def mask_to_geojson(img_mask, label=None, simplify_tol=1.5):
"""
Args:
img_mask (numpy array): numpy data, with each object being assigned with a unique uint number
label (str): like 'cell', 'nuclei'
simplify_tol (float): give a higher number if you want less coordinates.
"""
# for img_mask, for cells on border, should make sure on border pixels are # set to 0
shape_x, shape_y = img_mask.shape
shape_x, shape_y = shape_x - 1, shape_y - 1
img_mask[0, :] = img_mask[:, 0] = img_mask[shape_x, :] = img_mask[:, shape_y] = 0
features = []
label = label or "cell"
# Get all object ids, remove 0 since this is background
ind_objs = np.unique(img_mask)
ind_objs = np.delete(ind_objs, np.where(ind_objs == 0))
for obj_int in np.nditer(ind_objs):
# Create binary mask for current object and find contour
img_mask_loop = np.zeros((img_mask.shape[0], img_mask.shape[1]))
img_mask_loop[img_mask == obj_int] = 1
contours_find = measure.find_contours(img_mask_loop, 0.5)
if len(contours_find) == 1:
index = 0
else:
pixels = []
for _, item in enumerate(contours_find):
pixels.append(len(item))
index = np.argmax(pixels)
contour = contours_find[index]
contour_as_numpy = contour[:, np.argsort([1, 0])]
contour_as_numpy[:, 1] = np.array([img_mask.shape[0] - h[0] for h in contour])
contour_asList = contour_as_numpy.tolist()
if simplify_tol is not None:
poly_shapely = shapely_polygon(contour_asList)
poly_shapely_simple = poly_shapely.simplify(
simplify_tol, preserve_topology=False
)
contour_asList = list(poly_shapely_simple.exterior.coords)
contour_as_Numpy = np.asarray(contour_asList)
# Create and append feature for geojson
pol_loop = geojson_polygon([contour_asList])
full_label = label + "_idx"
index_number = int(obj_int - 1)
features.append(
Feature(
geometry=pol_loop, properties={full_label: index_number, "label": label}
)
)
feature_collection = FeatureCollection(
features, bbox=[0, 0, img_mask.shape[1] - 1, img_mask.shape[0] - 1]
)
return feature_collection
def _as_shapely_polygon(self) -> shapely_polygon:
points = [
(self.x1, self.y1),
(self.x2, self.y1),
(self.x2, self.y2),
(self.x1, self.y2),
(self.x1, self.y1),
]
return shapely_polygon(points)
def _convert_mask(img_mask, label=None, simplify_tol=1.5):
# for img_mask, for cells on border, should make sure on border pixels are # set to 0
shape_x, shape_y = img_mask.shape
shape_x, shape_y = shape_x - 1, shape_y - 1
img_mask[0, :] = img_mask[:,
0] = img_mask[shape_x, :] = img_mask[:,
shape_y] = 0
features = []
label = label or "cell"
# Get all object ids, remove 0 since this is background
ind_objs = np.unique(img_mask)
ind_objs = np.delete(ind_objs, np.where(ind_objs == 0))
for obj_int in np.nditer(ind_objs, flags=["zerosize_ok"]):
# Create binary mask for current object and find contour
img_mask_loop = np.zeros((img_mask.shape[0], img_mask.shape[1]))
img_mask_loop[img_mask == obj_int] = 1
contours_find = measure.find_contours(img_mask_loop, 0.5)
if len(contours_find) == 1:
index = 0
else:
pixels = []
for _, item in enumerate(contours_find):
pixels.append(len(item))
index = np.argmax(pixels)
contour = contours_find[index]
contour_as_numpy = contour[:, np.argsort([1, 0])]
contour_as_numpy[:, 1] = np.array(
[img_mask.shape[0] - h[0] for h in contour])
contour_asList = contour_as_numpy.tolist()
if simplify_tol is not None:
poly_shapely = shapely_polygon(contour_asList)
poly_shapely_simple = poly_shapely.simplify(
simplify_tol, preserve_topology=False)
contour_asList = list(poly_shapely_simple.exterior.coords)
contour_as_Numpy = np.asarray(contour_asList)
# Create and append feature for geojson
pol_loop = geojson_polygon([contour_asList])
full_label = label + "_idx"
index_number = int(obj_int - 1)
