[go: up one dir, main page]
More Web Proxy on the site http://driver.im/ Skip to main content
Springer Nature Link
Log in

Deep Siamese Network with Handcrafted Feature Extraction for Hyperspectral Image Classification

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

Abstract

The prominence of deep learning models for classification of hyperspectral images is directly proportional to their ability to exploit spatial context and spectral bands jointly. The effectiveness of these deep learning models, however, is heavily reliant on a good amount of labelled training samples. In contrast, one of the biggest challenges with hyperspectral images is limited labelled samples availability as getting the samples annotated is a time consuming and labor-intensive process. Traditional machine learning algorithms are available for classification with a higher training time and very deep pre-trained networks like GoogleNet and VGGNet did not work well for hyperspectral image classification. The idea of one shot classification has been quite motivating in recent years to deal with the problems of limited labelled samples, imbalanced distribution of samples leading to poor classification results and overfitting. To implement one shot classification model and overcome these challenges, the proposed work is based on Siamese network that can work with limited samples or imbalanced samples. The proposed Siamese network has a handcrafted feature generation network that extracts discriminative features from the image. Experimental findings on two benchmark hyperspectral datasets demonstrate that the proposed network is capable of improving the classification performance with an overall accuracy of 95.17 and 93.25 for Pavia U and Indian Pines dataset respectively with a small scale trained data.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
£29.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (United Kingdom)

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
Fig. 13
Fig. 14
Fig. 15

Similar content being viewed by others

Data Availability

All the related data can be found at https://www.ehu.eus/ccwintco/index.php/Hyperspectral_Remote_Sensing_Scenes.

References

  1. Bandos TV, Bruzzone L, Camps-Valls G (2009) Classification of hyperspectral images with regularized linear discriminant analysis. IEEE Trans Geosci Remote Sens 47(3):862–873. https://doi.org/10.1109/TGRS.2008.2005729

    Article  Google Scholar 

  2. Cai W, Wei Z (2022) Remote sensing image classification based on a cross-attention mechanism and graph convolution. IEEE Geosci Remote Sens Lett 19:1–5. https://doi.org/10.1109/LGRS.2020.3026587

    Article  Google Scholar 

  3. Chapel L, Burger T, Courty N, Lefevre S (2012) Classwise hyperspectral image classification with PerTurbo method,  in 2012 IEEE International Geoscience and Remote Sensing Symposium, Munich, Germany, 6883–6886. https://doi.org/10.1109/IGARSS.2012.6352581.

  4. Chen Y, Jiang H, Li C, Jia X, Ghamisi P (2016) Deep feature extraction and classification of hyperspectral images based on convolutional neural networks. IEEE Trans Geosci Remote Sens 54(10):6232–6251. https://doi.org/10.1109/TGRS.2016.2584107

    Article  Google Scholar 

  5. Chopra S, Hadsell R,  LeCun R (2005) Learning a similarity metric discriminatively, with application to face verification in 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), San Diego, CA, USA, 1:539–546. https://doi.org/10.1109/CVPR.2005.202

  6. Ciresan D, Meier U, Schmidhuber J (2012) Multi-column deep neural networks for image classification  in 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, 3642–3649. https://doi.org/10.1109/CVPR.2012.6248110

  7. Dalla Mura M, Villa A, Benediktsson JA, Chanussot J, Bruzzone L (2011) Classification of hyperspectral images by using extended morphological attribute profiles and independent component analysis. IEEE Geosci Remote Sens Lett 8(3):542–546. https://doi.org/10.1109/LGRS.2010.2091253

  8. Deng F, Pu S, Chen X, Shi Y, Yuan T, Pu S (2018) Hyperspectral image classification with capsule network using limited training samples. Sensors 18(9):3153. https://doi.org/10.3390/s18093153

    Article  Google Scholar 

  9. Dopido I, Li J, Marpu PR, Plaza A, Bioucas Dias JM, Benediktsson JA (2013) Semisupervised self-learning for hyperspectral image classification. IEEE Trans Geosci Remote Sens 51(7):4032–4044. https://doi.org/10.1109/TGRS.2012.2228275

  10. Eeti LN, Buddhiraju KM (2021) Two hidden layer neural network-based rotation forest ensemble for hyperspectral image classification. Geocarto Int 36(16):1820–1837. https://doi.org/10.1080/10106049.2019.1678680

