A dual-mode mean-shift algorithm
Shih-Yu Chiu, Jiarui Zhang, Leu-Shing Lan · 2008
As a nonparametric statistical method, the mean shift algorithm has recently attracted much attention in the computer vision community due to its efficiency in motion tracking and clustering analysis. Its convergence rate is, however, slow around the convergence point. One way to tackle this problem is to switch the search mechanism to Newton’s method which has a quadratic order of convergence rate. This article thus presents a dual-mode mean-shift algorithm which combines both merits of the mean-shift and Newton’s algorithms. Some numerical experiments were conducted to confirm the effectiveness of the proposed approach.