Skip to main content
SpringerLink
Log in

An effective feature extraction method via spectral-spatial filter discrimination analysis for hyperspectral image

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Multi band, high spatial resolution and information redundancy are the most significant characteristics of hyperspectral image. These remarkable characteristics are mainly caused by the high-dimensional image data. In view of these characteristics, feature extraction of hyperspectral image has naturally become one of the research hotspots in this field. However, it is impossible to fully describe the intrinsic geometric structure of hyperspectral image only by using spectral information. To improve the subsequent forecasting accuracy, spatial information should be mined to further describe the geometric structure of hyperspectral image. Therefore, an effective feature extraction method (SSF_HM) was proposed via using harmonic mean and spectral-spatial filter. This investigation divides the SSF_HM into three steps. First, the pi principal components were extracted by using principal components analysis (PCA) skill and subsequent the pi spatial filtering features were obtained via using area median filter (AMF) method. Then, the original spectral features and extracted spatial filtering features combine to form the fusion feature matrix, and then the scatter matrix \(S_{b}^{HM}\) (based on harmonic mean (HM) spectral-spatial filter inter-class) and scatter matrix \(S_{w}^{HM}\) (based on harmonic mean (HM) spectral-spatial filter intra-class) can be established in the fusion feature space, respectively. Finally, combining the Fisher discriminant analysis model and regularization technique, a new feature extraction method SSF_HM is developed. The proposed SSF_HM method combines spectral information and spatial information. At the same time, the range of feature extraction is expanded from spectral space to spectral-spatial fusion space. The experimental results on three real-world hyperspectral image data sets show the better performance of SSF_HM in comparison with other feature extraction methods in small sample size situation by using maximum likelihood classifier (MLC).

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

References

  1. Ait-Sahalia Y, Xiu D (2019) Principal component analysis of high-frequency data[J]. J Am Stat Assoc 114(525):287–303

    Article  MathSciNet  MATH  Google Scholar 

  2. Bi Z, Yu L, Gao H, Zhou P, Yao H (2020) Improved VGG model-based efficient traffic sign recognition for safe driving in 5G scenarios[J]. Int J Mach Learn Cybern. https://doi.org/10.1007/s13042-020-01185-5https://doi.org/10.1007/s13042-020-01185-5

  3. Cai D, He X, Han J (2007) Semi-supervised discriminant analysis[C]. In: IEEE 11th International conference on computer vision, 2007. ICCV 2007. IEEE, 1–7

  4. Chang CI, Ren H (2000) An experiment-based quantitative and comparative analysis of target detection and image classification algorithms for hyperspectral imagery[J]. IEEE Trans Geosci Remote Sens 38(2):1044–1063

    Article  Google Scholar 

  5. Chang CI, Safavi H (2011) Progressive dimensionality reduction by transform for hyperspectral imagery[J]. Pattern Recogn 44(10-11):2760–2773

    Article  Google Scholar 

  6. Chen T, Xu J, Ying H, Chen X, Feng R, Fang X, Gao H, Wu J (2019) Prediction of extubation failure for intensive care unit patients using light gradient boosting machine[J]. IEEE Access 7(1):150960-150968. https://doi.org/10.1109/ACCESS.2019.2946980

    Article  Google Scholar 

  7. Chen J, Ying H, Liu X, Gu J, Feng R, Chen T, Gao H, Wu JA (2020) Transfer learning based super-resolution microscopy for biopsy slice images: the joint methods perspective[J]. IEEE/ACM Trans Comput Biol Bioinf (TCBB). https://doi.org/10.1109/TCBB.2020.2991173

  8. Chen S, Zhang D (2011) Semisupervised dimensionality reduction with pairwise constraints for hyperspectral image classification[J]. IEEE Geosci Remote Sens Lett 8(2):369–373

    Article  Google Scholar 

  9. David L (2002) Hyperspectral image data analysis as a high dimensional signal processing problem[J]. IEEE Signal Processing Mag 19(1):17–28

    Article  Google Scholar 

  10. Elton EJ, Gruber MJ, Brown SJ et al (2011) Modern portfolio theory and investment analysis[M]. Wiley, Hoboken

    Google Scholar 

  11. Fabija n ska A, Sankowski D (2011) Noise adaptive switching median-based filter for impulse noise removal from extremely corrupted images[J]. IET Image Processing 5(5):472–480

    Article  Google Scholar 

  12. Fauvel M, Chanussot J, Benediktsson JA (2009) Kernel principal component analysis for the classification of hyperspectral remote sensing data over urban areas[J]. EURASIP J Adv Signal Process 2009(1):783194

    Article  Google Scholar 

  13. Gao J, Xu L (2015) An efficient method to solve the classification problem for remote sensing image[J]. AEU-Int J Electron Commun 69(1):198–205

    Article  Google Scholar 

  14. Gao J, Xu L (2016) A novel spatial analysis method for remote sensing image classification[J]. Neural Process Lett 43(3):805–821

    Article  Google Scholar 

  15. Gao J, Xu L, Huang F (2016) A spectral-textural kernel-based classification method of remotely sensed images[J]. Neural Comput Applic 27(2):431–446