    Article  Google Scholar 

  11. Fauvel M, Chanussot J, Benediktsson JA, Sveinsson JR (2007) Spectral and spatial classification of hyperspectral data using SVMs and morphological profiles, in 2007 IEEE International Geoscience and Remote Sensing Symposium, Barcelona, Spain, pp. 4834–4837https://doi.org/10.1109/IGARSS.2007.4423943

  12. Fukushima K (1988) Neocognitron: A hierarchical neural network capable of visual pattern recognition. Neural Netw 1(2):119–130. https://doi.org/10.1016/0893-6080(88)90014-7

    Article  MathSciNet  Google Scholar 

  13. Gao H, Zhang J, Cao X, Chen Z, Zhang Y, Li C (2021) Dynamic data augmentation method for hyperspectral image classification based on siamese structure. IEEE J Sel Top Appl Earth Obs Remote Sens 14:8063–8076. https://doi.org/10.1109/JSTARS.2021.3102610

  14. Graña M, Veganzons M, Ayerdi B (2021) Computational Intelligence Group (GIC). Hyperspectral Remote Sensing Scenes. http://www.ehu.eus/ccwintco/index.php/Hyperspectral_Remote_Sensing_Scenes#Indian_Pines (Accessed Nov. 30, 2021)

  15. Guo B, Gunn SR, Damper RI, Nelson JDB (2008) Customizing Kernel Functions for SVM-Based Hyperspectral Image Classification. IEEE Trans Image Process 17(4):622–629. https://doi.org/10.1109/TIP.2008.918955

    Article  MathSciNet  Google Scholar 

  16. He Z, He D (2020) Spatial-adaptive siamese residual network for multi-/hyperspectral classification. Remote Sens 12(10):1640. https://doi.org/10.3390/rs12101640

    Article  Google Scholar 

  17. He K, Zhang X, Ren S, Sun J (2015) Deep residual learning for image recognition. ArXiv151203385 Cs. Accessed: Oct. 27, 2021. [Online]. Available: http://arxiv.org/abs/1512.03385

  18. He X, Chen Y, Ghamisi P (2022) Dual graph convolutional network for hyperspectral image classification with limited training samples. IEEE Trans Geosci Remote Sens 60:1–18. https://doi.org/10.1109/TGRS.2021.3061088

    Article  Google Scholar 

  19. Hu W, Huang Y, Wei L, Zhang F, Li H (2015) Deep convolutional neural networks for hyperspectral image classification. J Sens 2015:1–12. https://doi.org/10.1155/2015/258619

    Article  Google Scholar 

  20. Huang L, Chen Y (2021) Dual-Path Siamese CNN for hyperspectral image classification with limited training samples. IEEE Geosci Remote Sens Lett 18(3):518–522. https://doi.org/10.1109/LGRS.2020.2979604

    Article  MathSciNet  Google Scholar 

  21. Huang H, Chen M, Duan Y (2019) Dimensionality reduction of hyperspectral image using spatial-spectral regularized sparse hypergraph embedding. Remote Sens 11(9):1039. https://doi.org/10.3390/rs11091039

    Article  Google Scholar 

  22. Hyperspectral Remote Sensing Scenes - Grupo de Inteligencia Computacional (GIC). http://www.ehu.eus/ccwintco/index.php/Hyperspectral_Remote_Sensing_Scenes (accessed Jan. 31, 2022).

  23. Javaid N, Jan N, Javed MU (2021) An adaptive synthesis to handle imbalanced big data with deep siamese network for electricity theft detection in smart grids. J Parallel Distrib Comput 153:44–52. https://doi.org/10.1016/j.jpdc.2021.03.002

    Article  Google Scholar 

  24. Jia S et al. (2021) A semisupervised siamese network for hyperspectral image classification. IEEE Trans Geosci Remote Sens. 1–17. https://doi.org/10.1109/TGRS.2021.3116138

  25. Khan MJ, Khan HS, Yousaf A, Khurshid K, Abbas A (2018) Modern trends in hyperspectral image analysis: A review. IEEE Access 6:14118–14129. https://doi.org/10.1109/ACCESS.2018.2812999

    Article  Google Scholar 

  26. Koch G, Zemel R, Salakhutdinov R (2015) Siamese neural networks for one-shot Image Recognition 8

  27. Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks in advances in neural information processing systems 25. [Online]. Available: https://proceedings.neurips.cc/paper/2012/file/c399862d3b9d6b76c8436e924a68c45b-Paper.pdf

  28. Kuo B-C, Li C-H, Yang J-M (2009) Kernel nonparametric weighted feature extraction for hyperspectral image classification. IEEE Trans Geosci Remote Sens 47(4):1139–1155. https://doi.org/10.1109/TGRS.2008.2008308

