Path: news.mathworks.com!newsfeed-00.mathworks.com!news.kjsl.com!newsfeed.stanford.edu!newsfeed.news.ucla.edu!nrc-news.nrc.ca!newsflash.concordia.ca!canopus.cc.umanitoba.ca!not-for-mail
From: roberson@ibd.nrc-cnrc.gc.ca (Walter Roberson)
Newsgroups: comp.soft-sys.matlab
Subject: Re: How does bwlabel work?
Date: Thu, 31 Jan 2008 19:23:14 +0000 (UTC)
Organization: National Research Council Canada - Conseil national de rechereches Canada
Lines: 34
Message-ID: <fnt772$561$1@canopus.cc.umanitoba.ca>
References: <fnrl3h$i3i$1@fred.mathworks.com> <fnsnmc$gar$1@canopus.cc.umanitoba.ca> <fnsr4n$57s$1@fred.mathworks.com> <fnt68l$tv$1@fred.mathworks.com>
NNTP-Posting-Host: origin.ibd.nrc.ca
X-Trace: canopus.cc.umanitoba.ca 1201807394 5313 192.70.172.160 (31 Jan 2008 19:23:14 GMT)
X-Complaints-To: abuse@cc.umanitoba.ca
NNTP-Posting-Date: Thu, 31 Jan 2008 19:23:14 +0000 (UTC)
Originator: roberson@ibd.nrc-cnrc.gc.ca (Walter Roberson)
Xref: news.mathworks.com comp.soft-sys.matlab:448628


In article <fnt68l$tv$1@fred.mathworks.com>,
Ross  <ross.nospam.kozz@yahoo.com> wrote:
>Basically, I'm 
>trying to assign "identities" to each blob. So if a blob 
>starts labelled as 2, even if it moves to a different 
>location, I'd like it to remain as 2, and not change to a 
>different label. 

>That will give me the ability to track these blobs rather 
>than just know where the blobs are. 

That is not possible in general, unless additional motion information
can be provided.

Consider image1 with two non-intersecting circles, C1, C2, near the
bottom of the image, and then consider image2 with two non-intersecting
circles near the top of the image. So C1 moved upwards and C2 moved
upwards? Not necessarily: C1 and C2 might have moved in diagonally
opposite directions and changed places, so in image2 the identities
might be in the order C2 then C1.

The tracking problem is significantly worse if the blobs can shrink
or grow or divide (one blob split, or two overlapping blobs seperate).
Recorded color changes with shadows and lighting angle, so the
boundaries of a moving blob might not be the same in two images,
even beyond "staircase" effects of image quantization into
discrete pixels.

bwlabel thus cannot really be expected to track blob identities.
You need to do some kind of post processing to find some kind of
"signature" for each blob to determine which is which, and that
signature is likely to need to incorporate domain-specific knowledge.
-- 
  "All is vanity."                                   -- Ecclesiastes