o h>@sddlZddlmZddlmZddlZddlmZddlm Z ddl m Z m Z ddl mZdd lmZdd lmZdd lmZmZd d lmZmZddZddZejdd   dddddZdS)N)Iterable)warn)random)kmeans2)pdist squareform)utils)gaussian)rgb2lab) img_as_float regular_grid)"_enforce_label_connectivity_cython _slic_cythoncCstjt|tdj}td}tjt|t d}t |j |t |t|dd}d}|r2|j dn|j }t |||} t|| krOt |j || dd} nt} t|| ||dd\} } tt| } t| tj| d }t| | |d d fd }| |fS) aFind regularly spaced centroids on a mask. Parameters ---------- mask : 3D ndarray The mask within which the centroids must be positioned. n_centroids : int The number of centroids to be returned. Returns ------- centroids : 2D ndarray The coordinates of the centroids with shape (n_centroids, 3). steps : 1D ndarray The approximate distance between two seeds in all dimensions. dtype{F)replace r)iterNr)nparraynonzerofloatTr RandomStatearangelenintsortchoiceminndimEllipsisrrr fill_diagonalinfargminabsmean)mask n_centroids multichannelcoordrngidx_fullidx dense_factor ndim_spatialn_dense idx_dense centroids_dist closest_ptsstepsr<`/var/www/html/scripts/venv/lib/python3.10/site-packages/skimage/segmentation/slic_superpixels.py_get_mask_centroidss,         r>cCs|jdd\}}}tjd|d|d|f\}}}t|jdd|}||dtjf} ||dtjf} ||dtjf} tj| | | gdd} tdd|D} | | fS)aFind regularly spaced centroids on the image. Parameters ---------- image : 2D, 3D or 4D ndarray Input image, which can be 2D or 3D, and grayscale or multichannel. n_centroids : int The (approximate) number of centroids to be returned. Returns ------- centroids : 2D ndarray The coordinates of the centroids with shape (~n_centroids, 3). steps : 1D ndarray The approximate distance between two seeds in all dimensions. N.raxiscSs$g|]}|jdurt|jndqS)N?)stepr).0sr<r<r= jsz'_get_grid_centroids..)shapermgridr ravelnewaxis concatenateasarray)imager-dhwgrid_zgrid_ygrid_xslices centroids_z centroids_y centroids_xr7r;r<r<r=_get_grid_centroidsKs"  rXF)multichannel_outputd$@rT?r?r) channel_axisc " Cs|jdkr| durtd| dt|}t|j}|j|dd}| durGtj| t d} | dur@tj | | d}t ||j }n| }||}n|}| }|}t|rZtd t|sdt|rhtd ||8}||krv|||}| du}|j}d }| du}|jdkr|tjd tjf}d}n|jd kr|r|tjd f}d}n|jd kr|s|d tjf}|r|s|dur|j | d kr|rtd|j | d krt|}| dvrtdd }|r| d} | jdkrt| tjd f} | j |j dd krtdt| ||\}}d}nt||\}}|dur"tjd |d}nPt|trntj||d}|rW|jdkrO|jd krFtdtddn td|jdt|dd}n|jd krftd|jdtj||d}ntdt|rtj |||g|d}||}nDt|trtj||d}|r|jdkr|jd krtdtddn td|jdt|dd}n|jd krtd|jd|dk!rt"|dg}t#||dd }|j d}tjtj$|t%||j d fgd!d|d}t|}d"|}tj|||d}|rt&|| ||||| d| d# t&|| ||||| d | d# }|rV|r6| '|}n t()|j dd |}t*||} t*| |}!t+|| |!| d$}|r]|d}|S)%uSegments image using k-means clustering in Color-(x,y,z) space. Parameters ---------- image : 2D, 3D or 4D ndarray Input image, which can be 2D or 3D, and grayscale or multichannel (see `channel_axis` parameter). Input image must either be NaN-free or the NaN's must be masked out n_segments : int, optional The (approximate) number of labels in the segmented output image. compactness : float, optional Balances color proximity and space proximity. Higher values give more weight to space proximity, making superpixel shapes more square/cubic. In SLICO mode, this is the initial compactness. This parameter depends strongly on image contrast and on the shapes of objects in the image. We recommend exploring possible values on a log scale, e.g., 0.01, 0.1, 1, 10, 100, before refining around a chosen value. max_num_iter : int, optional Maximum number of iterations of k-means. sigma : float or array-like of floats, optional Width of Gaussian smoothing kernel for pre-processing for each dimension of the image. The same sigma is applied to each dimension in case of a scalar value. Zero means no smoothing. Note that `sigma` is automatically scaled if it is scalar and if a manual voxel spacing is provided (see Notes section). If sigma is array-like, its size must match ``image``'s number of spatial dimensions. spacing : array-like of floats, optional The voxel spacing along each spatial dimension. By default, `slic` assumes uniform spacing (same voxel resolution along each spatial dimension). This parameter controls the weights of the distances along the spatial dimensions during k-means clustering. convert2lab : bool, optional Whether the input should be converted to Lab colorspace prior to segmentation. The input image *must* be RGB. Highly recommended. This option defaults to ``True`` when ``channel_axis` is not None *and* ``image.shape[-1] == 3``. enforce_connectivity : bool, optional Whether the generated segments are connected or not min_size_factor : float, optional Proportion of the minimum segment size to be