Anti-rotation image matching algorithms based on hybrid genetic algorithm

Abstract

Algorithm for rotated image matching was slow, inefficient and standard genetic algorithm (SGA) in image matching was not high in accuracy, this article introduce a fast anti-rotation image matching algorithm based on hybrid genetic algorithm. The algorithm combines GA and hill-climbing algorithm in an efficient way and performs fast both in global search and local search. The algorithm use circular and ring template instead of rectangle template, and use the histogram of the template to calculate the fitness of the individual in the hybrid genetic algorithm. The speed and accuracy of the Algorithm was proved by the experiment.