Module: future.graph
| Perform Normalized Graph cut on the Region Adjacency Graph. |
| Combine regions separated by weight less than threshold. |
Perform hierarchical merging of a RAG. | |
| Perform Normalized Graph cut on the Region Adjacency Graph. |
| Comouter RAG based on region boundaries |
| Compute the Region Adjacency Graph using mean colors. |
| Show a Region Adjacency Graph on an image. |
| The Region Adjacency Graph (RAG) of an image, subclasses networx.Graph |
cut_normalized
-
skimage.future.graph.cut_normalized(labels, rag, thresh=0.001, num_cuts=10, in_place=True, max_edge=1.0, *, random_state=None)
[source] -
Perform Normalized Graph cut on the Region Adjacency Graph.
Given an image’s labels and its similarity RAG, recursively perform a 2-way normalized cut on it. All nodes belonging to a subgraph that cannot be cut further are assigned a unique label in the output.
- Parameters
-
-
labelsndarray
-
The array of labels.
-
ragRAG
-
The region adjacency graph.
-
threshfloat
-
The threshold. A subgraph won’t be further subdivided if the value of the N-cut exceeds
thresh
. -
num_cutsint
-
The number or N-cuts to perform before determining the optimal one.
-
in_placebool
-
If set, modifies
rag
in place. For each noden
the function will set a new attributerag.nodes[n]['ncut label']
. -
max_edgefloat, optional
-
The maximum possible value of an edge in the RAG. This corresponds to an edge between identical regions. This is used to put self edges in the RAG.
-
random_stateint, RandomState instance or None, optional
-
If int, random_state is the seed used by the random number generator; If RandomState instance, random_state is the random number generator; If None, the random number generator is the RandomState instance used by
np.random
. The random state is used for the starting point ofscipy.sparse.linalg.eigsh
.
-
- Returns
-
-
outndarray
-
The new labeled array.
-
References
-
1
-
Shi, J.; Malik, J., “Normalized cuts and image segmentation”, Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 22, no. 8, pp. 888-905, August 2000.
Examples
>>> from skimage import data, segmentation >>> from skimage.future import graph >>> img = data.astronaut() >>> labels = segmentation.slic(img) >>> rag = graph.rag_mean_color(img, labels, mode='similarity') >>> new_labels = graph.cut_normalized(labels, rag)
cut_threshold
-
skimage.future.graph.cut_threshold(labels, rag, thresh, in_place=True)
[source] -
Combine regions separated by weight less than threshold.
Given an image’s labels and its RAG, output new labels by combining regions whose nodes are separated by a weight less than the given threshold.
- Parameters
-
-
labelsndarray
-
The array of labels.
-
ragRAG
-
The region adjacency graph.
-
threshfloat
-
The threshold. Regions connected by edges with smaller weights are combined.
-
in_placebool
-
If set, modifies
rag
in place. The function will remove the edges with weights less thatthresh
. If set toFalse
the function makes a copy ofrag
before proceeding.
-
- Returns
-
-
outndarray
-
The new labelled array.
-
References
-
1
-
Alain Tremeau and Philippe Colantoni “Regions Adjacency Graph Applied To Color Image Segmentation” DOI:10.1109/83.841950
Examples
>>> from skimage import data, segmentation >>> from skimage.future import graph >>> img = data.astronaut() >>> labels = segmentation.slic(img) >>> rag = graph.rag_mean_color(img, labels) >>> new_labels = graph.cut_threshold(labels, rag, 10)
merge_hierarchical
-
skimage.future.graph.merge_hierarchical(labels, rag, thresh, rag_copy, in_place_merge, merge_func, weight_func)
[source] -
Perform hierarchical merging of a RAG.
Greedily merges the most similar pair of nodes until no edges lower than
thresh
remain.- Parameters
-
-
labelsndarray
-
The array of labels.
-
ragRAG
-
The Region Adjacency Graph.
-
threshfloat
-
Regions connected by an edge with weight smaller than
thresh
are merged. -
rag_copybool
-
If set, the RAG copied before modifying.
-
in_place_mergebool
-
If set, the nodes are merged in place. Otherwise, a new node is created for each merge..
