Re: Detecting Bubbles in Digital Images

Jim Keller (keller@cecs.missouri.edu)
Thu, 17 Jun 1999 13:31:28 +0200 (MET DST)

At 07:14 PM 6/16/99 +0200, you wrote:
>In article <19990614162942.07581.00001714@ng-cp1.aol.com>,
> adriana0x0@aol.com (Adriana0x0) wrote:
>> ellipse fitting algorithms yer best bet
>>
>
>Thank you for your reply.
>
>Ellipse fitting algorithms fit an ellipse to a set of points which are
>all roughly associated with the ellipse although some algorithms are
>tolerant to scatter. Unfortunately, what I have is a large, rectanglar
>array of pixels with different grey-levels. Within this array of
>pixels there may be several bubbles. There may be none. It would
>appear that, to apply an ellipse fitting algorithm, it would be
>necessary to segment out points belonging to each bubble. That is the
>problem since it is not possible to identify points belonging to a
>bubble on the basis of gray level. The bubbles are superimposed on a
>background of much smaller rectangles of varying gray level. They are
>rather like crop circles or like raindrops on a painting except that
>they are flat. ie. there is no 3D info. My problem is that I need to do
>segmentation to get a set of points but it is not clear how the
>segmentation is to be achieved.
>
>Cheers,
>Peter.

Peter:
You might want to check out the "shell clustering" work by Raghu
Krishnapuram and his students and Raj Dave and his. They have formulated
several shape finding approaches that use fuzzy, possibilistic, and robust
methods to find unknown numbers of parameterized curves from sometimes
pretty sparce and noisy edge data. Perhaps start with IEEE Trans. Fuzzy
Systems vol 3, 1995, pp. 29-43 and pp.44-60. This will give you many
pointers into the literature.

With best regards,

Jim

*********************************************************************
Jim Keller
Professor
Computer Engineering and Computer Science Department
217 Engineering Building West
University of Missouri-Columbia
Columbia, MO 65211-2060
(573) 882-7339 (voice)
(573) 882-8318 (FAX)
keller@cecs.missouri.edu

http://sun16.cecs.missouri.edu/
*********************************************************************

############################################################################
This message was posted through the fuzzy mailing list.
(1) To subscribe to this mailing list, send a message body of
"SUB FUZZY-MAIL myFirstName mySurname" to listproc@dbai.tuwien.ac.at
(2) To unsubscribe from this mailing list, send a message body of
"UNSUB FUZZY-MAIL" or "UNSUB FUZZY-MAIL yoursubscription@email.address.com"
to listproc@dbai.tuwien.ac.at
(3) To reach the human who maintains the list, send mail to
fuzzy-owner@dbai.tuwien.ac.at
(4) WWW access and other information on Fuzzy Sets and Logic see
http://www.dbai.tuwien.ac.at/ftp/mlowner/fuzzy-mail.info
(5) WWW archive: http://www.dbai.tuwien.ac.at/marchives/fuzzy-mail/index.html