Skip to main content
SpringerLink
Log in

A probabilistic framework for weighted combination of multiple-feature classifications of hyperspectral images

  • Research Article
  • Published:
Earth Science Informatics Aims and scope Submit manuscript

Abstract

Spatial information such as texture and shape features as well as spatial contextual information play a key role in representation and analysis of hyperspectral images. Spatial information improves the classification accuracy and addresses the common problem of pixel-wise classification methods, i.e. limited training samples. In this article, a new combination of spectral, texture and shape features, as well as, contextual information in the probabilistic framework is proposed. The texture features are extracted utilizing Gabor filters and the shape features are represented by morphological profiles. The spectral, texture and shape features are separately fed into a probabilistic support vector machine classifier to estimate the per-pixel probability. These probabilities are combined together to calculate the total probability on which three weights determine the efficacy of each one. Finally, the classification result obtained in the previous step is refined by majority voting within the shape adaptive neighbourhood of each pixel. Instead of the simple majority vote we applied the majority vote in the probabilistic framework on which the reliability of the labels in the region is also considered. Experiments on three hyperspectral images: Indian Pines, Pavia University, and Salinas demonstrate the efficiency of the proposed method for the classification of hyperspectral images, especially with limited training samples. Moreover, after comparing with some recent spectral–spatial classification methods, the performance of the proposed method is demonstrated.

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

Similar content being viewed by others

References

  • Benediktsson JA, Ghamisi P (2015) Spectral-spatial classification of hyperspectral remote sensing images. Artech House 

  • Benediktsson JA, Palmason JA, Sveinsson JR (2005) Classification of hyperspectral data from urban areas based on extended morphological profiles. IEEE Trans Geosci Remote Sens 43(3):480–491

    Google Scholar 

  • Camps-Valls G, Bruzzone L (2005) Kernel-based methods for hyperspectral image classification. IEEE Trans Geosci Remote Sens 43(6):1351–1362

    Google Scholar 

  • Camps-Valls G, Gomez-Chova L, Munoz-Mari J, Vila-Frances J, Calpe-Maravilla J (2006) Composite kernels for hyperspectral image classification. IEEE Geosci Remote Sens Lett 3(1):93–97

    Google Scholar 

  • Camps-Valls G, Tuia D, Bruzzone L, Benediktsson JA (2014) Advances in hyperspectral image classification: earth monitoring with statistical learning methods. IEEE Signal Process Mag 31(1):45–54

    Google Scholar 

  • Canty MJ (2014) Image analysis, classification, and change detection in remote sensing with algorithms for ENVI/IDL, 3rd edn. CRC Press, Boca Raton

    Google Scholar 

  • Chang CC, Lin CJ (2011) LIBS SVM: a library for support vector machines. ACM Trans Intell Syst Technol 2(3):1–27 (software available at: www.csie.ntu.edu.tw/~cjlin/libsvm)

    Google Scholar 

  • Chen Y, Nasrabadi NM, Tran TD (2011) Hyperspectral image classification using dictionary-based sparse representation. IEEE Trans Geosci Remote Sens 49:3973–3985

    Google Scholar 

  • Cohen J (1960) A coefficient of agreement from nominal scales. Educ Psychol Meas 20: 37–46. https://doi.org/10.1177/001316446002000104

    Google Scholar 

  • Dalla Mura M, Benediktsson JA, Waske B, Bruzzone L (2010) Extended profiles with morphological attribute filters for the analysis of hyperspectral data. Int J Remote Sens 31(22):5975–5991

    Google Scholar 

  • Daugman J (1985) Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters. J Opt Soc Am A 2(7):1160–1169

    Google Scholar 

  • Fang L, Li S, Kang X, Benediktsson JA (2014) Spectral–spatial hyperspectral image classification via multiscale adaptive sparse representation. IEEE Trans Geosci Remote Sens 52(12):7738–7749

    Google Scholar 

  • Fang L, Li S, Duan W, Ren J, Benediktsson JA (2015) Classification of hyperspectral images by exploiting spectral–spatial information of superpixel via multiple kernels. IEEE Trans Geosci Remote Sens 53:6663–6674

    Google Scholar 

  • Fang L, Wang C, Li S, Benediktsson JA (2017) Hyperspectral image classification via multiple-feature-based adaptive sparse representation. IEEE Trans Instrum Meas 66:1646–1657

    Google Scholar 

  • Fang L, He N, Li S, Ghamisi P, Benediktsson JA (2018a) Extinction profiles fusion for hyperspectral images classification. IEEE Trans Geosci Remote Sens 56:1803–1815