-
merge_funccallable
-
This function is called before merging two nodes. For the RAG
graph
while mergingsrc
anddst
, it is called as followsmerge_func(graph, src, dst)
. -
weight_funccallable
-
The function to compute the new weights of the nodes adjacent to the merged node. This is directly supplied as the argument
weight_func
tomerge_nodes
.
-
- Returns
-
-
outndarray
-
The new labeled array.
-
ncut
-
skimage.future.graph.ncut(labels, rag, thresh=0.001, num_cuts=10, in_place=True, max_edge=1.0, *, random_state=None)
[source] -
Perform Normalized Graph cut on the Region Adjacency Graph.
Given an image’s labels and its similarity RAG, recursively perform a 2-way normalized cut on it. All nodes belonging to a subgraph that cannot be cut further are assigned a unique label in the output.
- Parameters
-
-
labelsndarray
-
The array of labels.
-
ragRAG
-
The region adjacency graph.
-
threshfloat
-
The threshold. A subgraph won’t be further subdivided if the value of the N-cut exceeds
thresh
. -
num_cutsint
-
The number or N-cuts to perform before determining the optimal one.
-
in_placebool
-
If set, modifies
rag
in place. For each noden
the function will set a new attributerag.nodes[n]['ncut label']
. -
max_edgefloat, optional
-
The maximum possible value of an edge in the RAG. This corresponds to an edge between identical regions. This is used to put self edges in the RAG.
-
random_stateint, RandomState instance or None, optional
-
If int, random_state is the seed used by the random number generator; If RandomState instance, random_state is the random number generator; If None, the random number generator is the RandomState instance used by
np.random
. The random state is used for the starting point ofscipy.sparse.linalg.eigsh
.
-
- Returns
-
-
outndarray
-
The new labeled array.
-
References
-
1
-
Shi, J.; Malik, J., “Normalized cuts and image segmentation”, Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 22, no. 8, pp. 888-905, August 2000.
Examples
>>> from skimage import data, segmentation >>> from skimage.future import graph >>> img = data.astronaut() >>> labels = segmentation.slic(img) >>> rag = graph.rag_mean_color(img, labels, mode='similarity') >>> new_labels = graph.cut_normalized(labels, rag)
rag_boundary
-
skimage.future.graph.rag_boundary(labels, edge_map, connectivity=2)
[source] -
Comouter RAG based on region boundaries
Given an image’s initial segmentation and its edge map this method constructs the corresponding Region Adjacency Graph (RAG). Each node in the RAG represents a set of pixels within the image with the same label in
labels
. The weight between two adjacent regions is the average value inedge_map
along their boundary.-
labelsndarray
-
The labelled image.
-
edge_mapndarray
-
This should have the same shape as that of
labels
. For all pixels along the boundary between 2 adjacent regions, the average value of the corresponding pixels inedge_map
is the edge weight between them. -
connectivityint, optional
-
Pixels with a squared distance less than
connectivity
from each other are considered adjacent. It can range from 1 tolabels.ndim
. Its behavior is the same asconnectivity
parameter inscipy.ndimage.filters.generate_binary_structure
.
Examples
>>> from skimage import data, segmentation, filters, color >>> from skimage.future import graph >>> img = data.chelsea() >>> labels = segmentation.slic(img) >>> edge_map = filters.sobel(color.rgb2gray(img)) >>> rag = graph.rag_boundary(labels, edge_map)
-
rag_mean_color
-
skimage.future.graph.rag_mean_color(image, labels, connectivity=2, mode='distance', sigma=255.0)
[source] -
Compute the Region Adjacency Graph using mean colors.
Given an image and its initial segmentation, this method constructs the corresponding Region Adjacency Graph (RAG). Each node in the RAG represents a set of pixels within
image
with the same label inlabels
. The weight between two adjacent regions represents how similar or dissimilar two regions are depending on themode
parameter.- Parameters
-
-
imagendarray, shape(M, N, […, P,] 3)
-
Input image.
