Gabor Feature-Based Collaborative Representation for Hyperspectral Imagery Classification
- 28 July 2014
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 53 (2), 1118-1129
- https://doi.org/10.1109/tgrs.2014.2334608
Abstract
Sparse-representation-based classification (SRC) assigns a test sample to the class with minimum representation error via a sparse linear combination of all the training samples, which has successfully been applied to several pattern recognition problems. According to compressive sensing theory, the l 1 -norm minimization could yield the same sparse solution as the l 0 norm under certain conditions. However, the computational complexity of the l 1 -norm optimization process is often too high for large-scale high-dimensional data, such as hyperspectral imagery (HSI). To make matter worse, a large number of training data are required to cover the whole sample space, which is difficult to obtain for hyperspectral data in practice. Recent advances have revealed that it is the collaborative representation but not the l 1 -norm sparsity that makes the SRC scheme powerful. Therefore, in this paper, a 3-D Gabor feature-based collaborative representation (3GCR) approach is proposed for HSI classification. When 3-D Gabor transformation could significantly increase the discrimination power of material features, a nonparametric and effective l 2 -norm collaborative representation method is developed to calculate the coefficients. Due to the simplicity of the method, the computational cost has been substantially reduced; thus, all the extracted Gabor features can be directly utilized to code the test sample, which conversely makes the l 2 -norm collaborative representation robust to noise and greatly improves the classification accuracy. The extensive experiments on two real hyperspectral data sets have shown higher performance of the proposed 3GCR over the state-of-the-art methods in the literature, in terms of both the classifier complexity and generalization ability from very small training sets.Keywords
Funding Information
- National Natural Science Foundation of China (61271022, 61272050)
- Guangdong College Excellent Young Teacher Training Program (Yq2013143)
- Shenzhen Scientific Research and Development Funding Program (ZDSY20121019111146499, JSGG20121026111056204, JCYJ20120613113106357, JCYJ20130329115750231)
- Shenzhen Dedicated Funding of Strategic Emerging Industry Development Program (JCYJ20121019111128765)
This publication has 52 references indexed in Scilit:
- Fast $\ell_{1}$-Minimization Algorithms for Robust Face RecognitionIEEE Transactions on Image Processing, 2013
- Remote Sensing Digital Image AnalysisPublished by Springer Science and Business Media LLC ,2013
- A Fast and Robust Sparse Approach for Hyperspectral Data Classification Using a Few Labeled SamplesIEEE Transactions on Geoscience and Remote Sensing, 2011
- Sparse representation or collaborative representation: Which helps face recognition?Published by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Is face recognition really a Compressive Sensing problem?Published by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Are sparse representations really relevant for image classification?Published by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Hyperspectral Image Classification Using Dictionary-Based Sparse RepresentationIEEE Transactions on Geoscience and Remote Sensing, 2011
- L1-L2 Optimization in Signal and Image ProcessingIEEE Signal Processing Magazine, 2010
- Investigation of the random forest framework for classification of hyperspectral dataIEEE Transactions on Geoscience and Remote Sensing, 2005
- Hyperspectral image data analysisIEEE Signal Processing Magazine, 2002