Skip to main content
SpringerLink
Log in

A new neuro-fuzzy-based classification approach for hyperspectral remote sensing images

  • Published:
Journal of Earth System Science Aims and scope Submit manuscript

Abstract

Hyperspectral images are widely used in many applications. However, finding the appropriate hyperspectral image classification technique is a challenge. In this paper, we propose a new method by using an artificial intelligence-based method for hyperspectral image classification. The system has two parts: first, a pre-processing step, which helps the training phase to work faster; and second, the training part, which consists of calculating the neuro-fuzzy parameters. The prepared system is then applied to the classification of images. Three well-known hyperspectral datasets, including Pavia University from reflective optics system imaging spectrometer, the Botswana image from Hyperion and the Indian Pine image from airborne visible/infrared imaging spectrometer, were chosen to test the method. The final results of the experiments show that this system outperforms two classical methods of hyperspectral classification: support vector machine and spectral angle mapper. The comparison of the final results was made using two different metrics: overall accuracy and total disagreement. The proposed method increases the overall accuracy by about 5% for the Pavia University dataset, 2% for the Botswana dataset and 7% for the Indian Pine dataset. The total disagreement was reduced by about 0.01 for the Pavia University, 0.03 for the Botswana and 0.1 for the Indian Pine dataset when the proposed method was applied.

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

Similar content being viewed by others

References

  • Aghaee R and Mokhtarzade M 2015 Classification of hyperspectral images using subspace projection feature space; IEEE Geosci. Remote Lett. 12(9) 1803–1807.

    Article  Google Scholar 

  • Alajlan N, Bazi Y, Melgani F and Yager R R 2012 Fusion of supervised and unsupervised learning for improved classification of hyperspectral images; Inform. Sci. 217 39–55.

    Article  Google Scholar 

  • Arslan O 2009 A novel confidence estimation method for neural networks in multispectral image classification; Int. J. Dig. Earth 2(4) 343–358.

    Article  Google Scholar 

  • Benítez J M, Castro J L and Requena I 1997 Are artificial neural networks black boxes?; IEEE Trans. Neural Netw. 8(5) 1156–1164.

    Article  Google Scholar 

  • Bilgin G, Erturk S and Yildirim T 2008 Unsupervised classification of hyperspectral-image data using fuzzy approaches that spatially exploit membership relations; IEEE Geosci. Remote Lett. 5(4) 673–677.

    Article  Google Scholar 

  • Bishop C M 2006 Pattern recognition and machine learning; Springer, New York.

    Google Scholar 

  • Borasca B, Bruzzone L, Carlin L and Zusi M 2006 A fuzzy-input fuzzy-output SVM technique for classification of hyperspectral remote sensing images; In: Proceedings of the 7th Nordic Signal processing symposium, NORSIG 2006, pp. 2–5.

  • Braspenning P J and Thuijsman F 1995 Artificial neural network, an introduction to ANN theory and practice; Springer, Berlin.

    Google Scholar 

  • Chi H-M and Ersoy O K 2005 A statistical self-organizing learning system for remote sensing classification; IEEE Trans. Geosci. Remote 43(8) 1890–1900.

    Article  Google Scholar 

  • Dennison P E and Roberts D A 2003 Endmember selection for multiple endmember spectral mixture analysis using endmember average RMSE; Remote Sens. Environ. 87(2) 123–135.

    Article  Google Scholar 

  • Dennison P E, Halligan K Q and Roberts D A 2004 A comparison of error metrics and constraints for multiple endmember spectral mixture analysis and spectral angle mapper; Remote Sens. Environ. 93(3) 359–367.

    Article  Google Scholar 

  • Franke J, Roberts D A, Halligan K and Menz G 2009 Hierarchical multiple endmember spectral mixture analysis (MESMA) of hyperspectral imagery for urban environments; Remote Sens. Environ. 113(8) 1712–1723.

    Article  Google Scholar 

  • Hughes G 1968 On the mean accuracy of statistical pattern recognizers; IEEE Trans. Inform. Theory 14(1) 55–63.

    Article  Google Scholar 

  • Jimenez L O, Morales-Morell A and Creus A 1999 Classification of hyperdimensional data based on feature and decision fusion approaches using projection pursuit, majority voting, and neural networks; IEEE Geosci. Remote Lett. 37(3) 1360–1366.

    Article  Google Scholar 

  • Jolliffe I 2002 Principal component analysis; John Wiley and Sons, Ltd.

  • Kohonen T 1990 The self-organizing map; Proc. IEEE 78(9) 1464–1480.

    Article  Google Scholar 

  • Kumar T, Prasad R, Choudhary A, Mishra V N, Gupta D K and Srivastava P K 2016 A statistical significance of differences in classification accuracy of crop types using different classification algorithms; Geocarto Int. 32(2) 206–224.

    Google Scholar 

  • Kuo B-C, Huang W-C, Liu H-C and Tseng S-C 2008 A novel fuzzy c-means method for hyperspectral image classification; In: Geoscience and remote sensing symposium 2008, IGARSS 2008, IEEE International 2, II-1002.

  • Mehrotro K, Mohan C K and Ranka S 2000 Elements of artificial neural networks (2nd edn), MIT Press, Cambridge.

