A band selection technique for spectral classification

In hyperspectral remote sensing, sensors acquire reflectance values at many different wavelength bands, to cover a complete spectral interval. These measurements are strongly correlated, and no new information might be added when increasing the spectral resolution. Moreover, the higher number of spectral bands increases the complexity of a classification task. Therefore, feature reduction is a crucial step. An alternative would be to choose the required sensor bands settings a priori. In this letter, we introduce a statistical procedure to provide band settings for a specific classification task. The proposed procedure selects wavelength band settings which optimize the separation between the different spectral classes. The method is applicable as a band reduction technique, but it can as well serve the purpose of data interpretation or be an aid in sensor design. Results on a vegetation classification task show an improvement in classification performance over feature selection and other band selection techniques.

[1]  J. C. Price,et al.  Band selection procedure for multispectral scanners. , 1994, Applied optics.

[2]  David A. Landgrebe,et al.  Analytical Design of Multispectral Sensors , 1980, IEEE Transactions on Geoscience and Remote Sensing.

[3]  Edward J. Milton,et al.  Supervised band selection for optimal use of data from airborne hyperspectral sensors , 2003, IGARSS 2003. 2003 IEEE International Geoscience and Remote Sensing Symposium. Proceedings (IEEE Cat. No.03CH37477).

[4]  Chein-I Chang,et al.  Hyperspectral image classification and dimensionality reduction: an orthogonal subspace projection approach , 1994, IEEE Trans. Geosci. Remote. Sens..

[5]  Robert Michael Lewis,et al.  Pattern Search Algorithms for Bound Constrained Minimization , 1999, SIAM J. Optim..

[6]  P. Groves,et al.  Methodology For Hyperspectral Band Selection , 2004 .

[7]  Jiang Li,et al.  Dimensionality reduction of hyperspectral data using discrete wavelet transform feature extraction , 2002, IEEE Trans. Geosci. Remote. Sens..

[8]  L. Ingber.  Adaptive Simulated Annealing (ASA) , 1993 .

[9]  Keinosuke Fukunaga,et al.  Introduction to statistical pattern recognition (2nd ed.) , 1990 .

[10]  S. M. de Jong,et al.  Imaging spectrometry : basic principles and prospective applications , 2001 .

[11]  Joydeep Ghosh,et al.  Best-bases feature extraction algorithms for classification of hyperspectral data , 2001, IEEE Trans. Geosci. Remote. Sens..

[12]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[13]  Lorenzo Bruzzone,et al.  A new search algorithm for feature selection in hyperspectral remote sensing images , 2001, IEEE Trans. Geosci. Remote. Sens..

[14]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[15]  Peter Bajcsy,et al.  Methodology for hyperspectral band and classification model selection , 2003, IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data, 2003.

[16]  Ingmar Renhorn,et al.  Wavelength band selection method for multispectral target detection. , 2002, Applied optics.

[17]  Rainer Storn,et al.  Differential Evolution – A Simple and Efficient Heuristic for global Optimization over Continuous Spaces , 1997, J. Glob. Optim..

[18]  Josef Kittler,et al.  Floating search methods in feature selection , 1994, Pattern Recognit. Lett..