-
labelsndarray, shape(M, N, […, P])
-
The labelled image. This should have one dimension less than
image
. Ifimage
has dimensions(M, N, 3)
labels
should have dimensions(M, N)
. -
connectivityint, optional
-
Pixels with a squared distance less than
connectivity
from each other are considered adjacent. It can range from 1 tolabels.ndim
. Its behavior is the same asconnectivity
parameter inscipy.ndimage.generate_binary_structure
. -
mode{‘distance’, ‘similarity’}, optional
-
The strategy to assign edge weights.
‘distance’ : The weight between two adjacent regions is the \(|c_1 - c_2|\), where \(c_1\) and \(c_2\) are the mean colors of the two regions. It represents the Euclidean distance in their average color.
‘similarity’ : The weight between two adjacent is \(e^{-d^2/sigma}\) where \(d=|c_1 - c_2|\), where \(c_1\) and \(c_2\) are the mean colors of the two regions. It represents how similar two regions are.
-
sigmafloat, optional
-
Used for computation when
mode
is “similarity”. It governs how close to each other two colors should be, for their corresponding edge weight to be significant. A very large value ofsigma
could make any two colors behave as though they were similar.
-
- Returns
-
-
outRAG
-
The region adjacency graph.
-
References
-
1
-
Alain Tremeau and Philippe Colantoni “Regions Adjacency Graph Applied To Color Image Segmentation” DOI:10.1109/83.841950
Examples
>>> from skimage import data, segmentation >>> from skimage.future import graph >>> img = data.astronaut() >>> labels = segmentation.slic(img) >>> rag = graph.rag_mean_color(img, labels)
show_rag
-
skimage.future.graph.show_rag(labels, rag, image, border_color='black', edge_width=1.5, edge_cmap='magma', img_cmap='bone', in_place=True, ax=None)
[source] -
Show a Region Adjacency Graph on an image.
Given a labelled image and its corresponding RAG, show the nodes and edges of the RAG on the image with the specified colors. Edges are displayed between the centroid of the 2 adjacent regions in the image.
- Parameters
-
-
labelsndarray, shape (M, N)
-
The labelled image.
-
ragRAG
-
The Region Adjacency Graph.
-
imagendarray, shape (M, N[, 3])
-
Input image. If
colormap
isNone
, the image should be in RGB format. -
border_colorcolor spec, optional
-
Color with which the borders between regions are drawn.
-
edge_widthfloat, optional
-
The thickness with which the RAG edges are drawn.
-
edge_cmapmatplotlib.colors.Colormap, optional
-
Any matplotlib colormap with which the edges are drawn.
-
img_cmapmatplotlib.colors.Colormap, optional
-
Any matplotlib colormap with which the image is draw. If set to
None
the image is drawn as it is. -
in_placebool, optional
-
If set, the RAG is modified in place. For each node
n
the function will set a new attributerag.nodes[n]['centroid']
. -
axmatplotlib.axes.Axes, optional
-
The axes to draw on. If not specified, new axes are created and drawn on.
-
- Returns
-
-
lcmatplotlib.collections.LineCollection
-
A colection of lines that represent the edges of the graph. It can be passed to the
matplotlib.figure.Figure.colorbar()
function.
-
Examples
>>> from skimage import data, segmentation >>> from skimage.future import graph >>> import matplotlib.pyplot as plt >>> >>> img = data.coffee() >>> labels = segmentation.slic(img) >>> g = graph.rag_mean_color(img, labels) >>> lc = graph.show_rag(labels, g, img) >>> cbar = plt.colorbar(lc)
RAG
-
class skimage.future.graph.RAG(label_image=None, connectivity=1, data=None, **attr)
[source] -
Bases:
networkx.classes.graph.Graph
The Region Adjacency Graph (RAG) of an image, subclasses networx.Graph
- Parameters
-
-
label_imagearray of int
-
An initial segmentation, with each region labeled as a different integer. Every unique value in
label_image
will correspond to a node in the graph. -
connectivityint in {1, …, label_image.ndim}, optional
-
The connectivity between pixels in
label_image
. For a 2D image, a connectivity of 1 corresponds to immediate neighbors up, down, left, and right, while a connectivity of 2 also includes diagonal neighbors. Seescipy.ndimage.generate_binary_structure
. -
datanetworkx Graph specification, optional
-
Initial or additional edges to pass to the NetworkX Graph constructor. See
networkx.Graph
. Valid edge specifications include edge list (list of tuples), NumPy arrays, and SciPy sparse matrices. -
**attrkeyword arguments, optional
-
Additional attributes to add to the graph.