    Google Scholar 

  • Mojaradi B, Abrishami-Moghaddam H, Zoej M J V and Duin R P 2009 Dimensionality reduction of hyperspectral data via spectral feature extraction; IEEE Trans. Geosci. Remote 47(7) 2091–2105.

    Article  Google Scholar 

  • Nauck D, Klawonn F and Kruse R 1997 Foundations of neuro-fuzzy systems; John Wiley & Sons, Ltd.

  • Neuenschwander A L, Crawford M M and Ringrose S 2005 Results from the EO-1 experiment – A comparative study of earth observing-1 advanced land imager (ALI) and Landsat ETM + data for land cover mapping in the Okavango delta, Botswana; Int. J. Remote 26(19) 4321–4337.

    Article  Google Scholar 

  • Nomura T and Miyoshi T 1995 An adaptive rule extraction with the fuzzy self-organizing map and a comparison with other methods; In: Third international symposium on uncertainty modeling and analysis, 1995, and annual conference of the North American Fuzzy Information Processing Society, Proceedings of ISUMA-NAFIPS’95.

  • Petropoulos G P, Kalivas D P, Georgopoulou I A and Srivastava P K 2015 Urban vegetation cover extraction from hyperspectral imagery and geographic information system spatial analysis techniques: Case of Athens, Greece J. Appl. Remote Sens. 9 096088.

    Article  Google Scholar 

  • Picón A, Ghita O, Whelan P F and Iriondo P M 2009 Fuzzy spectral and spatial feature integration for classification of nonferrous materials in hyperspectral data; IEEE Trans. Ind. Inform. 5(4) 483–494.

    Article  Google Scholar 

  • Pontius Jr R G and Millones M 2011 Death to Kappa: Birth of quantity disagreement and allocation disagreement for accuracy assessment; Int. J. Remote 32(15) 4407–4429.

    Article  Google Scholar 

  • Qiu F 2008 Neuro-fuzzy based analysis of hyperspectral imagery; Photogramm. Eng. Remote Sens. 74(10) 1235–1247.

    Article  Google Scholar 

  • Qiu F and Jensen J 2004 Opening the black box of neural networks for remote sensing image classification; Int. J. Remote 25(9) 1749–1768.

    Article  Google Scholar 

  • Ratle F, Camps-Valls G and Weston J 2010 Semisupervised neural networks for efficient hyperspectral image classification; IEEE Trans. Geosci. Remote 48(5) 2271–2282.

    Article  Google Scholar 

  • Richards J A 2013 Remote sensing digital image analysis (5th edn), Springer, Canberra.

    Book  Google Scholar 

  • Singh S K, Srivastava P K, Gupta M, Thakur J K and Mukherjee S 2014 Appraisal of land use/land cover of mangrove forest ecosystem using support vector machine; Environ. Earth Sci. 71 2245–2255.

    Article  Google Scholar 

  • Somers B, Asner G P, Tits L and Coppin P 2011 Endmember variability in spectral mixture analysis: A review; Remote Sens. Environ. 115(7) 1603–1616.

    Article  Google Scholar 

  • Song C 2005 Spectral mixture analysis for subpixel vegetation fractions in the urban environment: How to incorporate endmember variability?; Remote Sens. Environ. 95(2) 248–263.

    Article  Google Scholar 

  • Srivastava P K, Han D, Rico-Ramirez M A, Bray M and Islam T 2012 Selection of classification techniques for land use/land cover change investigation; Adv. Space Res. 50 1250–1265.

    Article  Google Scholar 

  • Su M and Tew C 2000 A self-organizing feature-map-based fuzzy system; In: Proceedings of the IEEE-INNS-ENNS international joint conference on neural networks, IJCNN 2000, pp. 20–25.

    Google Scholar 

  • Torabi A J, Er M J, Lim B S, Zhai L, Oentaryo R J, Peen G O and Zurada J M 2015 A survey on artificial intelligence-based modeling techniques for high speed milling processes; IEEE Syst. J. 9(3) 1069–1080.

  • Yamany S M, Farag A A and Hsu S-Y 1999 A fuzzy hyperspectral classifier for automatic target recognition (ATR) systems; Pattern Recogn. Lett. 20(11) 1431–1438.

    Article  Google Scholar 

  • Zhang J and Foody G 2001 Fully-fuzzy supervised classification of sub-urban land cover from remotely sensed imagery: Statistical and artificial neural network approaches; Int. J. Remote 22(4) 615–628.

    Article  Google Scholar 

  • Zhang C and Xie Z 2012 Combining object-based texture measures with a neural network for vegetation mapping in the Everglades from hyperspectral imagery; Remote Sens. Environ. 124 310–320.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. K.N. Toosi University of Technology, Vali-Asr Street, Mirdamad Cross, Tehran, 19967-15433, Iran

    Nafiseh Kakhani & Mehdi Mokhtarzade

Authors
  1. Nafiseh Kakhani
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mehdi Mokhtarzade
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Nafiseh Kakhani.

Additional information

Corresponding editor: Prasanth K Srivastava

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Kakhani, N., Mokhtarzade, M. A new neuro-fuzzy-based classification approach for hyperspectral remote sensing images. J Earth Syst Sci 128, 30 (2019). https://doi.org/10.1007/s12040-018-1054-9

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s12040-018-1054-9

Keywords

Search

Navigation