    Article  Google Scholar 

  29. Li Y, Zhang H, Xue X, Jiang Y, Shen Q (2018) Deep learning for remote sensing image classification: A survey. WIREs Data Min Knowl Discov 8(6). https://doi.org/10.1002/widm.1264

  30. Li W, Wu G, Zhang F, Du Q (2017) Hyperspectral image classification using deep pixel-pair features. IEEE Trans Geosci Remote Sens 55(2):844–853. https://doi.org/10.1109/TGRS.2016.2616355

    Article  Google Scholar 

  31. Li Y, Xie W, Li H (2017) Hyperspectral image reconstruction by deep convolutional neural network for classification. Pattern Recognit 63:371–383. https://doi.org/10.1016/j.patcog.2016.10.019

    Article  Google Scholar 

  32. Liang H, Bao W, Shen X (2021) Adaptive weighting feature fusion approach based on generative adversarial network for hyperspectral image classification. Remote Sens 13(2):198. https://doi.org/10.3390/rs13020198

    Article  Google Scholar 

  33. Liao X, Yin J, Chen M, Qin Z (2021) Adaptive payload distribution in multiple images steganography based on image texture features. IEEE Trans. Dependable Secure Comput. 1–1. https://doi.org/10.1109/TDSC.2020.3004708

  34. Liao X, Yu Y, Li B, Li Z, Qin Z (2020) A new payload partition strategy in color image steganography. IEEE Trans Circuits Syst Video Technol 30(3):685–696. https://doi.org/10.1109/TCSVT.2019.2896270

    Article  Google Scholar 

  35. Liao X, Li K, Zhu X, Liu KJR (2020) Robust detection of image operator chain with two-stream convolutional neural network. IEEE J Sel Top Signal Process 14(5):955–968. https://doi.org/10.1109/JSTSP.2020.3002391

    Article  Google Scholar 

  36. Licciardi G, Marpu PR, Chanussot J, Benediktsson JA (2012) Linear versus nonlinear PCA for the classification of hyperspectral data based on the extended morphological profiles. IEEE Geosci Remote Sens Lett 9(3):447–451. https://doi.org/10.1109/LGRS.2011.2172185

    Article  Google Scholar 

  37. Lin J, Mou L, Zhu XX, Ji X, Wang ZJ (2021) Attention-Aware Pseudo-3-D convolutional neural network for hyperspectral image classification. IEEE Trans Geosci Remote Sens 59(9):7790–7802. https://doi.org/10.1109/TGRS.2020.3038212

    Article  Google Scholar 

  38. Liu B, Yu X, Zhang P, Tan X, Yu A, Xue Z (2017) A semi-supervised convolutional neural network for hyperspectral image classification. Remote Sens Lett 8(9):839–848. https://doi.org/10.1080/2150704X.2017.1331053

    Article  Google Scholar 

  39. Liu J, Yang Z, Liu Y, Mu C (2021) Hyperspectral remote sensing images deep feature extraction based on mixed feature and convolutional neural networks. Remote Sens 13(13):2599. https://doi.org/10.3390/rs13132599

    Article  Google Scholar 

  40. Liu B, Yu X, Zhang P, Yu A, Fu Q, Wei X (2018) Supervised deep feature extraction for hyperspectral image classification. IEEE Trans Geosci Remote Sens 56(4):1909–1921. https://doi.org/10.1109/TGRS.2017.2769673

    Article  Google Scholar 

  41. Makantasis K, Karantzalos K, Doulamis A, Doulamis N (2015) Deep supervised learning for hyperspectral data classification through convolutional neural networks in 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Milan, pp. 4959–4962. https://doi.org/10.1109/IGARSS.2015.7326945

  42. Meng S, Wang X, Hu X, Luo C, Zhong Y (2021) Deep learning-based crop mapping in the cloudy season using one-shot hyperspectral satellite imagery. Comput Electron Agric 186:106188 https://doi.org/10.1016/j.compag.2021.106188

  43. Miao J, Wang B, Wu X, Zhang L, Hu B, Zhang JQ (2019) Deep feature extraction based on siamese network and auto-encoder for hyperspectral image classification in IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium, Yokohama, Japan, 397–400. https://doi.org/10.1109/IGARSS.2019.8899230

  44. Paoletti ME, Haut JM, Plaza J, Plaza A (2018) A new deep convolutional neural network for fast hyperspectral image classification. ISPRS J Photogramm Remote Sens 145:120–147. https://doi.org/10.1016/j.isprsjprs.2017.11.021

