Channel Capacity Approach to Hyperspectral Band Subset Selection

This paper develops an information theoretical approach using channel capacity as a criterion for band subset selection (BSS). It formulates a BSS problem as a channel capacity problem by constructing a band channel with the original full band set as a channel input space, a selected band subset as a channel output space and the channel transition specified by band discrimination between original bands and selected bands. Then BSS is selected by Blahut's algorithm that iteratively finds a best possible input space that yields the maximal channel capacity. As a result, there is no need of band prioritization and interband decorrelation generally required by traditional band selection (BS). Two iterative algorithms are developed for finding an optimal BSS, sequential channel capacity BSS (SQ-CCBSS) and successive CCBSS (SC-CCBSS), both of which avoid an exhaustive search for all possible band subset combinations. Experimental results demonstrate that using CCBSS-selected band subsets produce quite different and interesting results from multiple bands selected by traditional single BS (SBS) based methods.

[1]  Licheng Jiao,et al.  Hyperspectral Band Selection Based on Trivariate Mutual Information and Clonal Selection , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[2]  Qian Du,et al.  Similarity-Based Unsupervised Band Selection for Hyperspectral Image Analysis , 2008, IEEE Geoscience and Remote Sensing Letters.

[3]  Stephen D. Stearns,et al.  Dimensionality reduction by optimal band selection for pixel classification of hyperspectral imagery , 1993, Optics & Photonics.

[4]  Qian Du,et al.  Fast supervised hyperspectral band selection using graphics processing unit , 2012 .

[5]  Fang Liu,et al.  Mutual-Information-Based Semi-Supervised Hyperspectral Band Selection With High Discrimination, High Information, and Low Redundancy , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[6]  Chein-I Chang,et al.  Virtual dimensionality analysis for hyperspectral imagery , 2015, Commercial + Scientific Sensing and Imaging.

[7]  Wei Xia,et al.  Band Selection for Hyperspectral Imagery: A New Approach Based on Complex Networks , 2013, IEEE Geoscience and Remote Sensing Letters.

[8]  Chein-I Chang,et al.  Hyperspectral Data Processing: Algorithm Design and Analysis , 2013 .

[9]  Kang Sun,et al.  A New Sparsity-Based Band Selection Method for Target Detection of Hyperspectral Image , 2015, IEEE Geoscience and Remote Sensing Letters.

[10]  Optimum Band Selection for Supervised Classification of Multispectral Data , 2007 .

[11]  Nicolas H. Younan,et al.  Hyperspectral Pixel Unmixing via Spectral Band Selection and DC-Insensitive Singular Value Decomposition , 2007, IEEE Geoscience and Remote Sensing Letters.

[12]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[13]  Chein-I Chang,et al.  A New Growing Method for Simplex-Based Endmember Extraction Algorithm , 2006, IEEE Transactions on Geoscience and Remote Sensing.

[14]  Paul Scheunders,et al.  A band selection technique for spectral classification , 2005, IEEE Geoscience and Remote Sensing Letters.

[15]  Paul Scheunders,et al.  Band Selection for Hyperspectral Remote Sensing , 2004 .

[16]  Chein-I Chang,et al.  Band Subset Selection for Anomaly Detection in Hyperspectral Imagery , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[17]  Paul D. Gader,et al.  Hyperspectral Band Selection and Endmember Detection Using Sparsity Promoting Priors , 2008, IEEE Geoscience and Remote Sensing Letters.

[18]  Qian Du,et al.  Optimized Hyperspectral Band Selection Using Particle Swarm Optimization , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[19]  Chein-I Chang,et al.  Recursive Orthogonal Projection-Based Simplex Growing Algorithm , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[20]  Chein-I Chang,et al.  Fully constrained least squares linear spectral mixture analysis method for material quantification in hyperspectral imagery , 2001, IEEE Trans. Geosci. Remote. Sens..

[21]  Xiangtao Zheng,et al.  Discovering Diverse Subset for Unsupervised Hyperspectral Band Selection , 2017, IEEE Transactions on Image Processing.

[22]  Kang Sun,et al.  Exemplar Component Analysis: A Fast Band Selection Method for Hyperspectral Imagery , 2015, IEEE Geoscience and Remote Sensing Letters.

[23]  LinLin Shen,et al.  Unsupervised Band Selection for Hyperspectral Imagery Classification Without Manual Band Removal , 2012, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[24]  Adolfo Martínez Usó,et al.  Clustering-Based Hyperspectral Band Selection Using Information Measures , 2007, IEEE Transactions on Geoscience and Remote Sensing.

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

[26]  Mario Winter,et al.  N-FINDR: an algorithm for fast autonomous spectral end-member determination in hyperspectral data , 1999, Optics & Photonics.

[27]  Chuleerat Jaruskulchai,et al.  Band Selection for Dimension Reduction in Hyper Spectral Image Using Integrated InformationGain and Principal Components Analysis Technique , 2012 .

