A scale invariant keypoints detector
Tao Zhou · 2014
We propose a novel approach for detecting keypoints invariant to scale changes based on M-wavelet theory. The theory description and detecting process of our approach are presented The comparative evaluation of different detectors shows our approach can provides a competent performance in rotation invariant, scale invariant, illumination invariant and noiseproof. In terms of scale changes, our proposed approach improves keypoint repeatability by 2%~10% compared with scale invariant feature transform (SIFT), speeded up robust features (SURF), Harris-Laplace, Hessian-Laplace.