1r.kappa(1) Grass User's Manual r.kappa(1)
2
3
4
6 r.kappa - Calculates error matrix and kappa parameter for accuracy
7 assessment of classification result.
8
10 raster, statistics, classification
11
13 r.kappa
14 r.kappa --help
15 r.kappa [-wh] classification=name reference=name [output=name]
16 [title=string] [--overwrite] [--help] [--verbose] [--quiet]
17 [--ui]
18
19 Flags:
20 -w
21 Wide report
22 132 columns (default: 80)
23
24 -h
25 No header in the report
26
27 --overwrite
28 Allow output files to overwrite existing files
29
30 --help
31 Print usage summary
32
33 --verbose
34 Verbose module output
35
36 --quiet
37 Quiet module output
38
39 --ui
40 Force launching GUI dialog
41
42 Parameters:
43 classification=name [required]
44 Name of raster map containing classification result
45
46 reference=name [required]
47 Name of raster map containing reference classes
48
49 output=name
50 Name for output file containing error matrix and kappa
51 If not given write to standard output
52
53 title=string
54 Title for error matrix and kappa
55 Default: ACCURACY ASSESSMENT
56
58 r.kappa tabulates the error matrix of classification result by crossing
59 classified map layer with respect to reference map layer. Both overall
60 kappa (accompanied by its variance) and conditional kappa values are
61 calculated. This analysis program respects the current geographic
62 region and mask settings.
63
64 r.kappa calculates the error matrix of the two map layers and prepares
65 the table from which the report is to be created. kappa values for
66 overall and each classes are computed along with their variances. Also
67 percent of commission and ommission error, total correct classified
68 result by pixel counts, total area in pixel counts and percentage of
69 overall correctly classified pixels are tabulated.
70
71 The report will be write to an output file which is in plain text for‐
72 mat and named by user at prompt of running the program.
73
74 The body of the report is arranged in panels. The classified result
75 map layer categories is arranged along the vertical axis of the table,
76 while the reference map layer categories along the horizontal axis.
77 Each panel has a maximum of 5 categories (9 if wide format) across the
78 top. In addition, the last column of the last panel reflects a cross
79 total of each column for each row. All of the categories of the map
80 layer arranged along the vertical axis, i.e., the reference map layer,
81 are included in each panel. There is a total at the bottom of each
82 column representing the sum of all the rows in that column.
83
85 It is recommended to reclassify categories of classified result map
86 layer into a more manageable number before running r.kappa on the clas‐
87 sified raster map layer. Because r.kappa calculates and then reports
88 information for each and every category.
89
90 NA’s in output file mean non-applicable in case MASK exists.
91
92 The Estimated kappa value in r.kappa is the value only for one class,
93 i.e. the observed agreement between the classifications for those
94 observations that have been classified by classifier 1 into the class
95 i. In other words, here the choice of reference is important.
96
97 It is calculated as:
98
99 kpp[i] = (pii[i] - pi[i] * pj[i]) / (pi[i] - pi[i] * pj[i]);
100
101 where=
102
103 · pii[i] is the probability of agreement (i.e. number of pixels
104 for which there is agreement divided by total number of
105 assessed pixels)
106
107 · Pi[i] is the probability of classification i having classified
108 the point as i
109
110 · Pj[i] is the probability of classification j having classified
111 the point as i.
112
114 Example for North Carolina sample dataset:
115 g.region raster=landclass96 -p
116 r.kappa -w classification=landuse96_28m reference=landclass96
117
118 Verification of classified LANDSAT scene against training areas:
119 r.kappa -w classification=lsat7_2002_classes reference=training
120
122 g.region, r.category, r.mask, r.reclass, r.report, r.stats
123
125 Tao Wen, University of Illinois at Urbana-Champaign, Illinois
126
127 Last changed: $Date: 2018-10-18 21:13:18 +0200 (Thu, 18 Oct 2018) $
128
130 Available at: r.kappa source code (history)
131
132 Main index | Raster index | Topics index | Keywords index | Graphical
133 index | Full index
134
135 © 2003-2019 GRASS Development Team, GRASS GIS 7.4.4 Reference Manual
136
137
138
139GRASS 7.4.4 r.kappa(1)