Abstract
Hyperspectral images (HSIs) contain significant number of contiguous dense spectral bands which often have large redundancy and high correlation that subsequently results into “curse of dimensionality” in HSI analysis. Therefore, efficient band selection techniques are crucial for dimensionality reduction of HSIs without any significant loss of spectral information contained in it. In this paper, deep learning autoencoders and genetic algorithm (GA) are used for efficient selection of the most revealing bands from a remotely sensed HSI. The proposed method formulates the HSI band selection process as a GA-based evolutionary optimization that minimizes the reconstruction error of an autoencoder which uses a few informative bands for HSI reconstruction. The proposed approach starts with spectral segmentation of the bands in an HSI into a number of spectral regions, and then, different autoencoders are trained on each segment with the original input band vectors contained in the segmented region. Finally, GA-based search heuristics is applied on each region in order to find out sparse sub-combination of spectral bands in such a way that the trained autoencoders would reconstruct the original segmented spectral vectors from the resulting band sub-combinations with least reconstruction errors. The final band selection is carried out by aggregating all the band sub-combinations returned from the segmented regions. Finally, the effectiveness of the proposed method is verified through selected bands validation by a support vector machine classifier. Experimental results on three publicly available HSI datasets depict the consistently superior effectiveness of the proposed band selection method over other state-of-the-art methods in land cover classification of remotely sensed HSIs.
Similar content being viewed by others
References
Allwein EL, Schapire RE, Singer Y (2000) Reducing multiclass to binary: a unifying approach for margin classifiers. J Mach Learn Res 1:113–141
Bajcsy P, Groves P (2004) Methodology for hyperspectral band selection. Photogramm Eng Remote Sens 70(7):793–802
Bhattacharya S, Das S, Routray A (2018) Graph manifold clustering based band selection for hyperspectral face recognition. In: 2018 26th European signal processing conference (EUSIPCO). IEEE, pp 1990–1994
Borengasser M, Hungate WS, Watkins R (2007) Hyperspectral remote sensing: principles and applications. In: Remote sensing applications series. CRC Press
Burges CJ (1998) A tutorial on support vector machines for pattern recognition. Data Min Knowl Discov 2:121–167
Cai Y, Zhang Z, Liu X, Cai Z (2020) Efficient graph convolutional self-representation for band selection of hyperspectral image. IEEE J Sel Top Appl Earth Obs Remote Sens 13:4869–4880
Cao X, Wei C, Han J, Jiao L (2017) Hyperspectral band selection using improved classification map. IEEE Geosci Remote Sens Lett 14(11):2147–2151
Cao X, Wu B, Tao D, Jiao L (2016) Automatic band selection using spatial-structure information and classifier-based clustering. IEEE J Sel Top Appl Earth Obs Remote Sens 9(9):4352–4360
Cariou C, Chehdi K, Le Moan S (2011) BandClust: an unsupervised band reduction method for hyperspectral remote sensing. IEEE Geosci Remote Sens Lett 8(3):565–569
Cervantes J, Garcia-Lamont F, Rodríguez-Mazahua L, Lopez A (2020) A comprehensive survey on support vector machine classification: applications, challenges and trends. Neurocomputing 408:189–215
Chang CI, Liu KH (2014) Progressive band selection of spectral unmixing for hyperspectral imagery. IEEE Trans Geosci Remote Sens 52(4):2002–2017
Chang Chein-I, Qian Du, Sun Tzu-Lung, Althouse M (1999) A joint band prioritization and band-decorrelation approach to band selection for hyperspectral image classification. IEEE Trans Geosci Remote Sens 37(6):2631–2641
Chang CI, Wang S (2006) Constrained band selection for hyperspectral imagery. IEEE Trans Geosci Remote Sens 44(6):1575–1585
Chen Y, Lin Z, Zhao X, Wang G, Gu Y (2014) Deep learning-based classification of hyperspectral data. IEEE J Sel Top Appl Earth Obs Remote Sens 7(6):2094–2107
