python 分水岭算法的实现

“”“ watershed.py-分水岭算法
该模块实现了分水岭算法，可将像素分配到标记的盆地中。
该算法使用优先级队列来保存像素，优先级队列的度量标准是像素值，然后输入队列的时间-这将使关系更加紧密，有利于最接近的标记。
一些想法取自Soille，“使用数学形态从数字高程模型自动进行盆地划定”，信号处理20（1990）171-182。
该论文最重要的见解是，进入队列的时间解决了两个问题：应将像素分配给具有最大梯度的邻居，或者，如果没有梯度，则应将高原上的像素分配在相对侧的标记之间。
最初是CellProfiler的一部分，代码已获得GPL和BSD许可。
网址：http：//www.cellprofiler.org
版权所有（c）2003-2009麻省理工学院
版权所有（c）2009-2011 Broad Institute
版权所有。
原作者：Lee Kamentsky

import numpy as np
from scipy import ndimage as ndi

from . import _watershed
from ..util import crop, regular_seeds


def _validate_inputs(image, markers, mask):
    """确保分水岭算法的所有输入都具有相同的形状和类型。
    Parameters
    ----------
    image : array
        The input image.
    markers : int or array of int
        The marker image.
    mask : array, or None
        A boolean mask, True where we want to compute the watershed.
    Returns
    -------
    image, markers, mask : arrays
        The validated and formatted arrays. Image will have dtype float64,
        markers int32, and mask int8. If ``None`` was given for the mask,
        it is a volume of all 1s.
    Raises
    ------
    ValueError
        If the shapes of the given arrays don't match.
    """
    if not isinstance(markers, (np.ndarray, list, tuple)):
        # not array-like, assume int
        markers = regular_seeds(image.shape, markers)
    elif markers.shape != image.shape:
        raise ValueError("`markers` (shape {}) must have same shape "
                         "as `image` (shape {})".format(markers.shape, image.shape))
    if mask is not None and mask.shape != image.shape:
        raise ValueError("`mask` must have same shape as `image`")
    if mask is None:
        # Use a complete `True` mask if none is provided
        mask = np.ones(image.shape, bool)
    return (image.astype(np.float64),
            markers.astype(np.int32),
            mask.astype(np.int8))


def _validate_connectivity(image_dim, connectivity, offset):
    """Convert any valid connectivity to a structuring element and offset.
    Parameters
    ----------
    image_dim : int
        The number of dimensions of the input image.
    connectivity : int, array, or None
        The neighborhood connectivity. An integer is interpreted as in
        ``scipy.ndimage.generate_binary_structure``, as the maximum number
        of orthogonal steps to reach a neighbor. An array is directly
        interpreted as a structuring element and its shape is validated against
        the input image shape. ``None`` is interpreted as a connectivity of 1.
    offset : tuple of int, or None
        The coordinates of the center of the structuring element.
    Returns
    -------
    c_connectivity : array of bool
        The structuring element corresponding to the input `connectivity`.
    offset : array of int
        The offset corresponding to the center of the structuring element.
    Raises
    ------
    ValueError:
        If the image dimension and the connectivity or offset dimensions don't
        match.
    """
    if connectivity is None:
        connectivity = 1
    if np.isscalar(connectivity):
        c_connectivity = ndi.generate_binary_structure(image_dim, connectivity)
    else:
        c_connectivity = np.array(connectivity, bool)
        if c_connectivity.ndim != image_dim:
            raise ValueError("Connectivity dimension must be same as image")
    if offset is None:
        if any([x % 2 == 0 for x in c_connectivity.shape]):
            raise ValueError("Connectivity array must have an unambiguous "
                             "center")
        offset = np.array(c_connectivity.shape) // 2
    return c_connectivity, offset


def _compute_neighbors(image, structure, offset):
    """Compute neighborhood as an array of linear offsets into the image.
    These are sorted according to Euclidean distance from the center (given
    by `offset`), ensuring that immediate neighbors are visited first.
    """
    structure[tuple(offset)] = 0  # ignore the center; it's not a neighbor
    locations = np.transpose(np.nonzero(structure))
    sqdistances = np.sum((locations - offset)**2, axis=1)
    neighborhood = (np.ravel_multi_index(locations.T, image.shape) -
                    np.ravel_multi_index(offset, image.shape)).astype(np.int32)
    sorted_neighborhood = neighborhood[np.argsort(sqdistances)]
    return sorted_neighborhood