-
-
__init__(label_image=None, connectivity=1, data=None, **attr)
[source] -
Initialize a graph with edges, name, or graph attributes.
- Parameters
-
-
incoming_graph_datainput graph (optional, default: None)
-
Data to initialize graph. If None (default) an empty graph is created. The data can be an edge list, or any NetworkX graph object. If the corresponding optional Python packages are installed the data can also be a NumPy matrix or 2d ndarray, a SciPy sparse matrix, or a PyGraphviz graph.
-
attrkeyword arguments, optional (default= no attributes)
-
Attributes to add to graph as key=value pairs.
-
See also
-
convert
Examples
>>> G = nx.Graph() # or DiGraph, MultiGraph, MultiDiGraph, etc >>> G = nx.Graph(name="my graph") >>> e = [(1, 2), (2, 3), (3, 4)] # list of edges >>> G = nx.Graph(e)
Arbitrary graph attribute pairs (key=value) may be assigned
>>> G = nx.Graph(e, day="Friday") >>> G.graph {'day': 'Friday'}
-
add_edge(u, v, attr_dict=None, **attr)
[source] -
Add an edge between
u
andv
while updating max node id.See also
networkx.Graph.add_edge()
.
-
add_node(n, attr_dict=None, **attr)
[source] -
Add node
n
while updating the maximum node id.See also
networkx.Graph.add_node()
.
-
copy()
[source] -
Copy the graph with its max node id.
See also
networkx.Graph.copy()
.
-
fresh_copy()
[source] -
Return a fresh copy graph with the same data structure.
A fresh copy has no nodes, edges or graph attributes. It is the same data structure as the current graph. This method is typically used to create an empty version of the graph.
This is required when subclassing Graph with networkx v2 and does not cause problems for v1. Here is more detail from the network migrating from 1.x to 2.x document:
With the new GraphViews (SubGraph, ReversedGraph, etc) you can't assume that ``G.__class__()`` will create a new instance of the same graph type as ``G``. In fact, the call signature for ``__class__`` differs depending on whether ``G`` is a view or a base class. For v2.x you should use ``G.fresh_copy()`` to create a null graph of the correct type---ready to fill with nodes and edges.
-
merge_nodes(src, dst, weight_func=<function min_weight>, in_place=True, extra_arguments=[], extra_keywords={})
[source] -
Merge node
src
anddst
.The new combined node is adjacent to all the neighbors of
src
anddst
.weight_func
is called to decide the weight of edges incident on the new node.- Parameters
-
-
src, dstint
-
Nodes to be merged.
-
weight_funccallable, optional
-
Function to decide the attributes of edges incident on the new node. For each neighbor
n
forsrc and `dst
,weight_func
will be called as follows:weight_func(src, dst, n, *extra_arguments, **extra_keywords)
.src
,dst
andn
are IDs of vertices in the RAG object which is in turn a subclass ofnetworkx.Graph
. It is expected to return a dict of attributes of the resulting edge. -
in_placebool, optional
-
If set to
True
, the merged node has the iddst
, else merged node has a new id which is returned. -
extra_argumentssequence, optional
-
The sequence of extra positional arguments passed to
weight_func
. -
extra_keywordsdictionary, optional
-
The dict of keyword arguments passed to the
weight_func
.
-
- Returns
-
-
idint
-
The id of the new node.
-
Notes
If
in_place
isFalse
the resulting node has a new id, rather thandst
.
-
next_id()
[source] -
Returns the
id
for the new node to be inserted.The current implementation returns one more than the maximum
id
.- Returns
-
-
idint
-
The
id
of the new node to be inserted.
-
© 2019 the scikit-image team
Licensed under the BSD 3-clause License.
https://scikit-image.org/docs/0.18.x/api/skimage.future.graph.html