[28]  Chein-I Chang,et al.  Fully abundance-constrained endmember finding for hyperspectral images , 2015, 2015 7th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS).

[29]  Chein-I Chang,et al.  Sequential N-FINDR algorithms , 2008, Optical Engineering + Applications.

[30]  Qian Du,et al.  Semisupervised Band Clustering for Dimensionality Reduction of Hyperspectral Imagery , 2011, IEEE Geoscience and Remote Sensing Letters.

[31]  Chein-I Chang,et al.  An information-theoretic approach to spectral variability, similarity, and discrimination for hyperspectral image analysis , 2000, IEEE Trans. Inf. Theory.

[32]  Qi Wang,et al.  Hyperspectral Band Selection by Multitask Sparsity Pursuit , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[33]  Chein-I Chang,et al.  Automatic spectral target recognition in hyperspectral imagery , 2003 .

[34]  N. Keshava,et al.  Distance metrics and band selection in hyperspectral processing with applications to material identification and spectral libraries , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[35]  Chein-I Chang,et al.  Recursive Geometric Simplex Growing Analysis for Finding Endmembers in Hyperspectral Imagery , 2017, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[36]  Chein-I Chang,et al.  Component Analysis-Based Unsupervised Linear Spectral Mixture Analysis for Hyperspectral Imagery , 2011, IEEE Trans. Geosci. Remote. Sens..

[37]  Fabio Maselli,et al.  Selection of optimum bands from TM scenes through mutual information analysis , 1993 .

[38]  Qian Du,et al.  Hyperspectral Band Selection Using Improved Firefly Algorithm , 2016, IEEE Geoscience and Remote Sensing Letters.

[39]  Fuhui Long,et al.  Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy , 2003, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[40]  Chein-I Chang,et al.  Constrained band selection for hyperspectral imagery , 2006, IEEE Transactions on Geoscience and Remote Sensing.

[41]  Chao-Cheng Wu.  Design and analysis of maximum simplex volume-based endmember extraction algorithms , 2009 .

[42]  Kang Sun,et al.  A New Band Selection Method for Hyperspectral Image Based on Data Quality , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[43]  Qian Du,et al.  A joint band prioritization and band-decorrelation approach to band selection for hyperspectral image classification , 1999, IEEE Trans. Geosci. Remote. Sens..

[44]  José M. Bioucas-Dias,et al.  Vertex component analysis: a fast algorithm to unmix hyperspectral data , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[45]  Chein-I Chang,et al.  Relationship exploration among PPI, ATGP and VCA via theoretical analysis , 2013, Int. J. Comput. Sci. Eng..

[46]  Chein-I Chang,et al.  Real-Time Progressive Hyperspectral Image Processing , 2016 .

[47]  Chein-I Chang,et al.  Estimation of number of spectrally distinct signal sources in hyperspectral imagery , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[48]  Richard E. Blahut,et al.  Computation of channel capacity and rate-distortion functions , 1972, IEEE Trans. Inf. Theory.

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

[50]  Jon Atli Benediktsson,et al.  Spectral–Spatial Hyperspectral Image Classification With Edge-Preserving Filtering , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[51]  Hyperspectral band clustering and band selection for urban land cover classification , 2012 .

[52]  Qian Du,et al.  An Efficient Method for Supervised Hyperspectral Band Selection , 2011, IEEE Geoscience and Remote Sensing Letters.

[53]  Maoguo Gong,et al.  Unsupervised Hyperspectral Image Band Selection via Column Subset Selection , 2015, IEEE Geoscience and Remote Sensing Letters.

[54]  Chein-I Chang,et al.  A Review of Unsupervised Spectral Target Analysis for Hyperspectral Imagery , 2010, EURASIP J. Adv. Signal Process..

[55]  Chein-I Chang,et al.  Real-Time Simplex Growing Algorithms for Hyperspectral Endmember Extraction , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[56]  Luyan Ji,et al.  Band selection for target detection in hyperspectral imagery using sparse CEM , 2014 .

[57]  Mingyi He,et al.  Band selection based on feature weighting for classification of hyperspectral data , 2005, IEEE Geoscience and Remote Sensing Letters.

[58]  Jon Atli Benediktsson,et al.  Advances in Spectral-Spatial Classification of Hyperspectral Images , 2013, Proceedings of the IEEE.

[59]  Chein-I Chang,et al.  Comparative Study and Analysis Among ATGP, VCA, and SGA for Finding Endmembers in Hyperspectral Imagery , 2016, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[60]  Konstantinos Kalpakis,et al.  Fast Algorithms to Implement N-FINDR for Hyperspectral Endmember Extraction , 2010, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[61]  Chein-I Chang,et al.  An information theoretical approach to multiple-band selection for hyperspectral imagery , 2016, 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).