Chih-Wei Hsu, Chih-Jen Lin (2002) A comparison of methods for multiclass support vector machines. IEEE Trans Neural Netw 13(2):415–425
Chouhan SS, Kaul A, Singh UP (2018) Soft computing approaches for image segmentation: a survey. Multimed Tools Appl 77(21):28483–28537
Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20(3):273–297
Dopido I, Villa A, Plaza A, Gamba P (2012) A quantitative and comparative assessment of unmixing-based feature extraction techniques for hyperspectral image classification. IEEE J Sel Top Appl Earth Obs Remote Sens 5(2):421–435
Dou Z, Gao K, Zhang X, Wang H, Han L (2020) Band selection of hyperspectral images using attention-based autoencoders. IEEE Geosci Remote Sens Lett 18:147–151
Feng S, Itoh Y, Parente M, Duarte MF (2017) Hyperspectral band selection from statistical wavelet models. IEEE Trans Geosci Remote Sens 55(4):2111–2123
Foody G, Mathur A (2004) A relative evaluation of multiclass image classification by support vector machines. IEEE Trans Geosci Remote Sens 42(6):1335–1343
Fussell J, Rundquist D, Harrington JA (1986) On defining remote sensing. Photogramm Eng Remote Sens 52(9):1507–1511
Ghamisi P, Benediktsson JA (2015) Feature selection based on hybridization of genetic algorithm and particle swarm optimization. IEEE Geosci Remote Sens Lett 12(2):309–313
Goodfellow I, Bengio Y, Courville A (2016) Deep learning. MIT Press
Guo B, Gunn S, Damper R, Nelson J (2006) Band selection for hyperspectral image classification using mutual information. IEEE Geosci Remote Sens Lett 3(4):522–526
Harsanyi J, Chang CI (1994) Hyperspectral image classification and dimensionality reduction: an orthogonal subspace projection approach. IEEE Trans Geosci Remote Sens 32(4):779–785
Hedjam R, Cheriet M (2012) Hyperspectral band selection based on graph clustering. In: 2012 11th International conference on information science, signal processing and their applications (ISSPA). IEEE, pp 813–817
Jia S, Tang G, Zhu J, Li Q (2016) A novel ranking-based clustering approach for hyperspectral band selection. IEEE Trans Geosci Remote Sens 54(1):88–102
Kandavanam G, Botvich D, Balasubramaniam S, Jennings B (2010) A hybrid genetic algorithm/variable neighborhood search approach to maximizing residual bandwidth of links for route planning. Artif Evol. Springer, Berlin, pp 49–60
Katoch S, Chauhan SS, Kumar V (2021) A review on genetic algorithm: past, present, and future. Multimed Tools Appl 80(5):8091–8126
Kaur M, Kumar V (2018) Parallel non-dominated sorting genetic algorithm-II-based image encryption technique. Imaging Sci J 66(8):453–462
Kavitha AR, Chellamuthu C (2016) Brain tumour segmentation from MRI image using genetic algorithm with fuzzy initialisation and seeded modified region growing (GFSMRG) method. Imaging Sci J 64(5):285–297
Kumar B, Dikshit O, Gupta A, Singh MK (2020) Feature extraction for hyperspectral image classification: a review. Int J Remote Sens 41(16):6248–6287
Lamine S, Pandey MK, Petropoulos GP, GP, Brewer PA, Srivastava PK, Manevski K, Toulios L, Bachari N, Macklin MG (2020) Spectroradiometry as a tool for monitoring soil contamination by heavy metals in a floodplain site. In: Hyperspectral Remote Sensing. Elsevier, pp 249–268
Landgrebe D (2002) Hyperspectral image data analysis. IEEE Signal Process Mag 19(1):17–28
Lee C (2018) A review of applications of genetic algorithms in operations management. Eng Appl Artif Intell 76:1–12
Liu Y, Xie H, Wang L, Tan K (2016) Hyperspectral band selection based on a variable precision neighborhood rough set. Appl Opt 55(3):462
MartÍnez-UsÓMartinez-Uso A, Pla F, Sotoca JM, GarcÍa-Sevilla P (2007) Clustering-based hyperspectral band selection using information measures. IEEE Trans Geosci Remote Sens 45(12):4158–4171
Michalewicz Z (1996) Genetic algorithms + data structures = evolution programs. Springer, Berlin. https://doi.org/10.1007/978-3-662-03315-9
Michalewicz Z, Schoenauer M (1996) Evolutionary algorithms for constrained parameter optimization problems. Evol Comput 4(1):1–32
Mitchell M (1996) An introduction to genetic algorithms. MIT Press, Cambridge