    Google Scholar 

  • Fang L, He N, Li S, Plaza AJ, Plaza J (2018b) A new spatial–spectral feature extraction method for hyperspectral images using local covariance matrix representation. IEEE Trans Geosci Remote Sens 56:3534–3546

    Google Scholar 

  • Fang L, Liu G, Li S, Ghamisi P, Benediktsson JA (2018c) Hyperspectral image classification with squeeze multibias network IEEE Transactions on Geoscience and Remote Sensing 57:1291-1301

    Google Scholar 

  • Fauvel M, Tarabalka Y, Benediktsson JA, Chanussot J, Tilton JC (2013) Advances in spectral-spatial classification of hyperspectral images. Proc IEEE 101(3):652–675

    Google Scholar 

  • Fu W, Li S, Fang L, Kang X, Benediktsson JA (2016) Hyperspectral image classification via shape-adaptive joint sparse representation. IEEE J Sel Top Appl Earth Obs Remote Sens 9:556–567

    Google Scholar 

  • Ghamisi P, Souza R, Benediktsson JA, Rittner L, Lotufo R, Zhu XX (2016) Hyperspectral data classification using extended extinction profiles. IEEE Geosci Remote Sens Lett 13:1641–1645

    Google Scholar 

  • Golipour M, Ghassemian H, Mirzapour F (2016) Integrating hierarchical segmentation maps with MRF prior for classification of hyperspectral images in a Bayesian framework. IEEE Trans Geosci Remote Sens 54:805–816

    Google Scholar 

  • Guo X, Huang X, Zhang L (2014) Three-dimensional wavelet texture feature extraction and classification for multi/hyperspectral imagery. IEEE Geosci Remote Sens Lett 11:2183–2187

    Google Scholar 

  • Huo L-Z, Tang P (2011) Spectral and spatial classification of hyperspectral data using SVMs and Gabor textures. In: 2011 IEEE International Geoscience and Remote Sensing Symposium pp 1708–1711

  • Jia X, Kuo B-C, Crawford MM (2013) Feature mining for hyperspectral image classification. Proc IEEE 101:676–697

    Google Scholar 

  • Kang X, Li S, Benediktsson JA (2014) Spectral–spatial hyperspectral image classification with edge-preserving filtering. IEEE Trans Geosci Remote Sens 52:2666–2677

    Google Scholar 

  • Khodadadzadeh M, Li J, Plaza A, Ghassemian H, Bioucas-Dias JM, Li X (2014) Spectral–spatial classification of hyperspectral data using local and global probabilities for mixed pixel characterization. IEEE Trans Geosci Remote Sens 52:6298–6314

    Google Scholar 

  • Kianisarkaleh A, Ghassemian H (2016) Nonparametric feature extraction for classification of hyperspectral images with limited training samples. ISPRS J Photogramm Remote Sens 119:64–78

    Google Scholar 

  • Li G, Wan Y (2015) A new combination classification of pixel-and object-based methods. Int J Remote Sens 36:5842–5868

    Google Scholar 

  • Li J, Bioucas-Dias JM, Plaza A (2011) Hyperspectral image segmentation using a new Bayesian approach with active learning. IEEE Trans Geosci Remote Sens 49(10):3947–3960

    Google Scholar 

  • Li J, Marpu PR, Plaza A, Bioucas-Dias JM, Benediktsson JA (2013) Generalized composite kernel framework for hyperspectral image classification. IEEE Trans Geosci Remote Sens 51:4816–4829

    Google Scholar 

  • Li J, Huang X, Gamba P, Bioucas-Dias JM, Zhang L, Benediktsson JA, Plaza A (2015) Multiple feature learning for hyperspectral image classification. IEEE Trans Geosci Remote Sens 53:1592–1606

    Google Scholar 

  • Li S, Ni L, Jia X, Gao L, Zhang B, Peng M (2016) Multi-scale superpixel spectral–spatial classification of hyperspectral images. Int J Remote Sens 37:4905–4922

    Google Scholar 

  • Liu J, Lu W (2016) A probabilistic framework for spectral–spatial classification of hyperspectral images. IEEE Trans Geosci Remote Sens 54:5375–5384

    Google Scholar 

  • Matheron G (1975) Random sets and integral geometry. Wiley, New York 

  • Mirmehdi M (2008) Handbook of texture analysis. Imperial College Press

  • Mirzapour F, Ghassemian H (2015) Improving hyperspectral image classification by combining spectral, texture, and shape features. Int J Remote Sens 36:1070–1096

