**6. Conclusions**

In this paper, a novel semi-supervised classification method of hyperspectral images based on extended label propagation and rolling guidance filtering is proposed. The first advantage of this method is that the number of pseudo-labeled training samples is significantly increased. The second advantage is that the diversity of training samples is improved to enhance the generalization of the proposed method. The third advantage is that the spatial information is fully considered using graphs and superpixels. The experimental results on three different hyperspectral datasets demonstrate that the proposed ELP-RGF method offers an excellent performance in terms of both visual quality and quantitative evaluation indexes. In particular, when the number of training samples is relatively small, the improvement is more obvious.

**Acknowledgments:** This work was co-supported by the National Natural Science Foundation of China (NSFC) (41406200, 61701272) and Shandong Province Natural Science Foundation of China (ZR2014DQ030, ZR2017PF004).

**Author Contributions:** Binge Cui conceived of the idea of this paper. Xiaoyun Xie designed the experiments and drafted the paper. Binge Cui, Siyuan Hao, Jiandi Cui and Yan Lu revised the paper.

**Conflicts of Interest:** The authors declare no conflict of interest.