    Article  Google Scholar 

  45. Pathak DK, Kalita SK, Bhattacharya DK (2021) Hyperspectral image classification using support vector machine: a spectral spatial feature based approach. Evol Intell. https://doi.org/10.1007/s12065-021-00591-0

    Article  Google Scholar 

  46. Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale Image Recognition. ArXiv14091556 Cs. Accessed: Nov. 26, 2021. [Online]. Available: http://arxiv.org/abs/1409.1556

  47. Song H, Yang W, Yuan H, Bufford H (2020) Deep 3D-Multiscale densenet for hyperspectral image classification based on spatial-spectral information. Intell Autom Soft Comput 26(4):1441–1458. https://doi.org/10.32604/iasc.2020.011988

    Article  Google Scholar 

  48. Szegedy C et al. (2014) Going deeper with convolutions. ArXiv14094842 Cs. Accessed: Nov. 26, 2021. [Online]. Available: http://arxiv.org/abs/1409.4842

  49. Te-Ming Tu, Chen C-H, Jiunn-Lin Wu, Chang C-I (1998) A fast two-stage classification method for high-dimensional remote sensing data. IEEE Trans Geosci Remote Sens 36(1):182–191. https://doi.org/10.1109/36.655328

    Article  Google Scholar 

  50. Tong X, Yin J, Han B, Qv H (2020) Few-shot learning with attention-weighted graph convolutional networks for hyperspectral image classification, in 2020 IEEE International Conference on Image Processing (ICIP), Abu Dhabi, United Arab Emirates. 1686–1690. https://doi.org/10.1109/ICIP40778.2020.9190752.

  51. Villa A, Benediktsson JA, Chanussot J, Jutten C (2011) Hyperspectral image classification with independent component discriminant analysis. IEEE Trans Geosci Remote Sens 49(12):4865–4876. https://doi.org/10.1109/TGRS.2011.2153861

    Article  Google Scholar 

  52. Wang G, Ren P (2020) Hyperspectral Image Classification with Feature-Oriented Adversarial Active Learning. Remote Sens 12(23):3879. https://doi.org/10.3390/rs12233879

    Article  Google Scholar 

  53. Wang X, Ma L, Liu F (2013) Laplacian support vector machine for hyperspectral image classification by using manifold learning algorithms in 2013 IEEE International Geoscience and Remote Sensing Symposium - IGARSS, Melbourne, Australia, 1027–1030. https://doi.org/10.1109/IGARSS.2013.6721338

  54. Wang W, Chen Y, He X, Li Z (2022) Soft augmentation-based siamese CNN for hyperspectral image classification with limited training samples. IEEE Geosci Remote Sens Lett 19:1–5. https://doi.org/10.1109/LGRS.2021.3103180

    Article  Google Scholar 

  55. Xi J et al (2021) Dynamic wide and deep neural network for hyperspectral image classification. Remote Sens 13(13):2575. https://doi.org/10.3390/rs13132575

    Article  Google Scholar 

  56. Yang X, Ye Y, Li X, Lau RYK, Zhang X, Huang X (2018) Hyperspectral image classification with deep learning models. IEEE Trans Geosci Remote Sens 56(9):5408–5423. https://doi.org/10.1109/TGRS.2018.2815613

    Article  Google Scholar 

  57. Zhong Z, Li J, Luo Z, Chapman M (2018) Spectral–spatial residual network for hyperspectral image classification: A 3-D deep learning framework. IEEE Trans Geosci Remote Sens 56(2):847–858. https://doi.org/10.1109/TGRS.2017.2755542

    Article  Google Scholar 

  58. Zhu Q et al. (2021) A spectral-spatial-dependent global learning framework for insufficient and imbalanced hyperspectral image classification. IEEE Trans Cybern 1–15. https://doi.org/10.1109/TCYB.2021.3070577.

Download references

Author information

Authors and Affiliations

  1. Delhi Technological University, New Delhi, India

    Pallavi Ranjan & Ashish Girdhar

Authors
  1. Pallavi Ranjan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ashish Girdhar
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Pallavi Ranjan.

Ethics declarations

Conflict of interest

The authors have no conflicts of interest to declare that are relevant to the content of this article.

Additional information

Publisher's note

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

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ranjan, P., Girdhar, A. Deep Siamese Network with Handcrafted Feature Extraction for Hyperspectral Image Classification. Multimed Tools Appl 83, 2501–2526 (2024). https://doi.org/10.1007/s11042-023-15444-4

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-023-15444-4

Keywords

Search

Navigation