def densereg_face_iterator(istraining, db='helen'):
database_path = Path(
'/vol/atlas/homes/yz4009/databases/DenseReg/FaceRegDataset') / db
landmarks_path = Path('/vol/atlas/databases') / db
image_folder = 'Images_Resized'
uv_folder = 'Labels_Resized'
z_folder = 'Labels_Resized'
if istraining == 1:
database_path = database_path / 'trainset'
landmarks_path = landmarks_path / 'trainset'
elif istraining == 0:
database_path = database_path / 'testset'
landmarks_path = landmarks_path / 'testset'
for pimg in print_progress(
mio.import_images(database_path / image_folder / image_folder)):
image_name = pimg.path.stem
# load iuv data
labels = sio.loadmat(
str(database_path / uv_folder / uv_folder /
('%s.mat' % image_name)))
iuv = Image(
np.stack([(labels['LabelsH_resized'] >= 0).astype(np.float32),
labels['LabelsH_resized'],
labels['LabelsV_resized']]).clip(0, 1))
# load lms data
try:
orig_image = mio.import_image(landmarks_path /
('%s.jpg' % image_name))
except:
orig_image = mio.import_image(landmarks_path /
('%s.png' % image_name))
orig_image = orig_image.resize(pimg.shape)
pimg.landmarks['JOINT'] = orig_image.landmarks['PTS']
pimg_data = utils.crop_image_bounding_box(
pimg, pimg.landmarks['JOINT'].bounding_box(), [384, 384], base=256)
pimg = pimg_data[0]
iuv_data = utils.crop_image_bounding_box(
iuv, pimg.landmarks['JOINT'].bounding_box(), [384, 384], base=256)
iuv = iuv_data[0]
yield {
'image': pimg,
'iuv': iuv,
'visible_pts': np.array(list(range(68))),
'marked_index': np.array(list(range(68)))
}
def blue_peter():
import menpo.io as mio
import h5it
from menpo.visualize.image import glyph
from menpo.feature import hog
import matplotlib.pyplot as plt
# Loading the pre-built HOG AAM
import cPickle as pickle
with open('/Users/pts08/hog_lfpw_aam.pkl', 'rb') as f:
hog_aam = pickle.load(f)
#hog_aam = h5it.load('/Users/pts08/sparse_hog.hdf5')
print('Here is one I made earlier!')
bp = mio.import_image('blue_peter.jpg')
hog_blue_peter = hog(bp)
plt.figure()
plt.subplot(121)
bp.view()
plt.axis('off')
plt.gcf().set_size_inches(11, 11)
plt.title('RGB')
plt.subplot(122)
glyph(hog_blue_peter).view()
plt.axis('off')
plt.gcf().set_size_inches(11, 11)
plt.title('HOG')
return hog_aam
def save_faces(emotions, face_detector, fitter):
for element in emotions:
TEST_IMG_PATH = "/Users/joanna_frankiewicz/Desktop/Database/FaceDB_Emotions/images/"+element
for filename in os.listdir(TEST_IMG_PATH):
if filename.endswith(".jpg"):
img_path = TEST_IMG_PATH+"/"+filename
test_img = mio.import_image(img_path)
try:
test_face_bb = face_2_pointcloud(face_detector(test_img))
fitting_result = fitter.fit_from_bb(test_img, test_face_bb, max_iters=25)
# get points of bounding_box. left top and bottom right
p_left_top = fitting_result.final_shape.bounds()[0]
p_right_bottom = fitting_result.final_shape.bounds()[1]
image_width, image_height = test_img.width, test_img.height
# clip value to image range
p_left_top[0] = np.clip([p_left_top[0]], 0, image_height)[0]
p_left_top[1] = np.clip([p_left_top[1]], 0, image_width)[0]
p_right_bottom[0] = np.clip([p_right_bottom[0]], 0, image_height)[0]
p_right_bottom[1] = np.clip([p_right_bottom[1]], 0, image_width)[0]
img_tmp = test_img.pixels.squeeze()[int(p_left_top[0]):int(p_right_bottom[0]), int(p_left_top[1]):int(p_right_bottom[1])]*255
img_tmp = cv2.resize(img_tmp, (144, 144))
result = cv2.imwrite("/Users/joanna_frankiewicz/Desktop/Database/FaceDB_Emotions/result/"+element+"/"+filename, img_tmp)
except:
print('Invalid shape of image')
def from_menpo(cls, data_dir, verbose=True):
"""
Create class instance from directory of menpo files
Parameters
----------
data_dir: string
path to data directory
verbose: bool
whether or not to print current progress
Returns
-------
class instance
"""
if verbose:
print("Loading data from %s" % data_dir)
wrapper_fn = tqdm
else:
def linear_wrapper(x):
return x
wrapper_fn = linear_wrapper
img_paths = list(mio.image_paths(data_dir))
samples = []
for _img in wrapper_fn(img_paths):
samples.append(
SingleImage.from_menpo(mio.import_image(_img), img_file=_img))
return cls(samples=samples)
def dlib_landmark(img_path, img_dir):
detector = dlib.get_frontal_face_detector()
predictor_68_point_model = face_recognition_models.pose_predictor_model_location()
predictor = dlib.shape_predictor(predictor_68_point_model)
# load the input image, resize it, and convert it to grayscale
image = cv2.imread(img_path)
# image = imutils.resize(image, width=500)
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
# detect faces in the grayscale image
rects = detector(gray, 1)
# loop over the face detections
shapes = []
for (i, rect) in enumerate(rects):
shape = predictor(gray, rect)
shape = face_utils.shape_to_np(shape)
