1i.maxlik(1) Grass User's Manual i.maxlik(1)
2
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, i.class, or i.gensig.
9
11 imagery
12
14 i.maxlik
15 i.maxlik help
16 i.maxlik [-q] group=name subgroup=string sigfile=string class=string
17 [reject=string] [--verbose] [--quiet]
18 Flags:
20 -q
21 Run quietly
22 --verbose
24 Verbose module output
25 --quiet
27 Quiet module output
28 Parameters:
30 group=name
31 Imagery group to be classified
32 subgroup=string
34 Subgroup containing image files to be classified
35 sigfile=string
37 Signatures to use for classification
38 class=string
40 Raster map to hold classification results
41 reject=string
43 Raster map to hold reject threshold results
44
46 i.maxlik is a maximum-likelihood discriminant analysis classifier. It
47 can be used to perform the second step in either an unsupervised or a
48 supervised image classification.
49 Either image classification methods are performed in two steps. The
51 first step in an unsupervised image classification is performed by
52 i.cluster; the first step in a supervised classification is executed by
53 the GRASS program i.class. In both cases, the second step in the image
54 classification procedure is performed by i.maxlik.
55 In an unsupervised classification, the maximum-likelihood classifier
57 uses the cluster means and covariance matrices from the i.cluster sig‐
58 nature file to determine to which category (spectral class) each cell
59 in the image has the highest probability of belonging. In a supervised
60 image classification, the maximum-likelihood classifier uses the region
61 means and covariance matrices from the spectral signature file gener‐
62 ated by i.class, based on regions (groups of image pixels) chosen by
63 the user, to determine to which category each cell in the image has the
64 highest probability of belonging.
65 In either case, the raster map layer output by i.maxlik is a classified
67 image in which each cell has been assigned to a spectral class (i.e., a
68 category). The spectral classes (categories) can be related to spe‐
69 cific land cover types on the ground.
70 The program will run non-interactively if the user specifies the names
72 of raster map layers, i.e., group and subgroup names, seed signature
73 file name, result classification file name, and any combination of non-
74 required options in the command line, using the form i.maxlik[-q]
75 group=name subgroup=name sigfile=name class=name [reject=name]
76 where each flag and options have the meanings stated below.
78 Alternatively, the user can simply type i.maxlik in the command line
80 without program arguments. In this case the user will be prompted for
81 the program parameter settings; the program will run foreground.
82
84 Flags:
85 -q
86 Run quietly, without printing program messages to standard out‐
87 put.
88 Parameters:
90 group=name
91 The imagery group contains the subgroup to be classified.
92 subgroup=name
94 The subgroup contains image files, which were used to create the
95 signature file in the program i.cluster, i.class, or i.gensig to
96 be classified.
97 sigfile=name
99 The name of the signatures to be used for the classification.
100 The signature file contains the cluster and covariance matrices
101 that were calculated by the GRASS program i.cluster (or the
102 region means and covariance matrices generated by i.class, if
103 the user runs a supervised classification). These spectral sig‐
104 natures are what determine the categories (classes) to which
105 image pixels will be assigned during the classification process.
106 class=name
108 The name of a raster map holds the classification results. This
109 new raster map layer will contain categories that can be related
110 to land cover categories on the ground.
111 reject=name
113 The optional name of a raster map holds the reject threshold
114 results. This is the result of a chi square test on each dis‐
115 criminant result at various threshold levels of confidence to
116 determine at what confidence level each cell classified (catego‐
117 rized). It is the reject threshold map layer, and contains one
118 calculated confidence level for each classified cell in the
119 classified image. One of the possible uses for this map layer is
120 as a mask, to identify cells in the classified image that have
121 the lowest probability of being assigned to the correct class.
122
124 The maximum-likelihood classifier assumes that the spectral signatures
125 for each class (category) in each band file are normally distributed
126 (i.e., Gaussian in nature). Algorithms, such as i.cluster, i.class, or
127 i.gensig, however, can create signatures that are not valid distributed
128 (more likely with i.class). If this occurs, i.maxlik will reject them
129 and display a warning message.
130 This program runs interactively if the user types i.maxlik only. If the
132 user types i.maxlik along with all required options, it will overwrite
133 the classified raster map without prompting if this map existed.
134
136 The GRASS 4 Image Processing manual
137 i.class
139 i.cluster
140 i.gensig
141 i.group
142
144 Michael Shapiro, U.S.Army Construction Engineering Research Laboratory
145 Tao Wen, University of Illinois at Urbana-Champaign, Illinois
146 Last changed: $Date: 2007-06-14 14:18:14 +0200 (Thu, 14 Jun 2007) $
148 Full index
150 © 2003-2008 GRASS Development Team
152GRASS 6.3.0 i.maxlik(1)