1i.cluster(1) GRASS GIS User's Manual i.cluster(1)
2
6 i.cluster - Generates spectral signatures for land cover types in an
7 image using a clustering algorithm.
8 The resulting signature file is used as input for i.maxlik, to generate
9 an unsupervised image classification.
10
12 imagery, classification, signatures
13
15 i.cluster
16 i.cluster --help
17 i.cluster group=name subgroup=name signaturefile=name classes=integer
18 [seed=name] [sample=rows,cols] [iterations=integer] [conver‐
19 gence=float] [separation=float] [min_size=integer] [report‐
20 file=name] [--overwrite] [--help] [--verbose] [--quiet] [--ui]
21 Flags:
23 --overwrite
24 Allow output files to overwrite existing files
25 --help
27 Print usage summary
28 --verbose
30 Verbose module output
31 --quiet
33 Quiet module output
34 --ui
36 Force launching GUI dialog
37 Parameters:
39 group=name [required]
40 Name of input imagery group
41 subgroup=name [required]
43 Name of input imagery subgroup
44 signaturefile=name [required]
46 Name for output file containing result signatures
47 classes=integer [required]
49 Initial number of classes
50 Options: 1-255
51 seed=name
53 Name of file containing initial signatures
54 sample=rows,cols
56 Number of rows and columns over which a sample pixel is taken
57 iterations=integer
59 Maximum number of iterations
60 Default: 30
61 convergence=float
63 Percent convergence
64 Options: 0-100
65 Default: 98.0
66 separation=float
68 Cluster separation
69 Default: 0.0
70 min_size=integer
72 Minimum number of pixels in a class
73 Default: 17
74 reportfile=name
76 Name for output file containing final report
77
79 i.cluster performs the first pass in the two-pass unsupervised classi‐
80 fication of imagery, while the GRASS module i.maxlik executes the sec‐
81 ond pass. Both commands must be run to complete the unsupervised clas‐
82 sification.
83 i.cluster is a clustering algorithm (a modification of the k-means
85 clustering algorithm) that reads through the (raster) imagery data and
86 builds pixel clusters based on the spectral reflectances of the pixels
87 (see Figure). The pixel clusters are imagery categories that can be
88 related to land cover types on the ground. The spectral distributions
89 of the clusters (e.g., land cover spectral signatures) are influenced
90 by six parameters set by the user. A relevant parameter set by the user
91 is the initial number of clusters to be discriminated.
92 Fig.: Land use/land cover clustering of LANDSAT scene (sim‐
94 plified)
95 i.cluster starts by generating spectral signatures for this number of
98 clusters and "attempts" to end up with this number of clusters during
99 the clustering process. The resulting number of clusters and their
100 spectral distributions, however, are also influenced by the range of
101 the spectral values (category values) in the image files and the other
102 parameters set by the user. These parameters are: the minimum cluster
103 size, minimum cluster separation, the percent convergence, the maximum
104 number of iterations, and the row and column sampling intervals.
105 The cluster spectral signatures that result are composed of cluster
107 means and covariance matrices. These cluster means and covariance
108 matrices are used in the second pass (i.maxlik) to classify the image.
109 The clusters or spectral classes result can be related to land cover
110 types on the ground. The user has to specify the name of group file,
111 the name of subgroup file, the name of a file to contain result signa‐
112 tures, the initial number of clusters to be discriminated, and option‐
113 ally other parameters (see below) where the group should contain the
114 imagery files that the user wishes to classify. The subgroup is a sub‐
115 set of this group. The user must create a group and subgroup by run‐
116 ning the GRASS program i.group before running i.cluster. The subgroup
117 should contain only the imagery band files that the user wishes to
118 classify. Note that this subgroup must contain more than one band
119 file. The purpose of the group and subgroup is to collect map layers
120 for classification or analysis. The signaturefile is the file to con‐
121 tain result signatures which can be used as input for i.maxlik. The
122 classes value is the initial number of clusters to be discriminated;
123 any parameter values left unspecified are set to their default values.
124 Parameters:
126 group=name
127 The name of the group file which contains the imagery files that
128 the user wishes to classify.
129 subgroup=name
131 The name of the subset of the group specified in group option,
132 which must contain only imagery band files and more than one band
133 file. The user must create a group and a subgroup by running the
134 GRASS program i.group before running i.cluster.
135 signaturefile=name
137 The name assigned to output signature file which contains signa‐
138 tures of classes and can be used as the input file for the GRASS
139 program i.maxlik for an unsupervised classification.
140 classes=value
142 The number of clusters that will initially be identified in the
143 clustering process before the iterations begin.
144 seed=name
146 The name of a seed signature file is optional. The seed signatures
147 are signatures that contain cluster means and covariance matrices
148 which were calculated prior to the current run of i.cluster. They
149 may be acquired from a previously run of i.cluster or from a super‐
150 vised classification signature training site section (e.g., using
151 the signature file output by g.gui.iclass). The purpose of seed
152 signatures is to optimize the cluster decision boundaries (means)
153 for the number of clusters specified.
154 sample=rows,cols
156 These numbers are optional with default values based on the size of
157 the data set such that the total pixels to be processed is approxi‐
158 mately 10,000 (consider round up). The smaller these numbers, the
159 larger the sample size used to generate the signatures for the
160 classes defined.