for (x, y) in shape:
cv2.circle(image, (x, y), 5, (0, 0, 255), -1)
# show the output image with the face detections + facial landmarks
plt.imshow(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
plt.show()
shape = swap_np_columns(shape)
shapes.append(shape)
if i == 0:
pts_file = img_dir + img_path.split('/')[-1].split('.')[0] + '.pts'
print(pts_file)
mio.export_landmark_file(menpo.shape.PointCloud(shape),
pts_file,
overwrite=True)
mio_img = mio.import_image(img_path)
mio_img.view_landmarks()
plt.show()
return shapes
def image(self):
if self._image is None:
image = mio.import_image(self._image_path)
image.crop_to_landmarks_proportion_inplace(0.5)
self._image = image
return self._image
def test(fitter, mi0=28, mi1=24):
# error_list = []
# error_dict = {}
name_list, valid_name_dir, red_dot_location_dir, ground_truth_dir = get_test_path(
)
for name in name_list:
image_road = os.path.join(valid_name_dir, name + '.jpg')
image = mio.import_image(image_road)
# resolution = image.shape[1]
txt_path = os.path.join(red_dot_location_dir, name + '.txt')
bboxes = get_bbx(txt_path)
# txt_path = os.path.join(ground_truth_dir, name + '.txt')
# ground_truth_np = get_coordinate(txt_path)
result = fitter.fit_from_bb(image, bboxes, max_iters=[mi0, mi1])
pre_landmarks = result.final_shape.as_vector().copy()
pre_landmarks.resize((35, 2))
pre_landmarks[:, [0, 1]] = pre_landmarks[:, [1, 0]]
root = R"C:\Users\chen\Desktop\test_pre_label"
save_path = os.path.join(root, name + '.txt')
np.savetxt(save_path,
pre_landmarks,
fmt='%d',
delimiter=',',
newline='\r\n')
def image(self):
if self._image is None:
image = mio.import_image(self._image_path)
image.crop_to_landmarks_proportion_inplace(0.5)
self._image = image
return self._image
def get_pts_for_mirror_image(file_path, verbose=False):
for image_file_name in mio.image_paths(file_path):
if os.path.exists(
os.path.splitext(str(image_file_name))[0] +
'_mirror.jpg') and not os.path.exists(
os.path.splitext(str(image_file_name))[0] + '_mirror.pts'):
img = mio.import_image(image_file_name).mirror()
mirrored_points = []
for i in range(68):
unmirrored_points = img.landmarks.get('PTS').lms.points
mirrored_points.append([
unmirrored_points[mirror_transfrom[i + 1] - 1][1],
unmirrored_points[mirror_transfrom[i + 1] - 1][0]
])
if verbose:
print('Adding mirror pts for: ' + image_file_name)
with open(
os.path.splitext(str(image_file_name))[0] + '_mirror.pts',
'w') as f:
f.write('version: 1\nn_points: %d\n{\n' %
(len(mirrored_points)))
for point in mirrored_points:
f.write('%f %f\n' % (point[0], point[1]))
f.write('}')
def create_from_pkl_img(tfrecord_dir, image_dir, pickle_dir, shuffle):
print('Loading images from "%s"' % image_dir)
image_filenames = sorted(glob.glob(os.path.join(image_dir, '*')))
pickle_filenames = sorted(glob.glob(os.path.join(pickle_dir, '*')))
if len(image_filenames) == 0:
error('No input images found')
# good_ids = mio.import_pickle('/vol/construct3dmm/visualizations/nicp/mein3d/good_ids.pkl')
img = mio.import_pickle(pickle_filenames[0])
resolution = img.shape[2]
channels = img.shape[0] if img.ndim == 3 else 1
if img.shape[1] != resolution:
error('Input images must have the same width and height')
if resolution != 2**int(np.floor(np.log2(resolution))):
error('Input image resolution must be a power-of-two')
if channels not in [1, 3]:
error('Input images must be stored as RGB or grayscale')
with TFRecordExporter(tfrecord_dir, len(image_filenames)) as tfr:
order = tfr.choose_shuffled_order() if shuffle else np.arange(
len(image_filenames))
for idx in range(order.size):
img = mio.import_image(image_filenames[order[idx]]).pixels.astype(
np.float32) * 2 - 1
pkl = mio.import_pickle(pickle_filenames[order[idx]]).astype(
np.float32)
# pkl[0, :, :] = scipy.ndimage.gaussian_filter(pkl[0, :, :], 2)
# pkl[1, :, :] = scipy.ndimage.gaussian_filter(pkl[1, :, :], 2)
# pkl[2, :, :] = scipy.ndimage.gaussian_filter(pkl[2, :, :], 2)
# img_resized = np.stack((cv2.resize(img[0],dsize=(256,256)),cv2.resize(img[1],dsize=(256,256)),cv2.resize(img[2],dsize=(256,256))))
tfr.add_both(np.concatenate([img, pkl]))
def test():
img = mio.import_image(
'/home/sean/workplace/221/py-R-FCN-test/data/DB/face/300-w_face/otherDB/aflw-full/testset/0_image00002_1.jpg'
)
if img.n_channels != 1:
img = img.as_greyscale()
img.landmarks['face'] = mio.import_landmark_file(
'/home/sean/workplace/221/py-R-FCN-test/data/DB/face/300-w_face/temp/indoor_001.pts'
)
# objects return copies rather than mutating self, so we can chain calls
img = (img.crop_to_landmarks(
group='face',
boundary=10).rescale_landmarks_to_diagonal_range(100, group='face'))
# now lets take an image feature...
img = fast_dsift(img)
