def __call__(
self,
image,
window_size=10,
threshold=0,
fill_holes=True,
remove_borderobjects=True,
outline_smoothing=0,
use_watershed=False,
seeding_size=8,
*args,
**kw
):
"""Local adaptive threshold segmentation using a gaussian Kernel"""
thresh = adaptive_threshold(image, window_size, threshold)
if fill_holes:
thresh = ndi.morphology.binary_fill_holes(thresh)
# object don't touch border after outline smoothing
if remove_borderobjects:
thresh = clear_border(thresh)
if outline_smoothing >= 1:
thresh = outlineSmoothing(thresh, outline_smoothing)
if use_watershed:
label_image = watershed(thresh, seeding_size=seeding_size)
else:
label_image = ndi.label(thresh)[0]
return label_image
def __call__(self, image, window_size=10, threshold=0, fill_holes=True,
outline_smoothing=2, remove_borderobjects=True, size_min=1,
*args, **kw):
thresh = threshold_adaptive(image, block_size=window_size,
offset=-1*threshold)
if outline_smoothing >= 1:
thresh = outlineSmoothing(thresh, outline_smoothing)
thresh = remove_small_objects(thresh, size_min)
seeds = ndi.label(clear_border(~thresh))[0]
thresh = ndi.binary_fill_holes(thresh)
smask = seeds.astype(bool)
# object don't touch border after outline smoothing
if remove_borderobjects:
thresh = clear_border(thresh)
img = np.zeros(thresh.shape)
img[~smask] = 1
edt = ndi.morphology.distance_transform_edt(img)
edt -= ndi.morphology.distance_transform_edt(seeds)
labels = watershed(edt, seeds)
labels[smask] = 0
labels[~thresh] = 0
return labels