Band Selection Based on Chaotic Cuckoo Search Algorithm for Hyperspectral Image

A band selection technique based on chaotic cuckoo search algorithm is proposed in this paper, which combined with cuckoo search algorithm and chaotic map to solve the problem of dimension reduction of hyperspectral image. As a common used evolutionary algorithm, cuckoo search algorithm has the better global optimization ability, and chaotic map can improve the local optimization ability of evolutionary algorithm. Hence, a HYDICE image is utilized to test the efficiency of the proposed method. experimental results demonstrate that the search ability of chaotic cuckoo search algorithm is better than genetic algorithm, particle swarm optimization algorithm, and standard cuckoo search algorithm. Meanwhile, the classification accuracy could be increased by using the selected band subset.