Open AccessRBRIEF: a robust descriptor based on random binary comparisons
Author(s) -
Huang Wei,
Wu LingDa,
Song HanChen,
Wei YingMei
Publication year - 2013
Publication title -
iet computer vision
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.38
H-Index - 37
eISSN - 1751-9640
pISSN - 1751-9632
DOI - 10.1049/iet-cvi.2012.0087
Subject(s) - artificial intelligence , pattern recognition (psychology) , hamming distance , binary number , computer science , similarity (geometry) , feature (linguistics) , mathematics , scale invariant feature transform , rotation (mathematics) , computer vision , feature extraction , image (mathematics) , algorithm , linguistics , philosophy , arithmetic
The authors propose a robust descriptor based on BRIEF, called RBRIEF. Unlike the original BRIEF, the proposed descriptor is also robust to scale and in‐plane rotation transformations. Furthermore, the authors use first derivative as sample function to do binary comparisons which has proven to be better compared against the function of intensity used in BRIEF. In the feature matching stage, the authors use Hamming distance to evaluate the descriptor similarity. As a result, the performance of the proposed descriptor outperforms SURF, BRIEF and ORB using standard benchmarks. In particular, the experiments demonstrate the proposed descriptor's superior performance in the presence of image blur, JPEG compression and light changes. Furthermore, the descriptor exhibits robust performance using only relatively few bits compared to other descriptors.