comp.lang.idl-pvwave archive: archive » Classification of objects in 2D image

Home » Public Forums » archive » Classification of objects in 2D image

Show: Today's Messages :: Show Polls :: Message Navigator
E-mail to friend

Re: Classification of objects in 2D image [message #23000 is a reply to message #22764]

Mon, 18 December 2000 09:04

Paul van Delst
Messages: 364
Registered: March 1997

Senior Member

Ben Tupper wrote:
>
> Hello,
>
> If I understand you correctly, you have the the image segemented
> into 'features' and 'background'. I do have an object (still in
> the development stage that will spit out 'feature'
> characteristics given a segemented image with only one
> 'feature'. I don't have it handy here, but I could send it to
> you soon.
>
> One limitation it has (a least a limitation for me) is a 'good'
> way of finding the perimeter of the feature. I use the CONTOUR
> procedure on a binary version of the image. The results are OK
> for me, but IDL may not be calculating that perimeter the way you
> would want.

I thought that's what Sobel filters were for? Finding edges of features in images and such. An image
consisting of crystals or crystal aggregates/clumps on a uniform background should show up well
under edge enhancement.

paulv

--
Paul van Delst Ph: (301) 763-8000 x7274
CIMSS @ NOAA/NCEP Fax: (301) 763-8545
Rm.207, 5200 Auth Rd. Email: pvandelst@ncep.noaa.gov
Camp Springs MD 20746

Report message to a moderator

[Message index]

		Classification of objects in 2D image By: hahn on Fri, 01 December 2000 00:00
		Re: Classification of objects in 2D image By: Ben Tupper on Mon, 18 December 2000 17:46
		Re: Classification of objects in 2D image By: Paul van Delst on Mon, 18 December 2000 09:04
		Re: Classification of objects in 2D image By: Ben Tupper on Mon, 18 December 2000 06:33
		Re: Classification of objects in 2D image By: hahn on Fri, 15 December 2000 06:24

Previous Topic:	Join the PV-WAVE Team
Next Topic:	underscore bug?

-=] Back to Top [=-

[ Syndicate this forum (XML) ] [

] [

]

Current Time: Fri Oct 10 08:57:09 PDT 2025

Total time taken to generate the page: 0.00623 seconds