Next: Toward Learned Representations Up: Binary Descriptors Previous: ORB
ORB is not the only binary descriptor developed to achieve high computational performance.
BRISK (Binary Robust Invariant Scalable Keypoints) (LCS11) introduces a circular pattern of points sampled around the keypoint. Orientation is estimated using long-distance comparisons, while the descriptor is constructed using local comparisons between pairs of points. The result is a binary descriptor that is rotation robust and moderately scale invariant.
FREAK (Fast Retina Keypoint) (AOV12) is inspired by the distribution of photoreceptors in the human retina. The points used to construct the descriptor are arranged concentrically, with increasing density toward the center of the region being analyzed. This design produces descriptors that are particularly compact and fast to compare.
AKAZE (ANB13) is derived from the KAZE algorithm and introduces a multiscale representation based on nonlinear diffusion rather than traditional Gaussian filtering. This approach better preserves image structures and contours when constructing the scale space. The descriptor usually associated with AKAZE is M-LDB (Modified Local Difference Binary).