[GRASS-user] i.maxlik's reject versus i.segment's goodness

[Moritz Lennert]

On 20/11/14 08:40, Markus Metz wrote:
> On Wed, Nov 19, 2014 at 2:04 PM, Moritz Lennert
> <mlennert at club.worldonline.be> wrote:
>> On 18/11/14 09:47, Markus Metz wrote:
>>>
>>> On Sun, Nov 16, 2014 at 3:21 AM, Vaclav Petras <wenzeslaus at gmail.com>
>>> wrote:
>>>>
>>>> Hi,
>>>>
>>>> I executed the examples in i.cluster and i.maxlik manuals and also the
>>>> following i.segment command:
>>>>
>>>> i.segment group=lsat7_2002 at w1-imagery output=lsat7_2002_segments
>>>> threshold=0.5 goodness=lsat7_2002_segments_goodness
>>>>
>>>> (using the imagery group created in i.cluster example, otherwise
>>>> unrelated)
>>>>
>>>> I looked at goodness from i.segment and then reject from i.maxlik. I
>>>> noticed
>>>> that there is some correlation between these two. Well, this is quite
>>>> okay
>>>> since they are using same pixel values. However, then I noticed that low
>>>> values of goodness (-5000, ...)
>>>
>>>
>>> i.segment's goodness estimate is supposed to be in the range [0,1].
>>> Fixed in r62793,4. Can you test again?
>>
>>
>> Could you explain / put into the manual the explanation of the calculation /
>> meaning of this goodness of fit ?
>
> Done in r62830:
>
> The goodness of fit for each pixel is calculated as 1 - distance
> of the pixel to the object it belongs to. The distance is calculated
> with the selected similarity method. A value of 1 means
> identical values, perfect fit, and a value of 0 means maximum possible
> distance, worst possible fit.

Thanks !

:-)

Moritz