Newsgroups: comp.ai
Path: cantaloupe.srv.cs.cmu.edu!europa.chnt.gtegsc.com!news.sprintlink.net!noc.netcom.net!netcom.com!olea
From: olea@netcom.com (Michael Olea)
Subject: Re: Corners as a model to visual recognition
Message-ID: <oleaDAuv9u.38n@netcom.com>
Organization: NETCOM On-line Communication Services (408 261-4700 guest)
References: <3slka9$msg@nuscc.nus.sg>
Date: Tue, 27 Jun 1995 23:44:17 GMT
Lines: 39
Sender: olea@netcom17.netcom.com

ngkaihoe@iscs.nus.sg (StarGazer @ LUP) writes:

>Hi,

>I am a student in National University of Singapore. I posted this
>under ai.vision, seems that it is moderated and the posting was not
>sucessful. So I post here again, hoping that some of U may be able
>to clear my doubts.

>As I was saying, I am a student in NUS and under some research programme
>organised by the University, the topic is computer vision. The approach
>I used is to use corners to describe an object (eg : a three corners
>object describe a triangle, four corners object describe a rectangle,
>square, trapezium etc). The strange thing is, I dont seem to be able
>to find any book in my University library touching on using corners
>to recognise objects. Any1 know of any source on this ?? Any1 researching
>on visual recognition too ?? can email me so we can share some results ?

>Some of the interesting results I got is that even though the model
>seems to suggest that curve edges cannot be recognised by this model.
>When U visualise a circle to be a regular polygon with an infinite 
>number of corners, programming to recognise curve surface becomes a
>matter of implementation... This model seems to be able to recognise
>very complex shapes (but that would be an extension to my present
>project, if I continue on this project). Can some1 email me ??

>-- 
>/==BBSer===Emailer===IRCer===FTPer===XwingFighter=====\
>|  S T A R G A Z E R  a.k.a   Laugh Until Peng        |     
>|  email : ngkaihoe@iscs.nus.sg or isc40445@nus.sg    |
>|                                                     |
>|  Circle is a regular polygon with an infinite       | 
>|  number of corners - StarGazer                      |
>\==WorldWideWebber===DOOMer===YAKKer===MoutainBiker===/

	This is not exactly what you asked for, but probably
close enough - see "Machine Interpretation of Line Drawings",
Kokichi Sugihara, ISBN 0-262-19254-3.