# ...and extract the vector of pixels contained in the
# convex hull of the face...
vector = img.as_masked().constrain_mask_to_landmarks(
group='face').as_vector()
print(type(vector), vector.shape)
def _preprocess(self, idx):
name, *lms5pt = self.detection.loc[idx]
lms5pt = PointCloud(np.array(lms5pt).reshape([-1,2])[:,::-1])
img = mio.import_image((self.image_path/name).with_suffix('.jpg'))
cimg, _, _ = dm.utils.crop_image_bounding_box(img, lms5pt.bounding_box(), [112, 112], base=186)
return cimg.pixels_with_channels_at_back() * 2 - 1
def test_AAM(fitter, images):
for image in images:
image = mio.import_image(image)
image = image.as_greyscale()
initial_bbox = image.landmarks['PTS'].bounding_box()
gt_shape = image.landmarks['PTS'].lms
initial_shape = noisy_shape_from_bounding_box(gt_shape,
gt_shape.bounding_box())
image.landmarks['boundingbox'] = initial_bbox
image.landmarks['init_shape'] = initial_shape
image.view_landmarks(group='boundingbox',
line_colour='red',
render_markers=False,
line_width=4)
image.view_landmarks(group='init_shape')
# fit image
result = fitter.fit_from_bb(image,
initial_bbox,
max_iters=[15, 5],
gt_shape=image.landmarks['PTS'].lms)
# print result
print(result)
# fit image
result1 = fitter.fit_from_shape(image,
initial_shape,
max_iters=[15, 5],
gt_shape=image.landmarks['PTS'].lms)
# print result
print(result1)
result.view(render_initial_shape=True)
def warp_landmarked_image_folder(top_dir, template, detector, ext='.jpg'):
"""
finds all images with associated .pts landmark files and performs
warping on them
"""
mask = menpo.image.BooleanImage.init_from_pointcloud(template)
warpeds = []
shapes = []
labels = []
folders = glob.glob(os.path.join(top_dir, '*'))
new_folders = [
folder.replace(imset, '{}-warped'.format(imset)) for folder in folders
]
for label, folder in enumerate(tqdm(folders)):
os.makedirs(new_folders[label], exist_ok=True)
for im_fn in tqdm(glob.glob('{}/*{}'.format(folder, ext))):
try:
image = mio.import_image(im_fn)
shape = image.landmarks['PTS']
except:
continue
bboxes = detector(image)
if len(bboxes) < 1:
print('no face found in {}'.format(im_fn))
continue
min_b, max_b = bboxes[0].bounds()
cropped = image.crop(min_b, max_b)
new_fn = im_fn.replace(imset, '{}-warped'.format(imset))
transform = menpo.transform.AlignmentAffine(shape, template)
warped = cropped.warp_to_mask(mask, transform)
mio.export_image(warped, new_fn, overwrite=True)
warpeds.append(warped.pixels)
shapes.append(shape)
labels.append(label)
return warpeds, shapes, labels
def load_image_test(path, reference_shape, frame_num):
file_name = path[:-1] + "/%06d.jpg" % (frame_num)
im = mio.import_image(file_name)
im.landmarks['PTS'] = mio.import_landmark_file(path[:-1] +
"/annot/%06d.pts" %
(frame_num))
# im.landmarks['PTS'] = mio.import_landmark_file(path[:-1] + "/%06d.pts" % (frame_num))
bb_path = path[:-1] + "/bbs/%06d.pts" % (frame_num)
im.landmarks['bb'] = mio.import_landmark_file(bb_path)
im = im.crop_to_landmarks_proportion(0.3, group='bb')
reference_shape = PointCloud(reference_shape)
bb = im.landmarks['bb'].lms.bounding_box()
im.landmarks['__initial'] = align_shape_with_bounding_box(
reference_shape, bb)
im = im.rescale_to_pointcloud(reference_shape, group='__initial')
lms = im.landmarks['PTS'].lms
initial = im.landmarks['__initial'].lms
# if the image is greyscale then convert to rgb.
pixels = grey_to_rgb(im).pixels.transpose(1, 2, 0)
gt_truth = lms.points.astype(np.float32)
estimate = initial.points.astype(np.float32)
return 1, pixels.astype(np.float32).copy(), gt_truth, estimate
def test_importing_I_no_normalise(is_file, mock_image):
mock_image.return_value = PILImage.new('I', (10, 10))
is_file.return_value = True
im = mio.import_image('fake_image_being_mocked.jpg', normalise=False)
assert im.shape == (10, 10)
assert im.n_channels == 1
assert im.pixels.dtype == np.int32
def test_importing_GIF_normalise(is_file, mock_image):
mock_image.return_value = PILImage.new('P', (10, 10))
is_file.return_value = True
im = mio.import_image('fake_image_being_mocked.gif', normalise=True)
assert im.shape == (10, 10)
assert im.n_channels == 3
assert im.pixels.dtype == np.float
def test_importing_PIL_P_normalize(is_file, mock_image):
mock_image.return_value = PILImage.new("P", (10, 10))
is_file.return_value = True
im = mio.import_image("fake_image_being_mocked.ppm", normalize=True)
assert im.shape == (10, 10)
assert im.n_channels == 3
assert im.pixels.dtype == np.float
def test_importing_PIL_L_normalise(is_file, mock_image):
mock_image.return_value = PILImage.new('L', (10, 10))
is_file.return_value = True
im = mio.import_image('fake_image_being_mocked.ppm', normalise=True)
assert im.shape == (10, 10)
assert im.n_channels == 1
assert im.pixels.dtype == np.float
def test_importing_PIL_P_no_normalize(is_file, mock_image):
mock_image.return_value = PILImage.new('P', (10, 10))
is_file.return_value = True
im = mio.import_image('fake_image_being_mocked.ppm', normalize=False)
assert im.shape == (10, 10)
assert im.n_channels == 3
assert im.pixels.dtype == np.uint8