    Article  Google Scholar 

  16. Gao J, Xu L, Shen J et al (2015) A novel information transferring approach for the classification of remote sensing images[J]. EURASIP J Adv Signal Process 2015(1):38

    Article  Google Scholar 

  17. Gao J, Xu L, Shi A et al (2014) A kernel-based block matrix decomposition approach for the classification of remotely sensed images[J]. Appl Math Comput 228:531–545

    MathSciNet  MATH  Google Scholar 

  18. Gao W, Zhu Y, Zhang W, Zhang K, Gao H (2019) A hierarchical recurrent approach to predict scene graphs from a visual-attention-oriented perspective[J]. Comput Intell 35:496–516. https://doi.org/10.1111/coin.12202https://doi.org/10.1111/coin.12202

    Article  MathSciNet  Google Scholar 

  19. Ghamisi P, Benediktsson JA, Sveinsson JR (2014) Automatic spectral-spatial classification framework based on attribute profiles and supervised feature extraction[J]. IEEE Trans Geosci Remote Sens 52(9):5771–5782

    Article  Google Scholar 

  20. Guo AJX, Zhu F (2019) Spectral-spatial feature extraction and classification by ANN supervised with center loss in hyperspectral imagery[J]. IEEE Trans Geosci Remote Sens 57(3):1755–1767

    Article  Google Scholar 

  21. Guo-Feng F, Li-Ling P, Wei-Chiang H, Sun F Electric Load Forecasting by the SVR Model with Differential Empirical Mode Decomposition and Auto Regression[J]. Neurocomputing, https://doi.org/10.1016/j.neucom.2015.08.051

  22. He X, Cai D, Yan S et al (2005) Neighborhood preserving embedding[C]. In: Tenth IEEE international conference on computer vision, 2005. ICCV 2005. IEEE, 2, 1208–1213

  23. He X, Niyogi P (2004) Locality preserving projections[C]. Advan Neural Inform Process Syst:153–160

  24. Hong W-C (2011) Electric load forecasting by seasonal recurrent SVR (support vector regression) with chaotic artificial bee colony algorithm[J]. Energy 36:5568–5578

    Article  Google Scholar 

  25. Hosseini SA, Ghassemian H (2016) Hyperspectral data feature extraction using rational function curve fitting[J]. Int J Pattern Recogn Artif Intell 30 (01):1650001. https://doi.org/10.1142/S0218001416500014

    Article  MathSciNet  Google Scholar 

  26. Hosseini SA, Ghassemian H (2016) Rational function approximation for feature reduction in hyperspectral data[J]. Remote Sensing Letters 7(2):101–110

    Article  Google Scholar 

  27. Ibrahim H, Kong NSP, Ng TF (2008) Simple adaptive median filter for the removal of impulse noise from highly corrupted images[J]. IEEE Trans Consum Electron 54(4):1920–1927

    Article  Google Scholar 

  28. Imani M, Ghassemian H (2015) Feature space discriminant analysis for hyperspectral data feature reduction[J]. ISPRS J Photogramm Remote Sens 102:1–13

    Article  Google Scholar 

  29. Jiang J, Ma J, Chen C et al (2018) SuperPCA: a superpixelwise PCA approach for unsupervised feature extraction of hyperspectral imagery[J]. IEEE Trans Geoscience Remote Sens (99):1–13

  30. Journaux L, Tizon X, Foucherot I et al (2006) Dimensionality reduction techniques: an operational comparison on multispectral satellite images using unsupervised clustering[C]. In: Proceedings of the 7th Nordic, Signal Processing Symposium, 2006. NORSIG 2006. IEEE, 242–245

  31. Kuo BC, Landgrebe DA (2004) Nonparametric weighted feature extraction for classification[J]. IEEE Trans Geosci Remote Sens 42(5):1096–1105

    Article  Google Scholar 

  32. Landgrebe DA (2005) Signal theory methods in multispectral remote sensing [M]. Wiley, Hoboken

    Google Scholar 

  33. Li L, Ge H, Gao J (2017) A spectral-spatial kernel-based method for hyperspectral imagery classification[J]. Adv Space Res 59(4):954–967

    Article  Google Scholar 

  34. Li L, Ge H, Gao J et al (2019) Hyperspectral image feature extraction using maclaurin series function curve Fitting[J]. Neural Process Lett 49 (1):357–374

    Article  Google Scholar 

  35. Li L, Ge H, Gao J et al (2019) A novel geometric mean feature space discriminant analysis method for hyperspectral image feature extraction[J]. Neural Process Lett. https://doi.org/10.1007/s11063-019-10101-0https://doi.org/10.1007/s11063-019-10101-0

  36. Li M-W, Geng J, Hong W-C, Zhang L-D (2019) Periodogram estimation based on LSSVR-CCPSO compensation for forecasting ship motion[J]. Nonlinear Dyn 97:2579–2594

    Article  Google Scholar 

  37. Liao W, Pizurica A, Scheunders P et al (2013) Semisupervised local discriminant analysis for feature extraction in hyperspectral images[J]. IEEE Trans Geosci Remote Sens 51(1):184–198

