A Hybrid Evolutionary Approach to Band Selection for Hyperspectral Image Classification

DOI: 10.1007/978-3-642-12990-2_37

ABSTRACT With the development of the remote-sensing imaging technology, there are more and more applications of hyperspectral image
classification tasks, in which to select a minimal and effective subset from a mass of bands is the key issue. This paper
put forward a novel band selection strategy based on conditional mutual information between adjacent bands and branch and
bound algorithm for the high correlation between the bands. In addition, genetic algorithm and support vector machine are
employed to search for the best band combination. Experimental results on two benchmark data set have shown that this approach
is competitive and robust.

KeywordsHyperspectral Remote Sensing-Band Selection-Conditional Mutual Information-Support Vector Machine-Genetic Algorithm-Branch and Bound Algorithm

  • [Show abstract] [Hide abstract]
    ABSTRACT: Because of the difficulty of obtaining an analytic expression for Bayes error, a wide variety of separability measures has been proposed for feature selection. In this paper, we show that there is a general framework based on the criterion of mutual information (MI) that can provide a realistic solution to the problem of feature selection for high-dimensional data. We give a theoretical argument showing that the MI of multi-dimensional data can be broken down into several one-dimensional components, which makes numerical evaluation much easier and more accurate. It also reveals that selection based on the simple criterion of only retaining features with high associated MI values may be problematic when the features are highly correlated. Although there is a direct way of selecting features by jointly maximising MI, this suffers from combinatorial explosion. Hence, we propose a fast feature-selection scheme based on a ‘greedy’ optimisation strategy. To confirm the effectiveness of this scheme, simulations are carried out on 16 land-cover classes using the 92AV3C data set collected from the 220-dimensional AVIRIS hyperspectral sensor. We replicate our earlier positive results (which used an essentially heuristic method for MI-based band-selection) but with much reduced computational cost and a much sounder theoretical basis.
    Pattern Recognition 01/2008; 41:1653-1662. · 2.58 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Feature selection is an important problem for pattern classification systems. We study how to select good features according to the maximal statistical dependency criterion based on mutual information. Because of the difficulty in directly implementing the maximal dependency condition, we first derive an equivalent form, called minimal-redundancy-maximal-relevance criterion (mRMR), for first-order incremental feature selection. Then, we present a two-stage feature selection algorithm by combining mRMR and other more sophisticated feature selectors (e.g., wrappers). This allows us to select a compact set of superior features at very low cost. We perform extensive experimental comparison of our algorithm and other methods using three different classifiers (naive Bayes, support vector machine, and linear discriminate analysis) and four different data sets (handwritten digits, arrhythmia, NCI cancer cell lines, and lymphoma tissues). The results confirm that mRMR leads to promising improvement on feature selection and classification accuracy.
    IEEE Transactions on Pattern Analysis and Machine Intelligence 09/2005; 27(8):1226-38. · 4.80 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: A new suboptimal search strategy suitable for feature selection in very high-dimensional remote sensing images (e.g., those acquired by hyperspectral sensors) is proposed. Each solution of the feature selection problem is represented as a binary string that indicates which features are selected and which are disregarded. In turn, each binary string corresponds to a point of a multidimensional binary space. Given a criterion function to evaluate the effectiveness of a selected solution, the proposed strategy is based on the search for constrained local extremes of such a function in the above-defined binary space. In particular, two different algorithms are presented that explore the space of solutions in different ways. These algorithms are compared with the classical sequential forward selection and sequential forward floating selection suboptimal techniques, using hyperspectral remote sensing images (acquired by the airborne visible/infrared imaging spectrometer [AVIRIS] sensor) as a data set. Experimental results point out the effectiveness of both algorithms, which can be regarded as valid alternatives to classical methods, as they allow interesting tradeoffs between the qualities of selected feature subsets and computational cost
    IEEE Transactions on Geoscience and Remote Sensing 08/2001; · 3.47 Impact Factor