def test_importing_PIL_P_no_normalize(is_file, mock_image):
mock_image.return_value = PILImage.new('P', (10, 15))
is_file.return_value = True
im = mio.import_image('fake_image_being_mocked.ppm', normalize=False)
assert im.shape == (15, 10)
assert im.n_channels == 3
assert im.pixels.dtype == np.uint8
def test_importing_I_no_normalise(is_file, mock_image):
mock_image.return_value = PILImage.new('I', (10, 10))
is_file.return_value = True
im = mio.import_image('fake_image_being_mocked.jpg', normalise=False)
assert im.shape == (10, 10)
assert im.n_channels == 1
assert im.pixels.dtype == np.int32
def image(self):
if self._image is None:
image_ = mio.import_image(self._image_path)
image = Image(np.rollaxis(image_.pixels, -1))
image.landmarks = image_.landmarks
image.crop_to_landmarks_proportion_inplace(0.5)
self._image = image
return self._image
def test_importing_imageio_RGB_no_normalise(is_file, mock_image):
mock_image.return_value = np.zeros([10, 10, 3], dtype=np.uint8)
is_file.return_value = True
im = mio.import_image('fake_image_being_mocked.jpg', normalise=False)
assert im.shape == (10, 10)
assert im.n_channels == 3
assert im.pixels.dtype == np.uint8
def test_resolve_from_paths_multi_group():
def resolver(path):
test_dict = {'test': path.with_name('lenna.ljson')}
return mio.input.resolve_from_paths(test_dict)
image = mio.import_image(mio.data_path_to('einstein.jpg'),
landmark_resolver=resolver)
assert (image.landmarks.n_groups == 2)
assert (set(image.landmarks.keys()) == {'test_LJSON', 'test_pupils'})
def test_resolve_from_paths_single_group():
def resolver(path):
test_dict = {'test': path.with_name('takeo.pts')}
return mio.input.resolve_from_paths(test_dict)
image = mio.import_image(mio.data_path_to('einstein.jpg'),
landmark_resolver=resolver)
assert (image.landmarks.n_groups == 1)
assert (image.landmarks['test'].path == mio.data_path_to('takeo.pts'))
def test_importing_imageio_RGB_no_normalise(is_file, mock_image):
mock_image.return_value = np.zeros([10, 10, 3], dtype=np.uint8)
is_file.return_value = True
im = mio.import_image('fake_image_being_mocked.jpg', normalise=False)
assert im.shape == (10, 10)
assert im.n_channels == 3
assert im.pixels.dtype == np.uint8
def test_resolve_from_paths_multi_group():
def resolver(path):
test_dict = {"test": path.with_name("lenna.ljson")}
return mio.input.resolve_from_paths(test_dict)
image = mio.import_image(mio.data_path_to("einstein.jpg"),
landmark_resolver=resolver)
assert image.landmarks.n_groups == 2
assert set(image.landmarks.keys()) == {"test_LJSON", "test_pupils"}
def test_resolve_from_paths_single_group():
def resolver(path):
test_dict = {"test": path.with_name("takeo.pts")}
return mio.input.resolve_from_paths(test_dict)
image = mio.import_image(mio.data_path_to("einstein.jpg"),
landmark_resolver=resolver)
assert image.landmarks.n_groups == 1
assert image.landmarks["test"].path == mio.data_path_to("takeo.pts")
def ply_importer(filepath, asset=None, texture_resolver=None, **kwargs):
"""Allows importing Wavefront (OBJ) files.
Uses VTK.
Parameters
----------
asset : `object`, optional
An optional asset that may help with loading. This is unused for this
implementation.
texture_resolver : `callable`, optional
A callable that recieves the mesh filepath and returns a single
path to the texture to load.
\**kwargs : `dict`, optional
Any other keyword arguments.
Returns
-------
shape : :map:`PointCloud` or subclass
The correct shape for the given inputs.
"""
import vtk
from vtk.util.numpy_support import vtk_to_numpy
ply_importer = vtk.vtkPLYReader()
ply_importer.SetFileName(str(filepath))
ply_importer.Update()
# Get the output
polydata = ply_importer.GetOutput()
# We must have point data!
points = vtk_to_numpy(polydata.GetPoints().GetData()).astype(np.float)
trilist = np.require(vtk_ensure_trilist(polydata), requirements=['C'])
texture = None
if texture_resolver is not None:
texture_path = texture_resolver(filepath)
if texture_path is not None and texture_path.exists():
texture = mio.import_image(texture_path)
tcoords = None
if texture is not None:
try:
tcoords = vtk_to_numpy(polydata.GetPointData().GetTCoords())
except Exception:
pass
if isinstance(tcoords, np.ndarray) and tcoords.size == 0:
tcoords = None
colour_per_vertex = None
return _construct_shape_type(points, trilist, tcoords, texture,
colour_per_vertex)
def ply_importer(filepath, asset=None, texture_resolver=None, **kwargs):
"""Allows importing Wavefront (OBJ) files.
Uses VTK.
Parameters
----------
asset : `object`, optional
An optional asset that may help with loading. This is unused for this
implementation.
texture_resolver : `callable`, optional
A callable that recieves the mesh filepath and returns a single
path to the texture to load.
\**kwargs : `dict`, optional
Any other keyword arguments.
Returns
-------
shape : :map:`PointCloud` or subclass
The correct shape for the given inputs.
"""
import vtk
from vtk.util.numpy_support import vtk_to_numpy
ply_importer = vtk.vtkPLYReader()
ply_importer.SetFileName(str(filepath))
ply_importer.Update()
# Get the output
polydata = ply_importer.GetOutput()
