Semisupervised Hyperspectral Image Classification Using Small Sample Sizes

Hyperspectral image classification is a challenging task when only a small number of labeled samples are available due to the difficult, expensive, and time-consuming ground campaigns required to collect the ground-truth information. It is also known that the classification performance is highly dependent on the size of the labeled data. In this letter, a semisupervised learning-based hyperspectral image classification framework is proposed as a solution to these problems. One of the contributions of this letter is the selection of the initial labeled training samples with a subtractive clustering-based approach, which provides the most informative samples for graph-based self-training. Another contribution is the decision-level combination of results obtained by support vector machines and kernel sparse representation classifiers. Additionally, a combination of the spatial and spectral information by creating a window structure is also proposed via integrating contextual information from the neighboring pixels. The explanatory experiments confirm that the proposed framework offers better and more promising results, even using a small number of initial labeled samples.

[1]  Peijun Du,et al.  Semi-supervised dimensionality reduction for hyperspectral remote sensing image classification , 2012, 2012 4th Workshop on Hyperspectral Image and Signal Processing (WHISPERS).

[2]  Antonio J. Plaza,et al.  Semi-supervised discriminative random field for hyperspectral image classification , 2012, 2012 4th Workshop on Hyperspectral Image and Signal Processing (WHISPERS).

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

[4]  Zhenfeng Shao,et al.  A Novel Hierarchical Semisupervised SVM for Classification of Hyperspectral Images , 2014, IEEE Geoscience and Remote Sensing Letters.

[5]  Naif Alajlan,et al.  A hierarchical learning paradigm for semi-supervised classification of remote sensing images , 2015, 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[6]  Yukio Kosugi,et al.  Semi-Supervised Hyperspectral Subspace Learning Based on a Generalized Eigenvalue Problem for Regression and Dimensionality Reduction , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[7]  Lorenzo Bruzzone,et al.  Active and Semisupervised Learning for the Classification of Remote Sensing Images , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[8]  Lorenzo Bruzzone,et al.  Classification of hyperspectral data by continuation semi-supervised SVM , 2007, 2007 IEEE International Geoscience and Remote Sensing Symposium.

[9]  Jonathan Li,et al.  Semisupervised Classification for Hyperspectral Imagery With Transductive Multiple-Kernel Learning , 2014, IEEE Geoscience and Remote Sensing Letters.

[10]  Abdullah Bal,et al.  Kernel Fukunaga–Koontz Transform Subspaces for Classification of Hyperspectral Images With Small Sample Sizes , 2015, IEEE Geoscience and Remote Sensing Letters.

[11]  Bo Du,et al.  Domain Adaptation for Remote Sensing Image Classification: A Low-Rank Reconstruction and Instance Weighting Label Propagation Inspired Algorithm , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[12]  Antonio J. Plaza,et al.  A new semi-supervised approach for hyperspectral image classification with different active learning strategies , 2012, 2012 4th Workshop on Hyperspectral Image and Signal Processing (WHISPERS).

[13]  Mikhail F. Kanevski,et al.  A Survey of Active Learning Algorithms for Supervised Remote Sensing Image Classification , 2011, IEEE Journal of Selected Topics in Signal Processing.

[14]  Gökhan Bilgin,et al.  Segmentation of Hyperspectral Images via Subtractive Clustering and Cluster Validation Using One-Class Support Vector Machines , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[15]  Antonio J. Plaza,et al.  Semisupervised Hyperspectral Image Classification Using Soft Sparse Multinomial Logistic Regression , 2013, IEEE Geoscience and Remote Sensing Letters.

[16]  Sukumar Bandopadhyay,et al.  An Objective Analysis of Support Vector Machine Based Classification for Remote Sensing , 2008 .

[17]  Robert J. Moorhead,et al.  Semi-supervised co-training and active learning framework for hyperspectral image classification , 2015, 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[18]  Daniel Jiwoong Im,et al.  Semisupervised Hyperspectral Image Classification via Neighborhood Graph Learning , 2015, IEEE Geoscience and Remote Sensing Letters.

[19]  Liang Xiao,et al.  Hyperspectral Image Classification Using Kernel Sparse Representation and Semilocal Spatial Graph Regularization , 2014, IEEE Geoscience and Remote Sensing Letters.

[20]  Trac D. Tran,et al.  Hyperspectral Image Classification via Kernel Sparse Representation , 2011, IEEE Transactions on Geoscience and Remote Sensing.