A modified feature point descriptor based on binary robust independent elementary features

We present a modified feature point descriptor (M-BRIEF) based on Binary Robust Independent Elementary Features (BRIEF). BRIEF is much faster both to build and to match than SIFT and SURF, and it yields a better recognition as well. However, the matching results are not robust when the viewpoint changes obviously. In our paper, M-BRIEF automatically adjusts the coordinates of the image patch according to the main orientation of the feature point, and presents a new method for testing definition by introducing the adaptive threshold. The results show that the method is much robust in case of the obvious changes of the viewpoint.