    Article  Google Scholar 

  38. Ou D, Tan K, Du Q et al (2019) A novel tri-training technique for the semi-supervised classification of hyperspectral images based on regularized local discriminant embedding feature extraction[J]. Remote Sens 11(6):654

    Article  Google Scholar 

  39. Park CH, Park H (2008) A comparison of generalized linear discriminant analysis algorithms[J]. Pattern Recogn 41(3):1083–1097

    Article  MATH  Google Scholar 

  40. Plaza A, Martinez P, Plaza J et al (2005) Dimensionality reduction and classification of hyperspectral image data using sequences of extended morphological transformations[J]. IEEE Trans Geoscience Remote Sens 43(3):466–479

    Article  Google Scholar 

  41. Ren J, Zabalza J, Marshall S et al (2014) Effective feature extraction and data reduction in remote sensing using hyperspectral imaging[J]. IEEE Signal Proc Mag 31(4):149–154

    Article  Google Scholar 

  42. Sugiyama M, Id e T, Nakajima S et al (2010) Semi-supervised local fisher discriminant analysis for dimensionality reduction[J]. Mach Learn 78(1–2):35

    Article  MathSciNet  MATH  Google Scholar 

  43. Tarabalka Y, Benediktsson JA, Chanussot J (2009) Spectral-spatial classification of hyperspectral imagery based on partitional clustering techniques[J]. IEEE Trans Geosci Remote Sens 47(8):2973–2987

    Article  Google Scholar 

  44. Wang M, Yu J, Niu L et al (2017) Unsupervised feature extraction for hyperspectral images using combined low rank representation and locally linear embedding[C]. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, 1428–1431

  45. Wei-Chiang H, Dong Y, Zhang W, Li-Yueh C, Panigrahi BK (2013) Cyclic electric load forecasting by seasonal SVR with chaotic genetic algorithm[J]. Electr Power Energy Syst 44:604–614

    Article  Google Scholar 

  46. Xia J, Du P, He X et al (2013) Hyperspectral remote sensing image classification based on rotation forest[J]. IEEE Geosci Remote Sens Lett 11(1):239–243

    Article  Google Scholar 

  47. Xiao J, Xu H, Gao H, Bian M, Li Y (2020) A weakly supervised semantic segmentation network by aggregating seed cues[J]. ACM Trans Multimed Comput Commun Appl (TOMM). https://doi.org/10.1145/3419842

  48. Zabalza J, Ren J, Yang M et al (2014) Novel folded-PCA for improved feature extraction and data reduction with hyperspectral imaging and SAR in remote sensing[J]. ISPRS J Photogramm Remote Sens 93:112–122

    Article  Google Scholar 

  49. Zhang Z, Ding S, Jia W (2019) A hybrid optimization algorithm based on cuckoo search and differential evolution for solving constrained engineering problems[J]. Eng Appl Artif Intell 85:254–268

    Article  Google Scholar 

  50. Zhang Z, Ding S, Sun Y (2020) A support vector regression model hybridized with chaotic krill herd algorithm and empirical mode decomposition for regression task[J]. Neurocomputing 410:185–201

    Article  Google Scholar 

  51. Zhang Z, Wei-Chiang H (2019) Electric load forecasting by complete ensemble empirical mode decomposition adaptive noise and support vector regression with quantum-based dragonfly algorithm[J]. Nonlinear Dyn 98:1107–1136

    Article  Google Scholar 

  52. Zhang T, Yang J, Zhao D et al (2007) Linear local tangent space alignment and application to face recognition[J]. Neurocomputing 70(7–9):1547–1553

    Article  Google Scholar 

  53. Zhang L, Zhang L, Du B et al (2019) Hyperspectral image unsupervised classification by robust manifold matrix factorization[J]. Inf Sci 485:154–169

    Article  MathSciNet  MATH  Google Scholar 

  54. Zhou Y, Peng J, Chen CLP (2015) Dimension reduction using spatial and spectral regularized local discriminant embedding for hyperspectral image classification[J]. IEEE Trans Geosci Remote Sens 53:1082–1095

    Article  Google Scholar 

Download references

Acknowledgements

This work is partly supported by the Doctoral Research Foundation of Jining Medical University under Grant No.2018JYQD03, and the Doctoral Research Foundation of Jining Medical University for Dr. Li Li, and a Project of Shandong Province Higher Educational Science and Technology Program under Grant No.J18KA217, China.

Author information

Authors and Affiliations

  1. School of Medical Information Engineering, Jining Medical University, Rizhao, Shandong, 276826, China

    Li Li & Jianqiang Gao

  2. Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence, Jiangnan University, Wuxi, 214122, China

    Li Li, Hongwei Ge, Yixin Zhang & Haifei Zhang

Authors
  1. Li Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jianqiang Gao
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hongwei Ge
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yixin Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Haifei Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jianqiang Gao.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Li, L., Gao, J., Ge, H. et al. An effective feature extraction method via spectral-spatial filter discrimination analysis for hyperspectral image. Multimed Tools Appl 81, 40871–40904 (2022). https://doi.org/10.1007/s11042-022-13121-6

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-022-13121-6

Keywords

Search

Navigation