The problem happens when the multiplier is below 1.0. Is it a misuse to specify such a multiplier?<br><br>I attached a sample code, and I will send the sample image in private. (0.5MB)<br><br>Thanks,<br>Miklos<br><br><div class="gmail_quote">
On Tue, May 3, 2011 at 3:05 PM, Karthik Krishnan <span dir="ltr"><<a href="mailto:karthik.krishnan@kitware.com">karthik.krishnan@kitware.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;">
It should not. Are you adding as seeds an entire mask of pixels ? Can<br>
you post a minimal working example demonstrating this<br>
<br>
thx<br>
<div><div></div><div class="h5"><br>
On 5/3/11, Miklos Espak <<a href="mailto:espakm@gmail.com">espakm@gmail.com</a>> wrote:<br>
> Hi,<br>
><br>
> can the ConfidenceConnectedImageFilter remove pixels from the detected<br>
> region?<br>
><br>
> I found that if I increase the number of iterations (from 3 to 30), the<br>
> created mask will contain fewer pixels.<br>
><br>
> The documentation says that "letting the algorithm run for more iterations<br>
> the region will end up engulfing the entire image", but I have not found<br>
> anything about that the region may shrink.<br>
><br>
> How is that possible?<br>
><br>
> Regards,<br>
> Miklos<br>
><br>
</div></div></blockquote></div><br>