Re: cross-correlation for image registration

[Carnë Draug-2]

>On 2/21/12 5:59 AM, Carnë Draug wrote:
>> On 16 February 2012 17:04, Matthew Nicholas<[hidden email]>  wrote:
>>>> Quoting Carnë Draug<[hidden email]>:
>>>>> On 15 February 2012 21:15, Matt Nicholas<[hidden email]>  wrote:
>>>>> This might work for image registration with a small set of cases
>>>>> (eg bright spot on a dark background),
>> This is exactly my case. I do fluorescence microscopy, bright spots
>> moving on a black background that I want to track. Since it also
>> passes the example here
>> http://www-rohan.sdsu.edu/doc/matlab/toolbox/images/normxcorr2.html I
>> didn't bother about it anymore.
>
>I also happen to be a microscopist, which is where I do most of my image
>processing (a side project led me to use normxcorr2 for other types of
>images), so it is nice to know that it works well in this case!
>
>>>>   If I can find the time, I'll try to implement it and see how far I
>>>> get.
>> If you are able to implement this, that would be great. I'll gladly
>> add it to the image package. I don't know thought if it would be
>> better to fix the coeff option of xcorr2 and keep normxcorr2 a wrapper
>> for it though.
>That is a good point. To be honest, I am not sure whether the coeff
>option is 'wrong' or just follows some other definition of normalization
>than the one I want in this case. I'll try to figure this out and report
>back if I come up with anything.

Hi Matt

So I finally got around this and implemented another normalization. It works
fine with the example you gave that was giving you problems. Could you get
xcorr2 from development version
http://octave.svn.sourceforge.net/viewvc/octave/trunk/octave-forge/main/signal/inst/xcorr2.m
and see if it works for you too?

Carnë



--
View this message in context: 
http://octave.1599824.n4.nabble.com/cross-correlation-for-image-registration-tp4392009p4643382.html
Sent from the Octave - General mailing list archive at Nabble.com.