top bar
QuickTopic free message boards logo
Skip to Messages

TOPIC:

SIFT

8
Spam deleted by QuickTopic 08-18-2010 02:03 AM
7
hanyujoys
09-24-2009
11:11 PM ET (US)
Support of the Lou Zhu, Lou Zhu worked hard
Signature---------------------------------------------------------------- ---------------------------------------------------
Nothing is impossible for a willing heart.
ugg classic cardy
6
coppermine
01-13-2009
10:24 AM ET (US)
There are better alternative like SURF nowadays. However, new implementations, for example by Vedaldi, are still coming out and provide more performance in purely computational means.
5
nonodelal
08-17-2008
06:02 AM ET (US)
troceltdar
4
Deleted by topic administrator 07-21-2006 09:03 AM
3
David Thompson
03-20-2006
09:21 AM ET (US)
After working with the algorithm for a while now I'm pretty impressed with its performance. Nevertheless there's a sense in which its a bit TOO discriminative for object recognition. Lowe's illumination example aside, a small change in lighting can easily thwart recognition. Is SIFT really summarizing essential characteristics of an object, or simply identifying a few "accidental" points that happen to be descriptive?
2
Pete Barnum
03-19-2006
09:31 PM ET (US)
SIFT seems like a pretty clever technique, but in reading the paper, I felt like they just pulled a bunch of values out of a hat. They claim invariance to all sorts of phenomena, like rotation and illumination, but they don't really present proofs. I hear that SIFT is popular among some groups, so it's probably worth something. Still, I'd like to have a better understanding of the underlying reasoning for such features, not just values of sigma.
1
Dave BradleyPerson was signed in when posted
03-08-2006
09:32 AM ET (US)
Please post your thoughts about SIFT here.

Print | RSS Views: 1845 (Unique: 801 ) / Subscribers: 0 | What's this?