# feature detectors and descriptors comparison

There are several kinds of detectors and descriptors, like SIFT, SURF, FAST. I wonder are they all eligible for real-time applications? Which is the best or better?

And furthermore, is Harris-Laplacian dectector still useful when we already have the above three? Is it better than them?

## 1 Answer

I think SURF is better than all , as its clear from its name , Speed Up robust Feature Detector , but its not free to use , its a patent , so you can't use it for your commercial uses , you can only use it for your studies and knowledge purpose , but i think its also depend on your app that algo to use , but surf is better with speed

• What about Harris-Laplacian? It's not a good choice for real-time application, right? – avocado Aug 26 '13 at 11:42
• Harris-Laplacian performs best in scale invariance ,i think your right , but i didn't use harris laplacian – ARG Aug 26 '13 at 13:07
• Perform best? Really? Any proof? – avocado Aug 26 '13 at 13:37
• @loganecolss its depend on your use , you can read about it here : http://www-scf.usc.edu/~boqinggo/Feature.htm and as i stated above i didn't use it , thats why i didn't describe it in my answer – ARG Aug 26 '13 at 18:22