Spatial-Spectral Classification of Hyperspectral Images Using Discriminative Dictionary Designed by Learning Vector Quantization

• Published in: IEEE transactions on geoscience and remote sensing Vol. 52; no. 8; pp. 4808 - 4822
• Main Authors: Wang, Zhaowen, Nasrabadi, Nasser M., Huang, Thomas S.
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.08.2014; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Applied geophysics; Bayes methods; Classification; Complement; Dictionaries; dictionary learning; Distance learning; Earth sciences; Earth, ocean, space; Exact sciences and technology; hyperspectral imagery (HSI); Hyperspectral imaging; Internal geophysics; Learning; learning vector quantization (LVQ); Linear programming; Mathematical models; Objective function; Pixels; Probabilistic logic; sparse representation; spatial dependence; Spectra; Training; Vector quantization; hyperspectral imagery (HSI); dictionary learning; spatial dependence; Classification; learning vector quantization (LVQ); sparse representation; experimental studies; models; accuracy; remote sensing; classification; imagery; refinement; discrimination; Pixel; dictionaries
• ISSN: 0196-2892; 1558-0644
• DOI: 10.1109/TGRS.2013.2285049

In this paper, a novel discriminative dictionary learning method is proposed for sparse-representation-based classification (SRC) to label highly dimensional hyperspectral imagery (HSI). In SRC, a dictionary is conventionally constructed using all of the training pixels, which is not only inefficient due to the large size of typical HSI images but also ineffective in capturing class-discriminative information crucial for classification. We address the dictionary design problem with the inspiration from the learning vector quantization technique and propose a hinge loss function that is directly related to the classification task as the objective function for dictionary learning. The resulting online learning procedure systematically "pulls" and "pushes" dictionary atoms so that they become better adapted to distinguish between different classes. In addition, the spatial context for a test pixel within its local neighborhood is modeled using a Bayesian graph model and is incorporated with the sparse representation of a single test pixel in a unified probabilistic framework, which enables further refinement of our dictionary to capture the spatial class dependence that complements the spectral information. Experiments on different HSI images demonstrate that the dictionaries optimized using our method can achieve higher classification accuracy with substantially reduced dictionary size than using the whole training set. The proposed method also outperforms existing dictionary learning methods and attains the state-of-the-art results in both the spectral-only and spatial-spectral settings.