Improve ORB for rescaling ? (opencv)

asked 2016-09-22 08:49:09 -0500

drKzs gravatar image


I have to work on an application of image matching. I'm not specialized at all in image, but I do my best :)

I'm currently replacing sift by another descriptor (and detector).

I have used ORB/ORB, and the results are kinda good, except when there is some rescaling ... That's what I read about ORB, so i'm not surprised.

I am wondering if there's some tests (algo, concept, test ...) to improve the behaviour, like the way ratio test or cross matching improve matching ?

(I'm trying BRISK but the result I have at the moment are worse than ORB, though I still have to play with parameters)

Thanks for any idea/advice :)

edit retag flag offensive close merge delete


hmm, it's not actually clear, how you think, rescaling is connected to the choice of feature detectors.

can you try to improve on this ?

berak gravatar imageberak ( 2016-09-22 09:06:05 -0500 )edit

Well your answer is clear to me though : if I well understand, it depends on the detector, so there's nothing I can do except changing of detector, rigth ? So (still if I well understand), your answer is no :) thanks

drKzs gravatar imagedrKzs ( 2016-09-22 10:09:18 -0500 )edit

Thinking about that, I thought it was more depending on the descriptor than on the detector ?

drKzs gravatar imagedrKzs ( 2016-09-22 10:29:41 -0500 )edit