Multiple features fusion for hyperspectral image classification based on extreme learning machine

Abstract

Hyperspectral image (HSI) classification is a popular issue in the domain of remote sensing. The fundamental challenges in HSI classification include small number of training samples, high dimensionality of the hyperspectral data and suitable spatial-spectral features. In this paper, we propose a novel multiple features fusion method for HSI classification based on extreme learning machines (ELM). We extract spectral feature via the principal component analysis (PCA), and extract spatial features via local binary pattern (LBP), Gabor feature and extended multiattribute profile (EMAP). Then we utilize probability voting to fuse the multiple features based on extreme learning machine model. Experiment on real HSI demonstrates that the proposed method is superior to some existing methods and it is suitable for small training sample size conditions.