1i.maxlik(1) GRASS GIS User's Manual i.maxlik(1)
2
3
4
6 i.maxlik - Classifies the cell spectral reflectances in imagery data.
7 Classification is based on the spectral signature information generated
8 by either i.cluster, g.gui.iclass, or i.gensig.
9
11 imagery, classification, Maximum Likelihood Classification, MLC
12
14 i.maxlik
15 i.maxlik --help
16 i.maxlik group=name subgroup=name signaturefile=name output=name [re‐
17 ject=name] [--overwrite] [--help] [--verbose] [--quiet] [--ui]
18
19 Flags:
20 --overwrite
21 Allow output files to overwrite existing files
22
23 --help
24 Print usage summary
25
26 --verbose
27 Verbose module output
28
29 --quiet
30 Quiet module output
31
32 --ui
33 Force launching GUI dialog
34
35 Parameters:
36 group=name [required]
37 Name of input imagery group
38
39 subgroup=name [required]
40 Name of input imagery subgroup
41
42 signaturefile=name [required]
43 Name of input file containing signatures
44 Generated by either i.cluster, g.gui.iclass, or i.gensig
45
46 output=name [required]
47 Name for output raster map holding classification results
48
49 reject=name
50 Name for output raster map holding reject threshold results
51
53 i.maxlik is a maximum-likelihood discriminant analysis classifier. It
54 can be used to perform the second step in either an unsupervised or a
55 supervised image classification.
56
57 Either image classification methods are performed in two steps. The
58 first step in an unsupervised image classification is performed by
59 i.cluster; the first step in a supervised classification is executed by
60 the GRASS program g.gui.iclass (or by providing any other raster map
61 with already existing training areas). In both cases, the second step
62 in the image classification procedure is performed by i.maxlik.
63
64 In an unsupervised classification, the maximum-likelihood classifier
65 uses the cluster means and covariance matrices from the i.cluster sig‐
66 nature file to determine to which category (spectral class) each cell
67 in the image has the highest probability of belonging. In a supervised
68 image classification, the maximum-likelihood classifier uses the region
69 means and covariance matrices from the spectral signature file gener‐
70 ated by g.gui.iclass, based on regions (groups of image pixels) chosen
71 by the user, to determine to which category each cell in the image has
72 the highest probability of belonging.
73
74 In either case, the raster map output by i.maxlik is a classified image
75 in which each cell has been assigned to a spectral class (i.e., a cate‐
76 gory). The spectral classes (categories) can be related to specific
77 land cover types on the ground.
78
80 The maximum-likelihood classifier assumes that the spectral signatures
81 for each class (category) in each band file are normally distributed
82 (i.e., Gaussian in nature). Algorithms, such as i.cluster,
83 g.gui.iclass, or i.gensig, however, can create signatures that are not
84 valid distributed (more likely with g.gui.iclass). If this occurs,
85 i.maxlik will reject them and display a warning message.
86
87 The signature file (signaturefile) contains the cluster and covariance
88 matrices that were calculated by the GRASS program i.cluster (or the
89 region means and covariance matrices generated by g.gui.iclass, if the
90 user runs a supervised classification). These spectral signatures are
91 what determine the categories (classes) to which image pixels will be
92 assigned during the classification process.
93
94 The optional name of a reject raster map holds the reject threshold re‐
95 sults. This is the result of a chi square test on each discriminant re‐
96 sult at various threshold levels of confidence to determine at what
97 confidence level each cell classified (categorized). It is the reject
98 threshold map layer, and contains the index to one calculated confi‐
99 dence level for each classified cell in the classified image. 16 confi‐
100 dence intervals are predefined, and the reject map is to be interpreted
101 as 1 = keep and 16 = reject. One of the possible uses for this map
102 layer is as a mask, to identify cells in the classified image that have
103 a low probability (high reject index) of being assigned to the correct
104 class.
105
107 Second part of the unsupervised classification of a LANDSAT subscene
108 (VIZ, NIR, MIR channels) in North Carolina (see i.cluster manual page
109 for the first part of the example):
110 # using here the signaturefile created by i.cluster
111 i.maxlik group=lsat7_2002 subgroup=res_30m \
112 signaturefile=cluster_lsat2002 \
113 output=lsat7_2002_cluster_classes reject=lsat7_2002_cluster_reject
114 # visually check result
115 d.mon wx0
116 d.rast.leg lsat7_2002_cluster_classes
117 d.rast.leg lsat7_2002_cluster_reject
118 # see how many pixels were rejected at given levels
119 r.report lsat7_2002_cluster_reject units=k,p
120 # optionally, filter out pixels with high level of rejection
121 # here we remove pixels of at least 90% of rejection probability, i.e. categories 12-16
122 r.mapcalc "lsat7_2002_cluster_classes_filtered = \
123 if(lsat7_2002_cluster_reject <= 12, lsat7_2002_cluster_classes, null())"
124
125 RGB composite of input data
126
127 Output raster map with pixels classified (10 classes)
128
129 Output raster map with rejection probability values (pixel classifica‐
130 tion confidence levels)
131
133 Image processing and Image classification wiki pages and for historical
134 reference also the GRASS GIS 4 Image Processing manual
135
136 g.gui.iclass, i.cluster, i.gensig, i.group, i.segment, i.smap, r.kappa
137
139 Michael Shapiro, U.S.Army Construction Engineering Research Laboratory
140 Tao Wen, University of Illinois at Urbana-Champaign, Illinois
141 Semantic label support: Maris Nartiss, University of Latvia
142
144 Available at: i.maxlik source code (history)
145
146 Accessed: Saturday Oct 28 18:19:05 2023
147
148 Main index | Imagery index | Topics index | Keywords index | Graphical
149 index | Full index
150
151 © 2003-2023 GRASS Development Team, GRASS GIS 8.3.1 Reference Manual
152
153
154
155GRASS 8.3.1 i.maxlik(1)