    Google Scholar 

  • Negri RG, Dutra LV, Sant’Anna SJS (2014) An innovative support vector machine based method for contextual image classification. ISPRS J Photogramm Remote Sens 87:241–248

    Google Scholar 

  • Seifi Majdar R, Ghassemian H (2017a) Spectral-Spatial classification of hyperspectral images using functional data analysis. Remote Sens Lett 8:488–497

    Google Scholar 

  • Seifi Majdar R, Ghassemian H (2017b) A probabilistic SVM approach for hyperspectral image classification using spectral and texture features. Int J Remote Sens 38:4265–4284

    Google Scholar 

  • Serra J (1983) Image analysis and mathematical morphology. Academic Press, Inc.

  • Soille P (2013) Morphological image analysis: principles and applications. Springer Science & Business Media

  • Solberg AHS, Taxt T, Jain AK (1996) A Markov random field model for classification of multisource satellite imagery. IEEE Trans Geosci Remote Sens 34:100–113

    Google Scholar 

  • Tarabalka Y, Fauvel M, Chanussot J, Benediktsson JA (2010a) SVM-and MRF-based method for accurate classification of hyperspectral images. IEEE Geosci Remote Sens Lett 7:736–740

    Google Scholar 

  • Tarabalka Y, Chanussot J, Benediktsson JA (2010b) Segmentation and classification of hyperspectral images using watershed transformation. Pattern Recogn 43:2367–2379

    Google Scholar 

  • Vapnik VN (2000) The nature of statistical learning theory, 2nd edn. Springer-Verlag, New York

    Google Scholar 

  • Wang Y, Duan H (2018) Classification of hyperspectral images by SVM using a composite kernel by employing spectral, spatial and hierarchical structure information. Remote Sens 10:441

    Google Scholar 

  • Wang Y, Duan H (2019) Spectral–spatial classification of hyperspectral images by algebraic multigrid based multiscale information fusion. Int J Remote Sens 40:1301–1330

    Google Scholar 

  • Wang L, Shi C, Diao C, Ji W, Yin D (2016a) A survey of methods incorporating spatial information in image classification and spectral unmixing. Int J Remote Sens 37:3870–3910

    Google Scholar 

  • Wang Y, Song H, Zhang Y (2016b) Spectral-spatial classification of hyperspectral images using joint bilateral filter and graph cut based model. Remote Sens 8:748

    Google Scholar 

  • Wu T-F, Lin C-J, Weng RC (2004) Probability estimates for multi-class classification by pairwise coupling. J Mach Learn Res 5:975–1005

    Google Scholar 

  • Zehtabian A, Ghassemian H (2015) An adaptive pixon extraction technique for multispectral/hyperspectral image classification. IEEE Geosci Remote Sens Lett 12:831–835

    Google Scholar 

  • Zhang B, Li S, Jia X, Gao L, Peng M (2011) Adaptive Markov random field approach for classification of hyperspectral imagery. IEEE Geosci Remote Sens Lett 8:973–977

    Google Scholar 

  • Zhang L, Zhang L, Tao D, Huang X (2012) On combining multiple features for hyperspectral remote sensing image classification. IEEE Trans Geosci Remote Sens 50:879–893

    Google Scholar 

  • Zhang H, Li J, Huang Y, Zhang L (2014) A nonlocal weighted joint sparse representation classification method for hyperspectral imagery. IEEE J Sel Top Appl Earth Obs Remote Sens 7:2056–2206

    Google Scholar 

  • Zhu J, Fang L, Ghamisi P (2018) Deformable convolutional neural networks for hyperspectral image classification. IEEE Geosci Remote Sens Lett 15:1254–1258

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Electrical Engineering, Ardabil Branch, Islamic Azad University, Ardabil, Iran

    Reza Seifi Majdar

  2. Image Processing and Information Analysis Lab, Faculty of Computer and Electrical Engineering, Tarbiat Modares University, Tehran, Iran

    Hassan Ghassemian

Authors
  1. Reza Seifi Majdar
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hassan Ghassemian
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Reza Seifi Majdar.

Additional information

Communicated by: H. Babaie

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

Seifi Majdar, R., Ghassemian, H. A probabilistic framework for weighted combination of multiple-feature classifications of hyperspectral images. Earth Sci Inform 13, 55–69 (2020). https://doi.org/10.1007/s12145-019-00411-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12145-019-00411-1

Keywords

Search

Navigation