Thanks again for all the help Dan. I tried your suggestion for using the itkSignedMaurerDistanceMapImageFilter and got different results. I sent in my BinaryThresholdImageFilter output and got the following from my itkSignedMaurerDistanceMapImageFilter <div>
<a href="http://i.imgur.com/jZ1AN.png" target="_blank">http://i.imgur.com/jZ1AN.png</a><br><div><br></div><div>Are there any other inputs I need to set for my Mauerer Distance Map? This one is new to me and I didn't find much in the documentation. Thanks-</div>
<div>-Ryan</div><div><br></div><div>p.s. You were right about my previous lossy compression woes</div><div><br><div class="gmail_quote">On Thu, Aug 19, 2010 at 2:51 PM, Dan Mueller <span dir="ltr"><<a href="mailto:dan.muel@gmail.com" target="_blank">dan.muel@gmail.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="border-left:1px solid rgb(204, 204, 204);margin:0pt 0pt 0pt 0.8ex;padding-left:1ex">
Hi Ryan,<br>
<br>
1. The output of the connected component filter you provided does not<br>
seem right. Are you doubly sure you are passing the binary image to<br>
the connected component filter? I have attached the output you should<br>
get.<br>
<br>
2. That said, if you just need to extract seeds for further<br>
processing, I don't think you need to use the connected component<br>
filter. This filter simply assigns a unique identifier (Eg. 1, 2, 3,<br>
4, etc) to each component or "blob" in the image. One way of obtaining<br>
seeds is to take the binary image, compute the distance transform (try<br>
Code/BasicFilters/itkSignedMaurerDistanceMapImageFilter.h), and the<br>
apply the regional maxima filter<br>
(Code/Review/itkRegionalMaximaImageFilter.h). I have attached the<br>
output from this chain.<br>
<br>
HTH<br>
<br>
Cheers, Dan<br>
<div><div></div><div><br>
On 19 August 2010 21:20, Ryan Smith <<a href="mailto:ryanleesmith@gmail.com" target="_blank">ryanleesmith@gmail.com</a>> wrote:<br>
> Hi Dan-<br>
> The white top hat worked great at removing my extra features, and the binary<br>
> thresholding cleaned everything else up, however I am still having some<br>
> trouble using the ConnectedComponentFilter. I found this article which is<br>
> trying to do exactly what I am attempting:<br>
> <a href="http://www.itk.org/pipermail/insight-users/2007-January/020532.html" target="_blank">http://www.itk.org/pipermail/insight-users/2007-January/020532.html</a><br>
> I want the position and full width half max (FWHM) of each intensity maxima<br>
> in the image. I tried using the connected component filter and got the<br>
> output found at the following URL: <a href="http://i.imgur.com/TCqL8.png" target="_blank">http://i.imgur.com/TCqL8.png</a><br>
> It appears each feature is being tagged as several different features. Just<br>
> to confirm I am sending the binary thresholded image, not the<br>
> original Gaussian spot image into the ConnectedComponentFilter.<br>
> I feel like I am going down the wrong path here. I don't necessarily need<br>
> to segment my points, I just need to clean up the image (done) and<br>
> potentially use techniques such as those in other ITK problems I have read<br>
> to find 'seed points' for some region growing algorithms based on the<br>
> intensity maxima of my image. Any thoughts? Thanks in advance-<br>
> -Ryan<br>
><br>
><br>
> On Sun, Aug 15, 2010 at 11:22 PM, Dan Mueller <<a href="mailto:dan.muel@gmail.com" target="_blank">dan.muel@gmail.com</a>> wrote:<br>
>><br>
>> Hi Ryan,<br>
>><br>
>> You might consider using the "white top hat" operation to remove the<br>
>> background:<br>
>> WhiteTopHat = I - Dilate( Erode(I) )<br>
>> where I is the image, Erode is morphological erosion, and Dilate is<br>
>> morphological dilation.<br>
>><br>
>> You can find an implementation of this operation in:<br>
>> Code/BasicFilters/itkWhiteTopHatImageFilter.h<br>
>><br>
>> Once the background is removed, a simple global intensity threshold<br>
>> should suffice to segment the spots. The following filters may be<br>
>> helpful for that task:<br>
>> Code/BasicFilters/itkBinaryThresholdImageFilter.h<br>
>> Code/Algorithms/itkOtsuThresholdImageFilter.h<br>
>> Code/Review/itkKappaSigmaThresholdImageFilter.h<br>
>><br>
>> HTH<br>
>><br>
>> Cheers, Dan<br>
>><br>
>> On 15 August 2010 23:04, Ryan Smith <<a href="mailto:ryanleesmith@gmail.com" target="_blank">ryanleesmith@gmail.com</a>> wrote:<br>
>> > Hi-<br>
>> > I am attempting to remove the background and detect features in the<br>
>> > following image:<br>
>> > <a href="http://i.imgur.com/wd3Yt.jpg" target="_blank">http://i.imgur.com/wd3Yt.jpg</a><br>
>> ><br>
>> > I have a series of images in which the white circular spots travel and<br>
>> > the<br>
>> > white vertical stripes remain stationary. I would like to apply some<br>
>> > simple<br>
>> > background subtraction to remove the white stripes then autodetect the<br>
>> > intensity maxima associated with the circular features.<br>
>> ><br>
>> > A brief search provided the following results which address similar<br>
>> > problems<br>
>> > using itkConnectedComponentFilter. Is this what I want after my<br>
>> > background<br>
>> > is subtracted? Any example code on how to get the location and sizes of<br>
>> > the<br>
>> > components? Thanks in advance-<br>
>> ><br>
>> > -Ryan<br>
>> ><br>
>> ><br>
>> > _____________________________________<br>
>> > Powered by <a href="http://www.kitware.com" target="_blank">www.kitware.com</a><br>
>> ><br>
>> > Visit other Kitware open-source projects at<br>
>> > <a href="http://www.kitware.com/opensource/opensource.html" target="_blank">http://www.kitware.com/opensource/opensource.html</a><br>
>> ><br>
>> > Kitware offers ITK Training Courses, for more information visit:<br>
>> > <a href="http://www.kitware.com/products/protraining.html" target="_blank">http://www.kitware.com/products/protraining.html</a><br>
>> ><br>
>> > Please keep messages on-topic and check the ITK FAQ at:<br>
>> > <a href="http://www.itk.org/Wiki/ITK_FAQ" target="_blank">http://www.itk.org/Wiki/ITK_FAQ</a><br>
>> ><br>
>> > Follow this link to subscribe/unsubscribe:<br>
>> > <a href="http://www.itk.org/mailman/listinfo/insight-users" target="_blank">http://www.itk.org/mailman/listinfo/insight-users</a><br>
>> ><br>
>> ><br>
><br>
><br>
</div></div></blockquote></div><br></div></div>