An Image Registration Method Based on Region Selecting and Feature Points Matching

Abstract

A new image registration algorithm based on circles and Harris corner detection is described in this paper.It detects feature points by Harris operator,selects effective feature points automatically,and makes full use of the rotational invariance of circles and the maximum mutual information for feature points matching.The method can avoid a heavy computing load and the inaccurate matching of feature points compared with the traditional registration algorithms.The simulation results show that the method can accomplish the registration in 27.8 s,make the error of 0.07° in rotational angle with the exactness in translating distance.The method in this paper is better than the traditional ones.