# We must have point data!
points = vtk_to_numpy(polydata.GetPoints().GetData()).astype(np.float)
trilist = np.require(vtk_ensure_trilist(polydata), requirements=['C'])
texture = None
if texture_resolver is not None:
texture_path = texture_resolver(filepath)
if texture_path is not None and texture_path.exists():
texture = mio.import_image(texture_path)
tcoords = None
if texture is not None:
try:
tcoords = vtk_to_numpy(polydata.GetPointData().GetTCoords())
except Exception:
pass
if isinstance(tcoords, np.ndarray) and tcoords.size == 0:
tcoords = None
colour_per_vertex = None
return _construct_shape_type(points, trilist, tcoords, texture,
colour_per_vertex)
def test_custom_landmark_resolver():
def lmark_resolver(path):
return mio.import_landmark_file(mio.data_path_to("takeo.pts"))
img = mio.import_image(mio.data_path_to("lenna.png"),
landmark_resolver=lmark_resolver)
assert img.has_landmarks
takeo_lmarks = mio.import_builtin_asset.takeo_pts()["PTS"]
np.allclose(img.landmarks["PTS"].points, takeo_lmarks.points)
def wrapper(index):
path = self.root / (index.decode("utf-8") + self.image_extension)
im = mio.import_image(path, normalize=False)
im = crop_face(im)
pixels = get_pixels(im)
landmarks = im.landmarks[None].lms.points.astype(np.float32)
return pixels.astype(np.float32), landmarks
def test_custom_landmark_resolver():
def lmark_resolver(path):
return mio.import_landmark_file(mio.data_path_to('takeo.pts'))
img = mio.import_image(mio.data_path_to('lenna.png'),
landmark_resolver=lmark_resolver)
assert (img.has_landmarks)
takeo_lmarks = mio.import_builtin_asset.takeo_pts()['PTS']
np.allclose(img.landmarks['PTS'].points, takeo_lmarks.points)
def getImageFromFile(path):
def load_image(i):
i = i.crop_to_landmarks_proportion(0.5)
if i.n_channels == 3:
i = i.as_greyscale()
labeller(i, 'PTS', face_ibug_68_to_face_ibug_68)
return i
image_path = Path(path)
i = load_image(mio.import_image(image_path))
return i
def test_importing_PIL_1_no_normalize(is_file, mock_image):
from menpo.image import BooleanImage
mock_image.return_value = PILImage.new('1', (10, 10))
is_file.return_value = True
im = mio.import_image('fake_image_being_mocked.ppm', normalize=False)
assert im.shape == (10, 10)
assert im.n_channels == 1
assert im.pixels.dtype == np.bool
assert type(im) == BooleanImage
def test_importing_PIL_RGBA_normalize(is_file, mock_image):
from menpo.image import MaskedImage
mock_image.return_value = PILImage.new('RGBA', (10, 10))
is_file.return_value = True
im = mio.import_image('fake_image_being_mocked.ppm', normalize=True)
assert im.shape == (10, 10)
assert im.n_channels == 3
assert im.pixels.dtype == np.float
assert type(im) == MaskedImage
def test_custom_landmark_resolver():
def lmark_resolver(path):
return {'PTS': mio.data_path_to('takeo.pts')}
img = mio.import_image(mio.data_path_to('lenna.png'),
landmark_resolver=lmark_resolver)
assert(img.has_landmarks)
takeo_lmarks = mio.import_builtin_asset.takeo_pts()
np.allclose(img.landmarks['PTS'].lms.points,
takeo_lmarks.lms.points)
def test_importing_PIL_1_no_normalize(is_file, mock_image):
from menpo.image import BooleanImage
mock_image.return_value = PILImage.new('1', (10, 15))
is_file.return_value = True
im = mio.import_image('fake_image_being_mocked.ppm', normalize=False)
assert im.shape == (15, 10)
assert im.n_channels == 1
assert im.pixels.dtype == np.bool
assert type(im) == BooleanImage
def test_importing_PIL_RGBA_normalize(is_file, mock_image):
from menpo.image import MaskedImage
mock_image.return_value = PILImage.new('RGBA', (10, 15))
is_file.return_value = True
im = mio.import_image('fake_image_being_mocked.ppm', normalize=True)
assert im.shape == (15, 10)
assert im.n_channels == 3
assert im.pixels.dtype == np.float
assert type(im) == MaskedImage
def getImageFromFile(path):
def load_image(i):
i = i.crop_to_landmarks_proportion(0.5)
if i.n_channels == 3:
i = i.as_greyscale()
labeller(i, 'PTS', face_ibug_68_to_face_ibug_68)
return i
image_path = Path(path)
i = load_image(mio.import_image(image_path))
return i
def test_importing_imageio_GIF_no_normalise(is_file, mock_image):
mock_image.return_value.get_data.return_value = np.ones((10, 10, 3),
dtype=np.uint8)
mock_image.return_value.get_length.return_value = 2
is_file.return_value = True
ll = mio.import_image('fake_image_being_mocked.gif', normalise=False)
assert len(ll) == 2
im = ll[0]
assert im.shape == (10, 10)
assert im.n_channels == 3
assert im.pixels.dtype == np.uint8
def test_register_image_importer(is_file):
from menpo.image import Image
image = Image.init_blank((10, 10))
def foo_importer(filepath, **kwargs):
return image
is_file.return_value = True
with patch.dict(mio.input.extensions.image_types, {}, clear=True):
mio.register_image_importer('.foo', foo_importer)
new_image = mio.import_image('fake.foo')
assert image is new_image
def load_images(list_frames, frames_path, path_land, clip_name, max_images=None,
training_images=None, crop_reading=0.3, pix_thres=330, feat=None):
"""
Read images from the clips that are processed. The landmarks can be a different folder with the extension of pts and
are searched as such.
:param list_frames: List of images that will be read and loaded.
:param frames_path: Path to the folder of images.
:param path_land: Path of the respective landmarks.
:param clip_name: The name of the clip being processed.
:param max_images: (optional) Max images that will be loaded from this clip.
:param training_images: (optional) List of images to append the new ones.
:param crop_reading: (optional) Amount of cropping the image around the landmarks.
:param pix_thres: (optional) If the cropped image has a dimension bigger than this, it gets cropped to this diagonal dimension.
:param feat: (optional) Features to be applied to the images before inserting them to the list.
:return: List of menpo images.
