Re: Pixel modification after classification [message #78159] |
Tue, 01 November 2011 05:21  |
David Fanning
Messages: 11724 Registered: August 2001
|
Senior Member |
|
|
Steffen Reich writes:
> I programmed a decission tree with IDL and now I`m at the point that I
> want to eliminate all areas of class below a specific value. For example
> all areas less than 20Pixels. I want use the region_grow function to
> calculate those areas and then change those pixels of the area since the
> result of the region_grow function is a vector of array indices. But
> perhaps I`m on a wrong or circuitous way, therefore I want to ask you
> what do you think about it and if you have any hints for me.
This sounds more like a job for Label_Region, rather than
Region_Grow. My blob analysis tools have a feature that
will allow you to exclude "blobs" below a certain size
from further analysis.
http://www.idlcoyote.com/ip_tips/blobanalysis.html
Cheers,
David
--
David Fanning, Ph.D.
Fanning Software Consulting, Inc.
Coyote's Guide to IDL Programming: http://www.idlcoyote.com/
Sepore ma de ni thui. ("Perhaps thou speakest truth.")
|
|
|
Re: Pixel modification after classification [message #78240 is a reply to message #78159] |
Wed, 02 November 2011 04:15  |
Steffen Reich
Messages: 8 Registered: October 2011
|
Junior Member |
|
|
Am 01.11.2011 13:21, schrieb David Fanning:
> Steffen Reich writes:
>
>> I programmed a decission tree with IDL and now I`m at the point that I
>> want to eliminate all areas of class below a specific value. For example
>> all areas less than 20Pixels. I want use the region_grow function to
>> calculate those areas and then change those pixels of the area since the
>> result of the region_grow function is a vector of array indices. But
>> perhaps I`m on a wrong or circuitous way, therefore I want to ask you
>> what do you think about it and if you have any hints for me.
>
> This sounds more like a job for Label_Region, rather than
> Region_Grow. My blob analysis tools have a feature that
> will allow you to exclude "blobs" below a certain size
> from further analysis.
>
> http://www.idlcoyote.com/ip_tips/blobanalysis.html
>
> Cheers,
>
> David
>
>
>
Thank you for your answer.
Greeting
Steffen
|
|
|