[Insight-users] How can I get the pixels' values in .PNG after OtsuTresholding?

syssboxx-reg at yahoo.fr syssboxx-reg at yahoo.fr
Fri May 20 06:38:32 EDT 2005


Hi Zachary,
Thinks for your help,but I solved the problem.I have
been  verifing my outputs after every
operation(dilatation,closing) and the otput after
OtsuThresholding was correct but  the problem was
always there;Finally I found that the input after Otsu
Filter wasn't initialized correctly. 

Stanislava Ivanova  Hi Zachary,
Thinks for your help,but I solved the problem.I have
been  verifing my outputs after every
operation(dilatation,closing) and the otput after
OtsuThresholding was correct but  the problem was
always there;Finally I found that the input after Otsu
Filter wasn't initialized correctly. 

Stanislava Ivanova  
--- Zachary Pincus <zpincus at stanford.edu> a écrit:
> Hello,
> 
> You might want to check that the Otsu thresholder is
> getting reasonable  
> inputs. So try saving the output of the dilation and
> closing to a  
> separate file to make sure that that is what you
> want. (Remember that  
> if you save unsigned short images to a file you'll
> need a viewer [such  
> as ImageJ] that is savvy to them, otherwise all
> you'll see is black.)
> 
> Then, check that the Otsu thresholder is calculating
> a legitimate  
> threshold for your input image. You'll want to check
> what the  
> calculated threshold is with the GetThreshold()
> method (after calling  
> Update() of course), and make sure that that number
> is reasonable for  
> the input image you provided.
> 
> Finally, you will want to make sure that your "bleck
> pixel findong"  
> code (simple as it may be) is correct. Try saving
> the output of the  
> Otsu calculator to a file and looking at it in a
> simple image viewer to  
> see if it looks at all thresholded.
> 
> If none of this clears up the situation, you could
> send a *minimal*  
> example of code that produces the problem to the
> list and I'll try to  
> look it over.
> 
> 
> Zach Pincus
> 
> Department of Biochemistry and Program in Biomedical
> Informatics
> Stanford University School of Medicine
> 
> 
> On May 19, 2005, at 9:31 AM, <syssboxx-reg at yahoo.fr>
> wrote:
> 
> > Hello everybody
> > I have a problem with accessing the pixels'
> values;
> > I do the folowing:
> > I read a PNG file,then I use  grayscale dilatation
> and
> > closing,then i use the OtsuTresholding filter
> setting
> > the paratemeters to 255(white background) and
> 0(black
> > object).Then I want to loop over ther tresholded
> image
> > for detect the contour exterior of the object it
> and
> > save it to another file.For this purpose I'm
> looking
> > for the first black pixel in the object.It's the
> > problem.It can't find any black pixels in the
> image.I
> > tried to use unsigned char and unsigned short for
> > InputImageType but  i can get the pixels' values.
> > I supose after OtsuTresholding I have to be 0 and
> 255
> > values.How can I access to values in order to can
> use
> > it for my purpose?
> >
> >
> >
> > 	
> >
> > 	
> > 		
> >
>
_______________________________________________________________________
> 
> > ______
> > Découvrez le nouveau Yahoo! Mail : 1 Go d'espace
> de stockage pour vos  
> > mails, photos et vidéos !
> > Créez votre Yahoo! Mail sur
> http://fr.mail.yahoo.com
> > _______________________________________________
> > Insight-users mailing list
> > Insight-users at itk.org
> > http://www.itk.org/mailman/listinfo/insight-users
> >
> 
> 


	

	
		
_____________________________________________________________________________ 
Découvrez le nouveau Yahoo! Mail : 1 Go d'espace de stockage pour vos mails, photos et vidéos ! 
Créez votre Yahoo! Mail sur http://fr.mail.yahoo.com


More information about the Insight-users mailing list