`skimage.morphology.isotropic:isotropic_erosion`

source: /dev/scikit-image/src/skimage/morphology/isotropic.py :9

Signature

def isotropic_erosion ( image , radius , out = None , spacing = None )

Summary

Return binary morphological erosion of an image.

Extended Summary

Compared to the more general skimage.morphology.erosion, this function only supports binary inputs and circular footprints. However, it performs typically faster for large (circular) footprints. This works by applying a threshold to the exact Euclidean distance map of the image ^[1], ^[2]. The implementation is based on: func:scipy.ndimage.distance_transform_edt.

Parameters

image : ndarray: Binary input image.
radius : float: The radius of the footprint used for the operation.
out : ndarray of bool, optional: The array to store the result of the morphology. If None, a new array will be allocated.
spacing : float, or sequence of float, optional: Spacing of elements along each dimension. If a sequence, must be of length equal to the input's dimension (number of axes). If a single number, this value is used for all axes. If not specified, a grid spacing of unity is implied.

Returns

eroded : ndarray of bool: The result of the morphological erosion taking values in [False, True].

Examples

Erosion shrinks bright regions

import numpy as np
import skimage as ski
image = np.array([[0, 0, 1, 0, 0],
                  [0, 1, 1, 1, 0],
                  [0, 1, 1, 1, 0],
                  [0, 1, 1, 1, 0],
                  [0, 0, 0, 0, 0]], dtype=bool)
result = ski.morphology.isotropic_erosion(image, radius=1)
result.view(np.uint8)

✓

Aliases

skimage.morphology.isotropic_erosion