Spectral-Spatial Classification of Hyperspectral Image Using Extreme Learning Machine and Loopy Belief Propagation

摘要

As a new machine learning method, extreme learning machine (ELM) has received wide attention for image classification due to its good performances. Since ELM cannot catch the spatial information, the results of classification is not good while applying to hyperspectral image (HSI) classification. In view of this, this paper proposes a new method for HSI classification by combining ELM with Loopy Belief Propagation (LBP). The proposed method can not only reduce time-consuming, but also improve the accuracy of classification greatly. The experimental result in HSI data set of Indian Pines demonstrates that the proposed method outperforms several classical algorithms.