Semisupervised Sparse Manifold Discriminative Analysis for Feature Extraction of Hyperspectral Images

• Published in: IEEE transactions on geoscience and remote sensing Vol. 54; no. 10; pp. 6197 - 6211
• Main Authors: Luo, Fulin, Huang, Hong, Ma, Zezhong, Liu, Jiamin
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.10.2016; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithm design and analysis; Algorithms; Classification; Construction; Feature extraction; Feature extraction (FE); graph embedding (GE); Graphs; hyperspectral image (HSI); Hyperspectral sensors; Imaging spectrometers; Iron; Laplace equations; Manifolds; semisupervised discriminative analysis; sparse manifold learning; Sparse matrices; Spectrometers
• ISSN: 0196-2892; 1558-0644
• DOI: 10.1109/TGRS.2016.2583219

The graph embedding (GE) framework is very useful to extract the discriminative features of hyperspectral images (HSIs) for classification. However, a major challenge of GE is how to select a proper neighborhood size for graph construction. To overcome this drawback, a new semisupervised discriminative learning algorithm, which is called the semisupervised sparse manifold discriminative analysis (S 3 MDA) method, was proposed by using manifold-based sparse representation (MSR) and GE. The proposed algorithm utilizes MSR to obtain the sparse coefficients of labeled and unlabeled samples. Then, it constructs a within-class graph and a between-class graph using the sparse coefficients of labeled samples, as well as an unsupervised graph with the sparse coefficients of unlabeled samples. Finally, it uses these graphs to obtain a projection matrix for feature extraction (FE) of HSI in a low-dimensional space. The S 3 MDA method not only inherits the merits of MSR to reveal the sparse manifold properties of data but also enhances interclass separability and intraclass compactness to improve the discriminating power for classification. Extensive experiments on two real HSI data sets obtained with a reflective optics system imaging spectrometer and an airborne visible/infrared imaging spectrometer show that the proposed algorithm is significantly superior to other state-of-the-art FE methods in terms of classification accuracy.