A feature selection approach for hyperspectral image based on modified ant lion optimizer

Abstract

Feature selection is one of the most important issues in hyperspectral image (HSI) classification to achieve high correlation between the adjacent bands. The main concern is selecting fewer bands with the highest accuracy as possible. Generally, it is a combinatorial optimization problem and cannot be fully solved by swarm intelligence algorithms. Ant lion optimizer (ALO) is a newly proposed swarm intelligence algorithm that mimics the swarming behaviour of antlions. In addition, wavelet support vector machine (WSVM) is able to enhance the stability of the classification result, and Lévy flight helps swarm intelligence algorithms jump out of the local optimum. Therefore, in this paper, a novel feature selection method based on a modified ALO (MALO) and WSVM is proposed to reduce the dimensionality of HSIs. The proposed method is compared with some state-of-the-art algorithms on some HSI datasets. Moreover, a new evaluating criteria is formulated to estimate the performance of feature selection, and the classification accuracy and selected number of bands are balanced as much as possible. Experimental results demonstrate that the proposed method outperforms other approaches, finds the optimal solution with a reasonable convergence orientation, and its classification accuracy is satisfied with fewer bands, it is robust, adaptive and might be applied for practical work of feature selection.