comp.lang.idl-pvwave archive
Messages from Usenet group comp.lang.idl-pvwave, compiled by Paulo Penteado

Home » Public Forums » archive » Calculating colocalization of three colours
Show: Today's Messages :: Show Polls :: Message Navigator
E-mail to friend 
Return to the default flat view Create a new topic Submit Reply
Re: Calculating colocalization of three colours [message #66751 is a reply to message #66692] Wed, 10 June 2009 08:29 Go to previous messageGo to previous message
pgrigis is currently offline  pgrigis
Messages: 436
Registered: September 2007
Senior Member
On Jun 4, 12:42 pm, Gianguido Cianci <gianguido.cia...@gmail.com>
wrote:
> Hi all,
>
> say I have two images, r(ed) and g(reen), and I want to know how
> colocalized these colours are. I do c1=correlate(r,g). if c is close
> to 1 then there is a lot of colocalization, if c~0 then there is none,
> if c~-1 then some joker just gave me the same image twice, inverting
> one of the copies! (usually, one calculates c on a ROI...)
>
> I am trying to figure out how to do something similar when a b(lue)
> image is added to the mix. I could do them pairwise, but that means
> for each set, I would end up with three numbers...
>
> Any ideas?
>
> Many thanks,
> Gianguido


Well, considering that you have 3 possibilities:

- all 3 correlated
- 2 correlated, one not
- none are correlated

I don't think anything less than 3 numbers would be enough anyway...

Ciao,
Paolo


Ciao,
Paolo
[Message index]
 
Read Message
Read Message
Read Message
Read Message
Read Message
Previous Topic: How to visit www.dfanning.com?
Next Topic: Converting Strings to Floating Point Numbers

-=] Back to Top [=-
[ Syndicate this forum (XML) ] [ RSS ] [ PDF ]

Current Time: Sat Oct 11 08:03:20 PDT 2025

Total time taken to generate the page: 1.67894 seconds