features.append(
Feature(geometry=pol_loop,
properties={
full_label: index_number,
"label": label
}))
return features
def simplify_contour(contour_asList, simplify_tol=0.2):
poly_shapely = shapely_polygon(contour_asList)
poly_shapely_simple = poly_shapely.simplify(simplify_tol,
preserve_topology=True)
contour_asList = list(poly_shapely_simple.exterior.coords)
return contour_asList
def masks_to_polygon(img_mask,
label=None,
simplify_tol=0,
plot_simplify=False,
save_name=None):
'''
Find contours with skimage, simplify them (optional), store as geojson:
1. Loops over each detected object, creates a mask and finds it contour
2. Contour can be simplified (reduce the number of points)
- uses shapely: https://shapely.readthedocs.io/en/stable/manual.html#object.simplify
- will be performed if tolernace simplify_tol is != 0
3. Polygons will be saved in geojson format, which can be read by ImJoys'
AnnotationTool. Annotations for one image are stored as one feature collection
each annotation is one feature:
"type": "Feature",
"geometry": {"type": "Polygon","coordinates": [[]]}
"properties": null
Args:
img_mask (2D numpy array): image wiht segmentation masks. Background is 0,
each object has a unique pixel value.
simplify_tol (float): tolerance for simplification (All points in the simplified object
will be within the tolerance distance of the original geometry)
No simplification will be performed when set to 0.
plot_simplify (Boolean): plot results of simplifcation. Plot will be shown for EACH mask.
Use better for debuggin only.
save_name (string): full file-name to save GeoJson file. Not file will be
saved when None.
Returns:
contours (List): contains polygon of each object stored as a numpy array.
feature_collection : GeoJson feature collection
'''
# Prepare list to store polygon coordinates and geojson features
features = []
contours = []
Ncells = img_mask.max()
# Loop over all masks (except with index 0 which is background)
for i, obj_int in enumerate(range(1, Ncells)):
# Create binary mask for current object and find contour
img_mask_loop = np.zeros((img_mask.shape[0], img_mask.shape[1]))
img_mask_loop[img_mask == obj_int] = 1
contour = measure.find_contours(img_mask_loop, 0.5)
# Proceeed only if one contour was found
if len(contour) == 1:
contour_asNumpy = contour[0]
contour_asList = contour_asNumpy.tolist()
# Simplify polygon if tolerance is set to any value except 0
if simplify_tol != 0:
poly_shapely = shapely_polygon(contour_asList)
poly_shapely_simple = poly_shapely.simplify(
simplify_tol, preserve_topology=False)
contour_asList = list(poly_shapely_simple.exterior.coords)
contour_asNumpy = np.asarray(contour_asList)
if plot_simplify:
plot_polygons(poly_shapely, poly_shapely_simple, obj_int)
# Append to polygon list
contours.append(contour_asNumpy)
# Create and append feature for geojson
pol_loop = geojson_polygon(contour_asList)
features.append(
Feature(geometry=pol_loop, properties={"label": label}))
#elif len(contour) == 0:
# print(f'No contour found for object {obj_int}')
#else:
# print(f'More than one contour found for object {obj_int}')
# Save to json file
if save_name:
feature_collection = FeatureCollection(features)
with open(save_name, 'w') as f:
dump(feature_collection, f)
f.close()
return features, contours
def _as_shapely_polygon(self) -> shapely_polygon:
coordinates = self.get_evenly_distributed_ellipse_coordinates()
return shapely_polygon(coordinates)
def _as_shapely_polygon(self) -> shapely_polygon:
"""
Returns the Polygon object as a shapely polygon which is used for calculating intersection between shapes.
"""
return shapely_polygon([(point.x, point.y) for point in self.points])