Since the FAST (Features from Accelerated Segment Test) detector is much faster than any of the commonly used detection algorithms, and the repeatability and efficiency of FAST-9 are best in the FAST family, we proposed a novel LBP descriptor based on FAST-9 algorithm. Firstly, feature points are detected by FAST-9 and then, the texture information of the interesting point neighborhood is studied with the proposed Fast LBP descriptor named F-LBP, structured the 256-bit descriptor of the interesting point, which effectively reduced the computational complexity of the descriptor. Finally, the descriptor matching is carried out with the logical XNOR. The experimental results show that the proposed algorithm has got good repeatability, efficiency, the rotation invariance, the affine invariance and the illumination invariance in the process of image matching.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.