removed with respect to the supposed segment size ```depth*width*height/n_segments``` max_size_factor : float, optional Proportion of the maximum connected segment size. A value of 3 works in most of the cases. slic_zero : bool, optional Run SLIC-zero, the zero-parameter mode of SLIC. [2]_ start_label : int, optional The labels' index start. Should be 0 or 1. .. versionadded:: 0.17 ``start_label`` was introduced in 0.17 mask : ndarray, optional If provided, superpixels are computed only where mask is True, and seed points are homogeneously distributed over the mask using a k-means clustering strategy. Mask number of dimensions must be equal to image number of spatial dimensions. .. versionadded:: 0.17 ``mask`` was introduced in 0.17 channel_axis : int or None, optional If None, the image is assumed to be a grayscale (single channel) image. Otherwise, this parameter indicates which axis of the array corresponds to channels. .. versionadded:: 0.19 ``channel_axis`` was added in 0.19. Returns ------- labels : 2D or 3D array Integer mask indicating segment labels. Raises ------ ValueError If ``convert2lab`` is set to ``True`` but the last array dimension is not of length 3. ValueError If ``start_label`` is not 0 or 1. ValueError If ``image`` contains unmasked NaN values. ValueError If ``image`` contains unmasked infinite values. ValueError If ``image`` is 2D but ``channel_axis`` is -1 (the default). Notes ----- * If `sigma > 0`, the image is smoothed using a Gaussian kernel prior to segmentation. * If `sigma` is scalar and `spacing` is provided, the kernel width is divided along each dimension by the spacing. For example, if ``sigma=1`` and ``spacing=[5, 1, 1]``, the effective `sigma` is ``[0.2, 1, 1]``. This ensures sensible smoothing for anisotropic images. * The image is rescaled to be in [0, 1] prior to processing (masked values are ignored). * Images of shape (M, N, 3) are interpreted as 2D RGB images by default. To interpret them as 3D with the last dimension having length 3, use `channel_axis=None`. * `start_label` is introduced to handle the issue [4]_. Label indexing starts at 1 by default. References ---------- .. [1] Radhakrishna Achanta, Appu Shaji, Kevin Smith, Aurelien Lucchi, Pascal Fua, and Sabine Süsstrunk, SLIC Superpixels Compared to State-of-the-art Superpixel Methods, TPAMI, May 2012. :DOI:`10.1109/TPAMI.2012.120` .. [2] https://www.epfl.ch/labs/ivrl/research/slic-superpixels/#SLICO .. [3] Irving, Benjamin. "maskSLIC: regional superpixel generation with application to local pathology characterisation in medical images.", 2016, :arXiv:`1606.09518` .. [4] https://github.com/scikit-image/scikit-image/issues/3722 Examples -------- >>> from skimage.segmentation import slic >>> from skimage.data import astronaut >>> img = astronaut() >>> segments = slic(img, n_segments=100, compactness=10) Increasing the compactness parameter yields more square regions: >>> segments = slic(img, n_segments=100, compactness=20) rNz channel_axis=z| indicates multichannel, which is not supported for a two-dimensional image; use channel_axis=None if the image is grayscaleT)copyrr@z.unmasked NaN values in image are not supportedz3unmasked infinite values in image are not supportedF.r?z/Lab colorspace conversion requires a RGB image.)rrzstart_label should be 0 or 1.uint8z*image and mask should have the same shape.zdInput image is 2D: spacing number of elements must be 2. In the future, a ValueError will be raised.) stacklevelz#Input image is 2D, but spacing has z elements (expected 2).rrz#Input image is 3D, but spacing has z elements (expected 3).z!spacing must be None or iterable.zbInput image is 2D: sigma number of elements must be 2. In the future, a ValueError will be raised.z!Input image is 2D, but sigma has z!Input image is 3D, but sigma has reflect)moderrB) ignore_color start_label)rd),r% ValueErrorr r _supported_float_typerastyperascontiguousarraybool expand_dims broadcast_torGr$maxisnanisinfrJr viewr>rXones isinstancerrLsizer FutureWarninginsert TypeErrorisscalarranylistr rKzerosrsummathprodr!r)"rM n_segments compactness max_num_itersigmaspacing convert2labenforce_connectivitymin_size_factormax_size_factor slic_zerordr,r] float_dtypemask_ image_valuesiminimaxuse_maskris_2dr.update_centroidsr7r;r-segmentsrCratiolabels segment_sizemin_sizemax_sizer<r<r=slicos                            r) rZr[rrNNTr\r?FrN)r{collections.abcrwarningsrnumpyrrscipy.cluster.vqrscipy.spatial.distancerr_sharedr _shared.filtersr colorr utilr r _slicrrr>rXchannel_as_last_axisrr<r<r<r=s,       : $