LSH matching giving better results than BF mathing in bag of words

asked 2014-11-25 13:43:57 -0500

Mariusz gravatar image

Hi guys!

I'm doing object recognision with bag of words with ORB as descriptor and matcher is:

  • in first case BFMatcher with NORM_HAMMING and cross-check enabled
  • in second case FlannBasedMatcher with LSH params.

I also create SVM classifiers based on BOW's vocabulary. The interesting thing is that classifiers have better accuracy for setup with LSH than brute force matching. By a lot, like 20%. How it can be possible?

Thanks in advance, Mariusz

edit retag flag offensive close merge delete