161 iterations=value
163 This parameter determines the maximum number of iterations which is
164 greater than the number of iterations predicted to achieve the
165 optimum percent convergence. The default value is 30. If the number
166 of iterations reaches the maximum designated by the user; the user
167 may want to rerun i.cluster with a higher number of iterations (see
168 reportfile).
169 Default: 30
170 convergence=value
172 A high percent convergence is the point at which cluster means
173 become stable during the iteration process. The default value is
174 98.0 percent. When clusters are being created, their means con‐
175 stantly change as pixels are assigned to them and the means are
176 recalculated to include the new pixel. After all clusters have
177 been created, i.cluster begins iterations that change cluster means
178 by maximizing the distances between them. As these means shift, a
179 higher and higher convergence is approached. Because means will
180 never become totally static, a percent convergence and a maximum
181 number of iterations are supplied to stop the iterative process.
182 The percent convergence should be reached before the maximum number
183 of iterations. If the maximum number of iterations is reached, it
184 is probable that the desired percent convergence was not reached.
185 The number of iterations is reported in the cluster statistics in
186 the report file (see reportfile).
187 Default: 98.0
188 separation=value
190 This is the minimum separation below which clusters will be merged
191 in the iteration process. The default value is 0.0. This is an
192 image-specific number (a "magic" number) that depends on the image
193 data being classified and the number of final clusters that are
194 acceptable. Its determination requires experimentation. Note that
195 as the minimum class (or cluster) separation is increased, the max‐
196 imum number of iterations should also be increased to achieve this
197 separation with a high percentage of convergence (see convergence).
198 Default: 0.0
199 min_size=value
201 This is the minimum number of pixels that will be used to define a
202 cluster, and is therefore the minimum number of pixels for which
203 means and covariance matrices will be calculated.
204 Default: 17
205 reportfile=name
207 The reportfile is an optional parameter which contains the result,
208 i.e., the statistics for each cluster. Also included are the
209 resulting percent convergence for the clusters, the number of iter‐
210 ations that was required to achieve the convergence, and the sepa‐
211 rability matrix.
212
214 Sampling method
215 i.cluster does not cluster all pixels, but only a sample (see parameter
216 sample). The result of that clustering is not that all pixels are
217 assigned to a given cluster; essentially, only signatures which are
218 representative of a given cluster are generated. When running i.cluster
219 on the same data asking for the same number of classes, but with dif‐
220 ferent sample sizes, likely slightly different signatures for each
221 cluster are obtained at each run.
222 Algorithm used for i.cluster
224 The algorithm uses input parameters set by the user on the initial num‐
225 ber of clusters, the minimum distance between clusters, and the corre‐
226 spondence between iterations which is desired, and minimum size for
227 each cluster. It also asks if all pixels to be clustered, or every
228 "x"th row and "y"th column (sampling), the correspondence between iter‐
229 ations desired, and the maximum number of iterations to be carried out.
230 In the 1st pass, initial cluster means for each band are defined by
232 giving the first cluster a value equal to the band mean minus its stan‐
233 dard deviation, and the last cluster a value equal to the band mean
234 plus its standard deviation, with all other cluster means distributed
235 equally spaced in between these. Each pixel is then assigned to the
236 class which it is closest to, distance being measured as Euclidean dis‐
237 tance. All clusters less than the user-specified minimum distance are
238 then merged. If a cluster has less than the user-specified minimum num‐
239 ber of pixels, all those pixels are again reassigned to the next near‐
240 est cluster. New cluster means are calculated for each band as the
241 average of raster pixel values in that band for all pixels present in
242 that cluster.
243 In the 2nd pass, pixels are then again reassigned to clusters based on
245 new cluster means. The cluster means are then again recalculated. This
246 process is repeated until the correspondence between iterations reaches
247 a user-specified level, or till the maximum number of iterations speci‐
248 fied is over, whichever comes first.
249
251 Preparing the statistics for unsupervised classification of a LANDSAT
252 subscene in North Carolina:
253 g.region raster=lsat7_2002_10 -p
254 # store VIZ, NIR, MIR into group/subgroup (leaving out TIR)
255 i.group group=lsat7_2002 subgroup=lsat7_2002 \
256 input=lsat7_2002_10,lsat7_2002_20,lsat7_2002_30,lsat7_2002_40,lsat7_2002_50,lsat7_2002_70
257 # generate signature file and report
258 i.cluster group=lsat7_2002 subgroup=lsat7_2002 \
259 signaturefile=sig_cluster_lsat2002 \
260 classes=10 reportfile=rep_clust_lsat2002.txt
261 To complete the unsupervised classification, i.maxlik is subsequently
262 used. See example in its manual page.
263
265 · Image classification wiki page
266 · Historical reference also the GRASS GIS 4 Image Processing man‐
268 ual (PDF)
269 · Wikipedia article on k-means clustering (note that i.cluster
271 uses a modification of the k-means clustering algorithm)
272 g.gui.iclass, i.group, i.gensig, i.maxlik, i.segment, i.smap, r.kappa
274
276 Michael Shapiro, U.S. Army Construction Engineering Research Laboratory
277 Tao Wen, University of Illinois at Urbana-Champaign, Illinois
278
280 Available at: i.cluster source code (history)
281 Main index | Imagery index | Topics index | Keywords index | Graphical
283 index | Full index
284 © 2003-2020 GRASS Development Team, GRASS GIS 7.8.5 Reference Manual
286GRASS 7.8.5 i.cluster(1)