def watershed(image, markers, connectivity=1, offset=None, mask=None,
              compactness=0, watershed_line=False):
    """Find watershed basins in `image` flooded from given `markers`.
    Parameters
    ----------
    image: ndarray (2-D, 3-D, ...) of integers
        Data array where the lowest value points are labeled first.
    markers: int, or ndarray of int, same shape as `image`
        The desired number of markers, or an array marking the basins with the
        values to be assigned in the label matrix. Zero means not a marker.
    connectivity: ndarray, optional
        An array with the same number of dimensions as `image` whose
        non-zero elements indicate neighbors for connection.
        Following the scipy convention, default is a one-connected array of
        the dimension of the image.
    offset: array_like of shape image.ndim, optional
        offset of the connectivity (one offset per dimension)
    mask: ndarray of bools or 0s and 1s, optional
        Array of same shape as `image`. Only points at which mask == True
        will be labeled.
    compactness : float, optional
        Use compact watershed [3]_ with given compactness parameter.
        Higher values result in more regularly-shaped watershed basins.
    watershed_line : bool, optional
        If watershed_line is True, a one-pixel wide line separates the regions
        obtained by the watershed algorithm. The line has the label 0.
    Returns
    -------
    out: ndarray
        A labeled matrix of the same type and shape as markers
    See also
    --------
    skimage.segmentation.random_walker: random walker segmentation
        A segmentation algorithm based on anisotropic diffusion, usually
        slower than the watershed but with good results on noisy data and
        boundaries with holes.
    Notes
    -----
    此函数实现了分水岭算法[1] _ [2] _，可将像素分配到标记的盆地中。 该算法使用优先级队列来保存 
    像素，优先级队列的度量标准是像素值，其次是输入队列的时间-这将使关系更加紧密，有利于最接近的 
    标记。
    Some ideas taken from
    Soille, "Automated Basin Delineation from Digital Elevation Models Using
    Mathematical Morphology", Signal Processing 20 (1990) 171-182
    该论文最重要的见解是，进入队列的时间解决了两个问题：应将像素分配给具有最大梯度的邻居，或者，如果没有梯度，则应将高原上的像素分配在相对侧的标记之间 。
    This implementation converts all arguments to specific, lowest common
    denominator types, then passes these to a C algorithm.
    Markers can be determined manually, or automatically using for example
    the local minima of the gradient of the image, or the local maxima of the
    distance function to the background for separating overlapping objects
    (see example).
    References
    ----------
    .. [1] http://en.wikipedia.org/wiki/Watershed_%28image_processing%29
    .. [2] http://cmm.ensmp.fr/~beucher/wtshed.html
    .. [3] Peer Neubert & Peter Protzel (2014). Compact Watershed and
           Preemptive SLIC: On Improving Trade-offs of Superpixel Segmentation
           Algorithms. ICPR 2014, pp 996-1001. DOI:10.1109/ICPR.2014.181
           https://www.tu-chemnitz.de/etit/proaut/forschung/rsrc/cws_pSLIC_ICPR.pdf

Examples
	分水岭算法可用于分离重叠的对象。
	我们首先生成带有两个重叠圆的初始图像：
	>>> x, y = np.indices((80, 80))
	>>> x1, y1, x2, y2 = 28, 28, 44, 52
	>>> r1, r2 = 16, 20
	>>> mask_circle1 = (x - x1)**2 + (y - y1)**2 < r1**2
	>>> mask_circle2 = (x - x2)**2 + (y - y2)**2 < r2**2
	>>> image = np.logical_or(mask_circle1, mask_circle2)
	接下来，我们要将两个圆圈分开。 我们在距背景的最大距离处生成标记：
	>>> from scipy import ndimage as ndi
	>>> distance = ndi.distance_transform_edt(image)
	>>> from skimage.feature import peak_local_max
	>>> local_maxi = peak_local_max(distance, labels=image,
	... footprint=np.ones((3, 3)),
	... indices=False)
	>>> markers = ndi.label(local_maxi)[0]
	最后，我们对图像和标记运行分水岭：
	>>> labels = watershed(-distance, markers, mask=image)