This forum is disabled, please visit https://forum.opencv.org
 | 1 | initial version |
I suggest to extend the BOW framework. Note that the distance between two features is no more in Euclidean space, it must be Hamming distance. So the following idea should work
to build visual vocabulary: the visual words are randomly selected among the training binary features.
assign a feature to the visual word of smallest Hamming distance.
