Semisupervised graph-based hyperspectral images classification using low-rank representation graph with considering the local structure of data

Abstract. Because of limited labeled samples, semisupervised learning (SSL) methods have attracted much attention for classification of hyperspectral images (HSIs). Graph-based methods that treat data samples as nodes in a graph are very popular classes of SSL in the HSI data analysis. However, constructing a graph that can well capture the essential data structure is critical for these classes of SSL methods. A graph construction method based on low-rank representation (LRR) is proposed. Since LRR only captures the global structure of data, it cannot provide an informative graph for graph-based SSL tasks. To increase the effectiveness of the LRR-based graph, the local structure information is incorporated into the objective function of LRR as an additional penalty term. The proposed low-rank and local linear graph (LRLLG) takes the global and local structure into account, hence it provides a more generative and discriminative graph. Experimental results on two well-known data sets demonstrate that LRLLG outperforms the traditional graph construction methods in label propagation and graph-based SSL methods for HSIs.

[1]  Bo Du,et al.  Semisupervised Discriminative Locally Enhanced Alignment for Hyperspectral Image Classification , 2013, IEEE Transactions on Geoscience and Remote Sensing.

[2]  A. Atiya,et al.  Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond , 2005, IEEE Transactions on Neural Networks.

[3]  Peng Zhang,et al.  Nonlinear Dimensionality Reduction by Locally Linear Inlaying , 2009, IEEE Transactions on Neural Networks.

[4]  Shuicheng Yan,et al.  Learning With $\ell ^{1}$-Graph for Image Analysis , 2010, IEEE Transactions on Image Processing.

[5]  Meng Jian,et al.  Discriminative Structure Learning for Semantic Concept Detection With Graph Embedding , 2014, IEEE Transactions on Multimedia.

[6]  Bo Du,et al.  Joint Sparse Representation and Multitask Learning for Hyperspectral Target Detection , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[7]  Antonio J. Plaza,et al.  A Novel Semi-Supervised Method for Obtaining Finer Resolution Urban Extents Exploiting Coarser Resolution Maps , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[8]  Junbin Gao,et al.  Laplacian Regularized Low-Rank Representation and Its Applications , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Gustavo Camps-Valls,et al.  Semi-Supervised Graph-Based Hyperspectral Image Classification , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[10]  Yue Han,et al.  Semi-supervised low-rank representation graph for pattern recognition , 2013, IET Image Process..

[11]  Wei Li,et al.  Hyperspectral Image Classification via Low-Rank and Sparse Representation With Spectral Consistency Constraint , 2017, IEEE Geoscience and Remote Sensing Letters.

[12]  Haibo Wang,et al.  Albedo recovery for hyperspectral image classification , 2017, J. Electronic Imaging.

[13]  Gustavo Camps-Valls,et al.  Semisupervised Remote Sensing Image Classification With Cluster Kernels , 2009, IEEE Geoscience and Remote Sensing Letters.

[14]  J. Tenenbaum,et al.  A global geometric framework for nonlinear dimensionality reduction. , 2000, Science.

[15]  David A. Clausi,et al.  Hyperspectral Image Classification With Limited Labeled Training Samples Using Enhanced Ensemble Learning and Conditional Random Fields , 2015, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[16]  Luis Alonso,et al.  Robust support vector method for hyperspectral data classification and knowledge discovery , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[17]  Fang Liu,et al.  Weighted Low-Rank Representation-Based Dimension Reduction for Hyperspectral Image Classification , 2017, IEEE Geoscience and Remote Sensing Letters.

[18]  Yulong Wang,et al.  Graph-Regularized Low-Rank Representation for Destriping of Hyperspectral Images , 2013, IEEE Transactions on Geoscience and Remote Sensing.

[19]  Nello Cristianini,et al.  Kernel Methods for Pattern Analysis , 2004 .

[20]  Zhixun Su,et al.  Linearized Alternating Direction Method with Adaptive Penalty for Low-Rank Representation , 2011, NIPS.

[21]  Haibo Wang,et al.  Large margin distribution machine for hyperspectral image classification , 2016, J. Electronic Imaging.

[22]  Jason Weston,et al.  Semisupervised Neural Networks for Efficient Hyperspectral Image Classification , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[23]  Jun Li,et al.  Simultaneous Sparse Graph Embedding for Hyperspectral Image Classification , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[24]  Mikhail Belkin,et al.  Laplacian Eigenmaps for Dimensionality Reduction and Data Representation , 2003, Neural Computation.

[25]  Xuan Hou,et al.  Semi-Supervised Classification Based on Low Rank Representation , 2016, Algorithms.

[26]  S. N. Merchant,et al.  Abnormality detection using deep neural networks with robust quasi-norm autoencoding and semi-supervised learning , 2018, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[27]  Yong Yu,et al.  Robust Recovery of Subspace Structures by Low-Rank Representation , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[28]  Guillermo Sapiro,et al.  Sparse Representation for Computer Vision and Pattern Recognition , 2010, Proceedings of the IEEE.

[29]  Bernhard Schölkopf,et al.  Learning with Local and Global Consistency , 2003, NIPS.

[30]  Yan Guo,et al.  Local-Manifold-Learning-Based Graph Construction for Semisupervised Hyperspectral Image Classification , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[31]  Jian Yang,et al.  Low rank representation with adaptive distance penalty for semi-supervised subspace classification , 2017, Pattern Recognit..

[32]  Shuicheng Yan,et al.  Semi-supervised Learning by Sparse Representation , 2009, SDM.

[33]  Xin Yang,et al.  Semi-supervised nonlinear dimensionality reduction , 2006, ICML.

[34]  Jinhui Tang,et al.  Constructing a Nonnegative Low-Rank and Sparse Graph With Data-Adaptive Features , 2014, IEEE Transactions on Image Processing.

[35]  Lorenzo Bruzzone,et al.  A Novel Transductive SVM for Semisupervised Classification of Remote-Sensing Images , 2006, IEEE Transactions on Geoscience and Remote Sensing.

[36]  Tong Zhang,et al.  Supervised and Semi-Supervised Text Categorization using LSTM for Region Embeddings , 2016, ICML.

[37]  Jon Atli Benediktsson,et al.  Classification of Hyperspectral Images by Exploiting Spectral–Spatial Information of Superpixel via Multiple Kernels , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[38]  Wilfried Philips,et al.  Feature Extraction of Hyperspectral Images With Semisupervised Graph Learning , 2016, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[39]  Horst Bischof,et al.  Semi-supervised image classification with huberized Laplacian Support Vector Machines , 2013, 2013 IEEE 9th International Conference on Emerging Technologies (ICET).

[40]  Jon Atli Benediktsson,et al.  Classification of Hyperspectral Images by Using Extended Morphological Attribute Profiles and Independent Component Analysis , 2011, IEEE Geoscience and Remote Sensing Letters.

[41]  Xiuping Jia,et al.  Deep Feature Extraction and Classification of Hyperspectral Images Based on Convolutional Neural Networks , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[42]  Zhi-Hua Zhou.  Large Margin Distribution Learning , 2014, ANNPR.

[43]  Allen Y. Yang,et al.  Robust Face Recognition via Sparse Representation , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.