[GRASS-user] i.maxlik can't read signature from i.class

[Markus Neteler]

Hello Cesar,


On Tue, Nov 26, 2013 at 4:47 PM, Cesar Augusto Ramírez Franco <
caesarivs at gmail.com> wrote:

> Hello everyone,
>
> I've been trying to do a supervised classification from landsat8 imagery
> using i.class and then i.maxlik, but I'm getting an error when running
> i.maxlik saying it can't read the signature file.
>
> I tested my procedure on the NC sample dataset and I'm getting the same
> error, I'm using Grass 6.4.2 on Debian Wheezy, installed from the debian
> repo. Here's the command set:
>
> #Display RGB enhanced map
> i.landsat.rgb blue=lsat7_2000_10 green=lsat7_2000_20 red=lsat7_2000_30
> d.rgb blue=lsat7_2000_10 green=lsat7_2000_20 red=lsat7_2000_30
> #"Real color" map
> r.composite red=lsat7_2000_30 green=lsat7_2000_20 blue=lsat7_2000_10
> output=lsat7_2000_RGB
> #Group images to process
> i.group group=lsat7_2000_RGB subgroup=lsat7_2000_RGB
> input=lsat7_2000_10,lsat7_2000_20,lsat7_2000_30
> #Unsupervised classification
> i.cluster group=lsat7_2000_RGB subgroup=lsat7_2000_RGB sigfile=clustlsat7
> classes=20 report=rep_clust_lsat7.txt
> i.maxlik group=lsat7_2000_RGB subgroup=lsat7_2000_RGB sigfile=clustlsat7
>  class=lsat7_classes reject=lsat7_classes_rej
> #Supervised classification
>  i.class map=lsat7_2000_RGB group=lsat7_2000_RGB subgroup=lsat7_2000_RGB
> outsig=classlsat7
> i.maxlik group=lsat7_2000_RGB subgroup=lsat7_2000_RGB sigfile=classlsat7
> class=lsat7_class_sup
>

I reproduced your example here (thanks for providing it, makes testing
easy!).



> Here I get the error in which i.maxlik can't read the signature file
> created by i.class (classlsat7) but read the one created by i.cluster
> flawlessly
>

Here it went through (Fedora 19 64bit, 6.4.4svn).


GRASS 6.4.4svn (nc_spm_08):~ > i.class map=lsat7_2000_RGB
group=lsat7_2000_RGB subgroup=lsat7_2000_RGB outsig=classlsat7

RESULT SIGNATURE

GRASS 6.4.4svn (nc_spm_08):~ > i.maxlik group=lsat7_2000_RGB
subgroup=lsat7_2000_RGB sigfile=clustlsat7  class=lsat7_classes
reject=lsat7_classes_rej --o
 100%



> This is what I'm selecting on the i.class monitor, I named it vegetation:
>
...

My map looked similar.



> And the contents of the classlsat7 signature file are the following:
>
>>  #
>
> #vegetation
>
> 166
>
>
This is strange... Here I get

GRASS 6.4.4svn
(nc_spm_08):~/grassdata/nc_spm_08/landsat/group/lsat7_2000_RGB/subgroup/lsat7_2000_RGB/sig
> cat classlsat7
#
#lake
899
68.2458 49.1224 38.317
2.30345
1.26392 2.63753
1.82294 2.67163 5.90938
#vegetation
92
76.3804 66.6957 57.2391
120.414
116.029 116.236
160.886 158.447 222.206

Maybe you remove the unfortunate signature from the ASCII file and digitize
it again?

Best,
Markus
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.osgeo.org/pipermail/grass-user/attachments/20131202/35a12bcb/attachment.html>