Provided by: grass-doc_6.4.3-3_all bug


       i.gensig  - Generates statistics for i.maxlik from raster map.


       imagery, classification, supervised, MLC


       i.gensig help
       i.gensig   trainingmap=name  group=name  subgroup=name  signaturefile=string   [--verbose]

           Ground truth training map

           Name of input imagery group

           Name of input imagery subgroup

           Name for output file containing result signatures


       i.gensig is a non-interactive method for generating input into i.maxlik.  It can  be  used
       as  the  first  pass in the GRASS two-pass classification process (instead of i.cluster or
       i.class).  It reads a raster map layer, called the training map, which  has  some  of  the
       pixels or regions already classified.  i.gensig will then extract spectral signatures from
       an image based on the classification of the pixels in the  training  map  and  make  these
       signatures available to i.maxlik.

       The  user  would  then  execute  the  GRASS  program i.maxlik to actually create the final
       classified map.


              ground truth training map

       This map must be prepared by the user in advance. Programs like v.digit or r.digit can  be
       used  to  define  representative areas of the classes the user defines to be in the image.
       Of course other methods could be devised by the user for  creating  this  training  map  -
       i.gensig  makes  no  assumption  about  the  origin  of  this map layer. It simply creates
       signatures for the classes defined in the training map for the image to be classified (the
       image is specified in other options - see below).

              imagery group

       This  is the name of the group that contains the band files which comprise the image to be
       analyzed. The  command is used to construct groups of raster layers which comprise
       an image.

              subgroup containing image files

       This  names  the  subgroup  within  the  group  that  selects  a subset of the bands to be
       analyzed. The  command is also  used  to  prepare  this  subgroup.   The  subgroup
       mechanism allows the user to select a subset of all the band files that form an image.

              resultant signature file

       This  is  the  resultant signature file (containing the means and covariance matrices) for
       each class in the training map that is associated with the  band  files  in  the  subgroup
       select (see above).


       If  none  of  the arguments are specified on the command line, i.gensig will interactively
       prompt for the names of these maps and files.

       It should be noted that interactive mode here only means interactive  prompting  for  maps
       and files.  It does not mean visualization of the signatures that result from the process.


       The  structure  of  the  SIG  files  generated by i.gensig is as follows (ASCII file, used
       internally by i.maxlik):
       Note: the line numbers are  not  present  in  the  file  but  have  been  added  here  for
       explanation only:

       SIG file "lsat7_2000_gensig":
        1 #
        2 #water
        3 4186
        4 67.9508 48.7346 37.8915 15.3129 13.8473 12.0855
        5 1.74334
        6 0.439504 2.07267
        7 0.662523 1.63501 4.21189
        8 0.530339 2.40757 5.52857 22.433
        9 0.561184 2.30762 5.18846 20.5364 20.4926
       10 0.393218 1.2184 2.63628 9.61528 9.36025 5.85314

                      Line 2: text label

                      Line 3: number of points in class

                      Line 4: mean values per band of the class

                      Line 5-10: (semi)-matrix of band-band covariance

SEE ALSO for creating groups and subgroups.

       v.digit and r.digit for interactively  creating the training map.

       i.cluster for unsupervised clustering as an alternative to i.gensig to create signatures.

       i.class for a graphic/interactive as an alternative to i.gensig to create signatures.


       Michael Shapiro, U.S.Army Construction Engineering Research Laboratory

       Last changed: $Date: 2013-06-09 14:37:33 +0200 (Sun, 09 Jun 2013) $

       Full index

       © 2003-2013 GRASS Development Team