关键词: GABA算法, 蝙蝠算法, 遗传算法, 图像分类, 遥感图像

Abstract:

In order to make up for the shortcomings of bat algorithm optimization in late, which convergence rate is slow, the accuracy is not high, and easy to fall into the local optimum, this paper proposes a new classification algorithm-GABA algorithm for remote sensing image, and in the algorithm, the operations of genetic algorithm, including selection, crossover, mutation operator are applied to the bat algorithm. It turns out that the bat algorithm with mutation mechanism to avoid the population into local optimum, improve the ability of global optimization algorithm to increase the diversity of bat algorithm. As the same time, in order to highlight the advantages of this algorithm, experiments compared the results of bat algorithm, K-Means algorithm, particle swarm algorithm and the algorithm, analyze and evaluated the classification results of remote sensing images. And experiments show that in the application of remote sensing image classification, this algorithm can not only improve the classification accuracy, but also reduce the classification time. It is a feasible and effective method for remote sensing image classification.

Key words: GABA algorithm, bat algorithm, genetic algorithm, image classification, remote sensing image