"""
from random import shuffle
if not check_path_and_landmarks(frames_path, clip_name, path_land):
return []
if feat is None:
feat = no_op
if training_images is None:
training_images = []
shuffle(list_frames) # shuffle the list to ensure random ones are chosen
if max_images is None:
max_images = len(list_frames)
elif max_images < 0:
print('Warning: The images cannot be negative, loading the whole list instead.')
max_images = len(list_frames)
cnt = 0 # counter for images appended to the list
for frame_name in list_frames:
try:
im = mio.import_image(frames_path + frame_name, normalise=True)
except ValueError: # in case the extension is unknown (by menpo)
print('Ignoring the \'image\' {}.'.format(frame_name))
continue
res = glob.glob(path_land + clip_name + sep + im.path.stem + '*.pts')
if len(res) == 0: # if the image does not have any existing landmarks, ignore it
continue
elif len(res) > 1:
#_r = randint(0,len(res)-1); #just for debugging reasons in different variable
#ln = mio.import_landmark_file(res[_r]) # in case there are plenty of landmarks for the image, load random ones
print('The image {} has more than one landmarks, for one person, loading only the first ones.'.format(frame_name))
ln = mio.import_landmark_file(res[0])
im.landmarks['PTS'] = ln
im = crop_rescale_img(im, crop_reading=crop_reading, pix_thres=pix_thres)
training_images.append(feat(im))
cnt += 1
if cnt >= max_images:
break # the limit of images (appended to the list) is reached
return training_images
def test_importing_PIL_1_proper_conversion(is_file, mock_image):
from menpo.image import BooleanImage
arr = np.zeros((10, 10), dtype=np.uint8)
arr[4, 4] = 255
mock_image.return_value = PILImage.fromarray(arr).convert('1')
is_file.return_value = True
im = mio.import_image('fake_image_being_mocked.ppm', normalize=False)
assert im.shape == (10, 10)
assert im.n_channels == 1
assert im.pixels.dtype == np.bool
assert type(im) == BooleanImage
assert np.all(im.pixels == arr.astype(np.bool))
def load_image(path, reference_shape, is_training=False, group='PTS',
mirror_image=False):
"""Load an annotated image.
In the directory of the provided image file, there
should exist a landmark file (.pts) with the same
basename as the image file.
Args:
path: a path containing an image file.
reference_shape: a numpy array [num_landmarks, 2]
is_training: whether in training mode or not.
group: landmark group containing the grounth truth landmarks.
mirror_image: flips horizontally the image's pixels and landmarks.
Returns:
pixels: a numpy array [width, height, 3].
estimate: an initial estimate a numpy array [68, 2].
gt_truth: the ground truth landmarks, a numpy array [68, 2].
"""
im = mio.import_image(path)
bb_root = im.path.parent.relative_to(im.path.parent.parent.parent)
if 'set' not in str(bb_root):
bb_root = im.path.parent.relative_to(im.path.parent.parent)
im.landmarks['bb'] = mio.import_landmark_file(str(Path('bbs') / bb_root / (
im.path.stem + '.pts')))
im = im.crop_to_landmarks_proportion(0.3, group='bb')
reference_shape = PointCloud(reference_shape)
bb = im.landmarks['bb'].lms.bounding_box()
im.landmarks['__initial'] = align_shape_with_bounding_box(reference_shape,
bb)
im = im.rescale_to_pointcloud(reference_shape, group='__initial')
if mirror_image:
im = utils.mirror_image(im)
lms = im.landmarks[group].lms
initial = im.landmarks['__initial'].lms
# if the image is greyscale then convert to rgb.
pixels = grey_to_rgb(im).pixels.transpose(1, 2, 0)
gt_truth = lms.points.astype(np.float32)
estimate = initial.points.astype(np.float32)
return pixels.astype(np.float32).copy(), gt_truth, estimate
def test_importing_ffmpeg_GIF_no_normalize(is_file, video_infos_ffprobe, pipe):
video_infos_ffprobe.return_value = {'duration': 2, 'width': 100,
'height': 150, 'n_frames': 10, 'fps': 5}
empty_frame = np.zeros(150*100*3, dtype=np.uint8).tostring()
pipe.return_value.stdout.read.return_value = empty_frame
is_file.return_value = True
ll = mio.import_image('fake_image_being_mocked.gif', normalize=False)
assert ll.path.name == 'fake_image_being_mocked.gif'
assert ll.fps == 5
assert len(ll) == 10
im = ll[0]
assert im.shape == (150, 100)
assert im.n_channels == 3
assert im.pixels.dtype == np.uint8
def im_read_greyscale(frame_name, frames_path, img_type, normalise=True):
"""
The function reads an image with name frame_name in frames_path and returns the greyscale menpo image.
:param frame_name: Name of the frame .
:param frames_path: Folder of the images (assumption that it exists).
:param img_type: Type/extension of the image.
:param normalise: (optional) Whether the image should be normalised when imported.
:return: Menpo greyscale image or [] if not found.
"""
if frame_name[frame_name.rfind('.'):] != img_type:
return [] # in case they are something different than an image
try:
im = mio.import_image(frames_path + frame_name, normalise=normalise)
if im.n_channels == 3 and normalise:
im = im.as_greyscale(mode='luminosity')
elif im.n_channels == 3:
im = im.as_greyscale(mode='channel', channel=1)
return im
except:
print('Potentially wrong path or wrong image.')
return []
def mjson_importer(filepath, asset=None, texture_resolver=True, **kwargs):
"""
Import meshes that are in a simple JSON format.
Parameters
----------
asset : `object`, optional
An optional asset that may help with loading. This is unused for this
implementation.
texture_resolver : `callable`, optional
A callable that recieves the mesh filepath and returns a single
path to the texture to load.
\**kwargs : `dict`, optional
Any other keyword arguments.
Returns
-------
shape : :map:`PointCloud` or subclass
The correct shape for the given inputs.
"""
with open(str(filepath), 'rb') as f:
mesh_json = json.load(f)
texture = None
if texture_resolver is not None:
texture_path = texture_resolver(filepath)
if texture_path is not None and texture_path.exists():
texture = mio.import_image(texture_path)
points = mesh_json['points']
trilist = mesh_json['trilist']
tcoords = mesh_json.get('tcoords'),
colour_per_vertex = mesh_json.get('colour_per_vertex')
return _construct_shape_type(points, trilist, tcoords, texture,
colour_per_vertex)
def test_import_image_no_norm():
img_path = os.path.join(mio.data_dir_path(), 'einstein.jpg')
im = mio.import_image(img_path, normalise=False)
assert im.pixels.dtype == np.uint8
def plot_image_latex_with_subcaptions(folds, pb, pout, name_im, legend_names=None,
normalise=None, allow_fail=False,
overwr=True):
"""
Customised function for my papers. It plots variations of an image (i.e. different
images) next to each other with the respective legend names.
