source'].lms)
new_indices = np.require(np.round(t.apply(
scaled_reference.mask.true_indices())), dtype=np.int)
modified_mask = deepcopy(reference.mask.pixels)
modified_mask[:] = False
modified_mask[:, new_indices[:, 0], new_indices[:, 1]] = True
true_positions = np.nonzero(
modified_mask[:, reference.mask.mask].ravel())[0]
return true_positions, BooleanImage(modified_mask[0])
def holistic_sampling_from_scale(aam, scale=0.35):
reference = aam.appearance_models[0].mean()
scaled_reference = reference.rescale(scale)
t = AlignmentUniformScale(scaled_reference.landmarks['source'].lms,
reference.landmarks['source'].lms)
new_indices = np.require(np.round(
t.apply(scaled_reference.mask.true_indices())),
dtype=np.int)
modified_mask = deepcopy(reference.mask.pixels)
modified_mask[:] = False
modified_mask[:, new_indices[:, 0], new_indices[:, 1]] = True
true_positions = np.nonzero(modified_mask[:,
reference.mask.mask].ravel())[0]
return true_positions, BooleanImage(modified_mask[0])
def holistic_sampling_from_scale(aam, scale=0.35):
r"""
Function that generates a sampling reference mask given a scale value.
Parameters
----------
aam : :map:`AAM` or subclass
The trained AAM.
scale : `float`, optional
The scale value.
Returns
-------
true_positions : `ndarray` of `bool`
The array that has ``True`` for the points of the reference shape that
belong to the new mask.
boolean_image : `menpo.image.BooleanImage`
The boolean image of the mask.
"""
reference = aam.appearance_models[0].mean()
scaled_reference = reference.rescale(scale)
t = AlignmentUniformScale(scaled_reference.landmarks['source'],
reference.landmarks['source'])
new_indices = np.require(np.round(
t.apply(scaled_reference.mask.true_indices())),
dtype=np.int)
modified_mask = deepcopy(reference.mask.pixels)
modified_mask[:] = False
modified_mask[:, new_indices[:, 0], new_indices[:, 1]] = True
true_positions = np.nonzero(modified_mask[:,
reference.mask.mask].ravel())[0]
return true_positions, BooleanImage(modified_mask[0])