Nasrabadi NM (2014) Hyperspectral target detection?: An overview of current and future challenges. IEEE Signal Process Mag 31(1):34–44
Peerlinck A, Sheppard J, Pastorino J, Maxwell B (2019) Optimal design of experiments for precision agriculture using a genetic algorithm. In: 2019 IEEE congress on evolutionary computation (CEC). IEEE, pp 1838–1845
Sermpinis G, Stasinakis C, Theofilatos K, Karathanasopoulos A (2015) Modeling, forecasting and trading the EUR exchange rates with hybrid rolling genetic algorithms—support vector regression forecast combinations. Eur J Oper Res 247(3):831–846
Shao Y, Lunetta RS (2012) Comparison of support vector machine, neural network, and CART algorithms for the land-cover classification using limited training data points. ISPRS J Photogramm Remote Sens 70:78–87
Shuaibu M, Lee WS, Schueller J, Gader P, Hong YK, Kim S (2018) Unsupervised hyperspectral band selection for apple Marssonina blotch detection. Comput Electron Agric 148:45–53
Sivanandam SN, Deepa SN (2008) Introduction to genetic algorithms. Springer, Berlin
Somers B, Asner GP (2013) Multi-temporal hyperspectral mixture analysis and feature selection for invasive species mapping in rainforests. Remote Sens Environ 136:14–27
Su H, Yang H, Du Q, Sheng Y (2011) Semisupervised band clustering for dimensionality reduction of hyperspectral imagery. IEEE Geosci Remote Sens Lett 8(6):1135–1139
Su H, Yong B, Du Q (2016) Hyperspectral band selection using improved firefly algorithm. IEEE Geosci Remote Sens Lett 13(1):68–72
Sun K, Geng X, Chen J, Ji L, Tang H, Zhao Y, Xu M (2016) A robust and efficient band selection method using graph representation for hyperspectral imagery. Int J Remote Sens 37(20):4874–4889
Sun W, Du Q (2018) Graph-regularized fast and robust principal component analysis for hyperspectral band selection. IEEE Trans Geosci Remote Sens 56(6):3185–3195
Sun W, Du Q (2019) Hyperspectral band selection: a review. IEEE Geosci Remote Sens Mag 7(2):118–139
Tong Q, Xue Y, Zhang L (2014) Progress in hyperspectral remote sensing science and technology in China over the past three decades. IEEE J Sel Top Appl Earth Obs Remote Sens 7(1):70–91
Vapnik VN (2000) The nature of statistical learning theory. Springer, New York
Varade D, Maurya AK, Dikshit O (2019) Unsupervised band selection of hyperspectral data based on mutual information derived from weighted cluster entropy for snow classification. Geocarto Int. https://doi.org/10.1080/10106049.2019.1665717
Whitley D (1994) A genetic algorithm tutorial. Stat Comput 4(2):65–85
Xie F, Li F, Lei C, Ke L (2018) Representative band selection for hyperspectral image classification. ISPRS Int J Geo-Inf 7(9):338
Yang H, Du Q, Chen G (2012) Particle swarm optimization-based hyperspectral dimensionality reduction for urban land cover classification. IEEE J Sel Top Appl Earth Obs Remote Sens 5(2):544–554
Yang R, Su L, Zhao X, Wan H, Sun J (2017) Representative band selection for hyperspectral image classification. J Vis Commun Image Represent 48:396–403
Yi Kim E, Jung K (2005) Genetic algorithms for video segmentation. Pattern Recognit 38(1):59–73
Yuan Y, Zhu G, Wang Q (2015) Hyperspectral band selection by multitask sparsity pursuit. IEEE Trans Geosci Remote Sens 53(2):631–644
Zeng M, Cai Y, Cai Z, Liu X, Hu P, Ku J (2019) Unsupervised hyperspectral image band selection based on deep subspace clustering. IEEE Geosci Remote Sens Lett 16(12):1889–1893
Zhang M, Ma J, Gong M (2017) Unsupervised hyperspectral band selection by fuzzy clustering with particle swarm optimization. IEEE Geosci Remote Sens Lett 14(5):773–777
Acknowledgements
First author is grateful to the University Grants Commission (UGC), New Delhi, India, for the research fellowship provided through UGC-JRF Scheme.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Singh, P.S., Karthikeyan, S. Enhanced classification of remotely sensed hyperspectral images through efficient band selection using autoencoders and genetic algorithm. Neural Comput & Applic 34, 21539–21550 (2022). https://doi.org/10.1007/s00521-021-06121-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-021-06121-4