The idea is: Import one by one from the folds, normalise (e.g. resize) and export each
with a predictable name. Write the tex file and compile it to create the image
with the several subplots and the custom labels.
Attention: Because of latex compilation, this function writes and reads from the disk,
so pay attention to the pout path.
:param folds: (list) Names of the parent folders to search the image to. The assumption
is that all those are relative to pb path.
:param pb: (str) Base path where the images to be imported exist.
:param pout: (str) Path to export the result in. The method will write the result in a
new sub-folder named 'concatenated'.
:param name_im: (str) Name (stem + suffix) of the image to be imported from folds.
:param legend_names: (optional, list or None) If provided, it should match in length the
folds; each one will be respectively provided as a sub-caption to the respective image.
:param normalise: (optional, list of functions or None) If not None, then the function accepts
a menpo image and normalises it.
:param allow_fail: (optional, list or bool) If bool, it is converted into a list of
length(folds). The images from folds that do not exist
will be ignored if allow_fail is True.
:param overwr: (optional, bool) To overwrite or not the intermediate results written.
:return:
# TODO: extend the formulation to provide freedom in the number of elements per line etc.
"""
# # short lambda for avoiding the long import command.
import_im = lambda p, norm=False: mio.import_image(p, landmark_resolver=None,
normalize=norm)
# # names_imout: Names of the output images in the disk.
# # names_meth: Method of the name to put in the sub-caption.
names_imout, names_meth = [], []
# # if allow_fail is provided as a single boolean, convert into a list, i.e.
# # each one of the folders has different permissions.
if not isinstance(allow_fail, list):
allow_fail = [allow_fail for _ in range(len(folds))]
# # if normalise is provided as a single boolean, convert into a list.
if not isinstance(normalise, list):
normalise = [normalise for _ in range(len(folds))]
for cnt, fold in enumerate(folds):
if allow_fail[cnt]:
# # In this case, we don't mind if an image fails.
try:
im = import_im(join(pb, fold, name_im))
except:
continue
else:
im = import_im(join(pb, fold, name_im))
# # get the name for the sub-caption (legend).
if legend_names is not None:
if '_' in legend_names[cnt]:
print('WARNING: `_` found on legend name, possibly issue with latex.')
names_meth.append(legend_names[cnt])
else:
assert 0, 'Not implemented for now! Need to use map_to_name()'
# # Optionally resize the image.
if normalise[cnt]:
im = normalise[cnt](im)
# # export the image into the disk and append the name exported in the list.
nn = '{}_{}'.format(Path(fold).stem, im.path.name)
mio.export_image(im, pout + nn, overwrite=overwr)
names_imout.append(nn)
# # export into a file the latex command.
nlat = Path(name_im).stem
fo = open(pout + '{}.tex'.format(nlat),'wt')
fo.writelines(('\\documentclass{article}\\usepackage{amsmath}'
'\n\\usepackage{graphicx}\\usepackage{subfig}'
'\\begin{document}\n'))
list_to_latex(names_imout, wrap_subfloat=True, names_subfl=names_meth, pbl='',
file_to_print=fo, caption=False)
fo.writelines('\\thispagestyle{empty}\\end{document}\n')
fo.close()
# # the concatenated for the final png
pout1 = Path(mkdir_p(join(pout, 'concatenated', '')))
# # create the png image and delete the tex and intermediate results.
cmd = ('cd {0}; pdflatex {1}.tex; pdfcrop {1}.pdf;'
'rm {1}.aux {1}.log {1}.pdf; mv {1}-crop.pdf {2}.pdf;'
'pdftoppm -png {2}.pdf > {2}.png; rm {2}.pdf; rm {0}*.png; rm {0}*.tex')
nconc = pout1.stem + sep + nlat
return popen(cmd.format(pout, nlat, nconc))
def test_importing_PIL_I_normalize(is_file, mock_image):
mock_image.return_value = PILImage.new('I', (10, 10))
is_file.return_value = True
im = mio.import_image('fake_image_being_mocked.ppm', normalize=True)
def build_all_models_frgc(images, ref_frame_path, subject_id,
out_path='/vol/atlas/homes/pts08/',
transform_class=ThinPlateSplines,
square_mask=False):
print "Beginning model creation for {0}".format(subject_id)
# Build reference frame
ref_frame = mio.import_image(ref_frame_path)
labeller([ref_frame], 'PTS', ibug_68_closed_mouth)
ref_frame.crop_to_landmarks(boundary=2, group='ibug_68_closed_mouth',
label='all')
if not square_mask:
ref_frame.constrain_mask_to_landmarks(group='ibug_68_closed_mouth',
label='all')
reference_shape = ref_frame.landmarks['ibug_68_closed_mouth'].lms
# Extract all shapes
labeller(images, 'PTS', ibug_68_closed_mouth)
shapes = [img.landmarks['ibug_68_closed_mouth'].lms for img in images]
# Warp each of the images to the reference image
print "Warping all frgc shapes to reference frame of {0}".format(subject_id)
tps_transforms = [transform_class(reference_shape, shape) for shape in shapes]
warped_images = [img.warp_to(ref_frame.mask, t)
for img, t in zip(images, tps_transforms)]
# Calculate the normal matrix
print 'Extracting all normals'
normal_matrix = extract_normals(warped_images)
