A discriminant sparse representation graph-based semi-supervised learning for hyperspectral image classification
The classification of hyperspectral image with a paucity of labeled samples is a challenging task. In this paper, we present a discriminant sparse representation (DSR) graph for semi-supervised learning (SSL) to address this problem. For graph-based methods, how to construct a graph among the pixels is the key to a successful classification. Our graph construction method contains two steps. Sparse representation (SR) method is first employed to estimate the probability matrix of the pairwise pixels belonging to the same class, and then this probability matrix is integrated into the SR graph, which can be obtained by solving an ℓ 1 optimization problem, to form a DSR graph. Experiments on Hyperion and AVIRIS hyperspectral data show that our proposed method outperforms state of the art.
KeywordsHyperspectral image classification Graph Semi-supervised learning (SSL) Sparse representation (SR)
This work is supported by the Project of the National Natural Science Foundation of China No.61433007 and No.61401170.
- 4.Cheng H, Liu Z, Yang J (2009) Sparsity induced similarity measure for label propagation. In: Proceedings of IEEE 12th international conference of computer vision, Kyoto, pp 317–324Google Scholar
- 6.Kim W, Crawford MM (2010) Adaptive classification for hyperspectral image data using manifold regularization kernel machines. IEEE Trans Geosci Remote Sens 48(11):4110–4121Google Scholar
- 10.Wang D, Lu H, Xiao Z, Yang MH (2015) Inverse sparse tracker with a locally weighted distance metric. IEEE Trans Image Process 24:2646–2657Google Scholar
- 11.Wang D, Lu H, Yang MH (2015) Kernel collaborative face recognition. Pattern Recogn:3025–3037Google Scholar
- 13.Wu M, Schölkopf B (2007) Transductive classification via local learning regularization. In: Proceeding of 11th international conference of artificial intelligence statistics, pp 628–635Google Scholar
- 14.Yan S, Wang H (2009) Semi-supervised learning by sparse representation. In: Proceedings of SIAM international conference of data mining. SIAM, Sparks, pp 792–801Google Scholar
- 15.Zhang L, Yang M, Feng X (2011) Sparse representation or collaborative representation: Which helps face recognition?. In: Proceedings of IEEE 12th international conference of computer vision. IEEE, pp 471–478Google Scholar
- 16.Zhou D, Bousquet O, Lal TN, Weston J, Schölkopf B (2004) Learning with local and global consistency. In: Thrun LSS, Scholkopf EB (eds) Proceedings of advance neural information processing system, vol 16, pp 321–328Google Scholar
- 17.Zhu X (2008) Semi-supervised learning literature survey. Tech. rep., Comput. Sci., Univ. Wisconsin-Madison, Madison, WI, USA, TR-1530Google Scholar
- 18.Zhu X, Ghahramani Z (2002) Learning from labeled and unlabeled data with label propagation. Tech. rep., School Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USAGoogle Scholar
- 19.Zhu X, Lafferty J, Ghahramani Z (2003) Semi-supervised learning using gaussian fields and harmonic functions. In: Proceedings of 20th international conference of machine learning, Washington, DC, pp 912–919Google Scholar