# Save memory by deleting all the images since we don't need them any more.
# Keep one around that we can query for it's size etc
example_image = deepcopy(warped_images[0])
del warped_images[:]
# Normals
print 'Computing normal feature space'
normal_images = create_feature_space(normal_matrix, example_image,
'normals', subject_id,
out_path=out_path)
# Spherical
print 'Computing spherical feature space'
spherical_matrix = Spherical().logmap(normal_matrix)
spherical_images = create_feature_space(spherical_matrix, example_image,
'spherical', subject_id,
out_path=out_path)
# AEP
print 'Computing AEP feature space'
mean_normals = normalise_vector(np.mean(normal_matrix, 0))
aep_matrix = AEP(mean_normals).logmap(normal_matrix)
aep_images = create_feature_space(aep_matrix, example_image, 'aep',
subject_id,
out_path=out_path)
# PGA
print 'Computing PGA feature space'
mu = intrinsic_mean(normal_matrix, PGA, max_iters=50)
pga_matrix = PGA(mu).logmap(normal_matrix)
pga_images = create_feature_space(pga_matrix, example_image, 'pga',
subject_id,
out_path=out_path)
# PCA models
n_components = 200
print 'Computing PCA models ({} components)'.format(n_components)
template = ref_frame
normal_model = PCAModel(normal_images, center=True)
normal_model.trim_components(200)
cosine_model = PCAModel(normal_images, center=False)
cosine_model.trim_components(200)
spherical_model = PCAModel(spherical_images, center=False)
spherical_model.trim_components(200)
aep_model = PCAModel(aep_images, center=False)
aep_model.trim_components(200)
pga_model = PCAModel(pga_images, center=False)
pga_model.trim_components(200)
mean_normals_image = normal_model.mean
mu_image = mean_normals_image.from_vector(mu)
# Save out models
pickle_model(out_path, subject_id, 'normal', normal_model, template,
mean_normals)
pickle_model(out_path, subject_id, 'cosine', cosine_model, template,
mean_normals)
pickle_model(out_path, subject_id, 'spherical', spherical_model, template,
mean_normals)
pickle_model(out_path, subject_id, 'aep', aep_model, template,
mean_normals)
pickle_model(out_path, subject_id, 'pga', pga_model, template,
mean_normals, intrinsic_means=mu_image)
def test_import_image_no_norm():
img_path = mio.data_dir_path() / 'einstein.jpg'
im = mio.import_image(img_path, normalize=False)
assert im.pixels.dtype == np.uint8
def test_import_image():
img_path = mio.data_dir_path() / 'einstein.jpg'
im = mio.import_image(img_path)
assert im.pixels.dtype == np.float
assert im.n_channels == 1
from mock import MagicMock
import numpy as np
from numpy.testing import assert_allclose
from menpo.shape import PointDirectedGraph
from menpodetect.detect import (detect, menpo_image_to_uint8)
import menpo.io as mio
takeo = mio.import_builtin_asset.takeo_ppm()
takeo_uint8 = mio.import_image(mio.data_path_to('takeo.ppm'), normalize=False)
fake_box = np.array([[0, 0], [1, 0], [1, 1], [0, 1]])
fake_detector = lambda x: ([PointDirectedGraph.init_from_edges(
fake_box.copy(),
np.array([[0, 1], [1, 2], [2, 3], [3, 0]]))])
def test_rescaling_image():
takeo_copy = takeo.copy()
ratio = 200.0 / takeo_copy.diagonal()
pcs = detect(fake_detector, takeo_copy, image_diagonal=200)
assert len(pcs) == 1
assert takeo_copy.n_channels == 3
assert takeo_copy.landmarks['object_0'][None].n_points == 4
assert_allclose(takeo_copy.landmarks['object_0'][None].points,
fake_box * (1.0 / ratio), atol=10e-2)
def test_passing_uint8_image():
takeo_copy = takeo_uint8.copy()
pcs = detect(fake_detector, takeo_copy, greyscale=False)
def test_importing_GIF_non_pallete_exception(is_file, mock_image):
mock_image.return_value = PILImage.new('RGB', (10, 10))
is_file.return_value = True
mio.import_image('fake_image_being_mocked.gif', normalise=False)
def wrl_importer(filepath, asset=None, texture_resolver=None, **kwargs):
"""Allows importing VRML 2.0 meshes.
Uses VTK and assumes that the first actor in the scene is the one
that we want.
Parameters
----------
asset : `object`, optional
An optional asset that may help with loading. This is unused for this
implementation.
texture_resolver : `callable`, optional
A callable that recieves the mesh filepath and returns a single
path to the texture to load.
\**kwargs : `dict`, optional
Any other keyword arguments.
Returns
-------
shape : :map:`PointCloud` or subclass
The correct shape for the given inputs.
"""
import vtk
from vtk.util.numpy_support import vtk_to_numpy
vrml_importer = vtk.vtkVRMLImporter()
vrml_importer.SetFileName(str(filepath))
vrml_importer.Update()
# Get the first actor.
actors = vrml_importer.GetRenderer().GetActors()
actors.InitTraversal()
mapper = actors.GetNextActor().GetMapper()
mapper_dataset = mapper.GetInput()
if actors.GetNextActor():
# There was more than one actor!
warnings.warn('More than one actor was detected in the scene. Only '
'single scene actors are currently supported.')
# Get the Data
polydata = vtk.vtkPolyData.SafeDownCast(mapper_dataset)
# We must have point data!
points = vtk_to_numpy(polydata.GetPoints().GetData()).astype(np.float)
trilist = vtk_ensure_trilist(polydata)
texture = None
if texture_resolver is not None:
texture_path = texture_resolver(filepath)
if texture_path is not None and texture_path.exists():
texture = mio.import_image(texture_path)
# Three different outcomes - either we have a textured mesh, a coloured
# mesh or just a plain mesh. Let's try each in turn.
# Textured
tcoords = None
try:
tcoords = vtk_to_numpy(polydata.GetPointData().GetTCoords())
except Exception:
pass
if isinstance(tcoords, np.ndarray) and tcoords.size == 0:
tcoords = None
# Colour-per-vertex
try:
colour_per_vertex = vtk_to_numpy(mapper.GetLookupTable().GetTable()) / 255.
except Exception:
pass
if isinstance(colour_per_vertex, np.ndarray) and colour_per_vertex.size == 0:
colour_per_vertex = None
return _construct_shape_type(points, trilist, tcoords, texture,
colour_per_vertex)
def test_landmark_resolver_none():
img = mio.import_image(mio.data_path_to('lenna.png'),
landmark_resolver=None)
assert(not img.has_landmarks)