Skip to main content
SpringerLink
Log in

Wavelet enabled convolutional autoencoder based deep neural network for hyperspectral image denoising

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

Abstract

Denoising of hyperspectral images (HSIs) is an important preprocessing step to enhance the performance of its analysis and interpretation. In reality, a remotely sensed HSI experiences disturbance from different sources and therefore gets affected by multiple noise types. However, most of the existing denoising methods concentrates in removal of a single noise type ignoring their mixed effect. Therefore, a method developed for a particular noise type doesn’t perform satisfactorily for other noise types. To address this limitation, a denoising method is proposed here, that effectively removes multiple frequently encountered noise patterns from HSI including their combinations. The proposed dual branch deep neural network based architecture works on wavelet transformed bands. The first branch of the network uses deep convolutional skip connected layers with residual learning for extracting local and global noise features. The second branch includes layered autoencoder together with subpixel upsampling that performs repeated convolution in each layer to extract prominent noise features from the image. Two hyperspectral datasets are used in the experiment to evaluate the performance of the proposed method for denoising of Gaussian, stripe and mixed noises. Experimental results demonstrate the superior performance of the proposed network compared to other state-of-the-art denoising methods with PSNR 36.74, SSIM 0.97 and overall accuracy 94.03 %.

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
Fig. 13
Fig. 14

Similar content being viewed by others

References

  1. Alsaiari A, Rustagi R, Alhakamy A (2019) Image denoising using a generative adversarial network. IEEE 2nd International Conference on Information and Computer Technologies. https://doi.org/10.1109/INFOCT.2019.8710893

  2. Chen Y, Pock T (2016) Trainable nonlinear reaction diffusion: a flexible framework for fast and effective image restoration. IEEE Trans Pattern Anal Mach Intell. https://doi.org/10.1109/TPAMI.2016.2596743

    Article  Google Scholar 

  3. Chen C, Xu Z (2018) Aerial-image denoising based on convolutional neural network with multi-scale residual learning approach. Information (Switzerland). https://doi.org/10.3390/info9070169

    Article  Google Scholar 

  4. Cortes C, Vapni V (1995) Support-vector networks. Mach Learn. https://doi.org/10.1007/BF00994018

    Article  Google Scholar 

  5. Dabov K, Foi A, Katkovnik V, Egiazarian K (2007) Image denoising by sparse 3-D transform-domain collaborative filtering. IEEE Trans Image Process. https://doi.org/10.1109/TIP.2007.901238

    Article  MathSciNet  Google Scholar 

  6. Fan L, Zhang F, Fan H, Zhang C (2019) Brief review of image denoising techniques. Visual Computing for Industry, Biomedicine, and Art. https://doi.org/10.1186/s42492-019-0016-7

  7. Garg V (2007) An overview of digital communication and transmission. In: Wireless communication and networking: The Morgan Kauffman series in Networking, Morgan Kauffman, ScienceDirect. pp 85-122

  8. Gonzalez RC, Woods R (2007) Digital image processing. Pearson Prentice Hall, Upper Saddle River

    Google Scholar 

  9. Gu S, Zhang L, Zuo W, Feng X (2014) Weighted nuclear norm minimization with application to image denoising. IEEE Conference on Computer Vision and Recognition P. https://doi.org/10.1109/CVPR.2014.366

  10. Guan J, Lai R, Xiong A (2019) Wavelet deep neural network for stripe noise removal. IEEE Access. https://doi.org/10.1109/ACCESS.2019.2908720

    Article  Google Scholar 

  11. Harmeling S, Burger H, Schuler C (2012) Image denoising: Can plain neural networks compete with BM3D. IEEE Conference on Computer Vision and Recognition P. https://doi.org/10.1109/CVPR.2012.6247952

  12. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. IEEE Conference on Computer Vision and Recognition P (CVPR). https://doi.org/10.1109/CVPR.2016.90

  13. Huang G, Liu Z, Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. CVPR 2017. https://doi.org/10.1109/CVPR.2017.243

  14. Jain AK (1989) Fundamentals of digital image processing. Prentice-hall, Upper Saddle River

    MATH  Google Scholar 

  15. Kheradmand A, Milanfar P (2014) A general framework for regularized, similarity-based image restoration. IEEE Trans Image Process. https://doi.org/10.1109/TIP.2014.2362059

    Article  MathSciNet  MATH  Google Scholar 

  16. Kuang X, Sui X, Chen Q, Gu G (2017) Single infrared image stripe noise removal using deep convolutional networks. IEEE Photonics J. https://doi.org/10.1109/JPHOT.2017.2717948

    Article  Google Scholar 

  17. Liu X, Mei S, Zhang Z, Zhang Y, Ji J (2019) Decs-Net: Convolutional self-encoding network for hyperspectral image denoising. IEEE Int Geosci Remote Sens Symp. https://doi.org/10.1109/IGARSS.2019.8900642

  18. Lu X, Ma C, Shen J, Yang X, Reid I, Yang H (2020) Deep object tracking with shrinkage loss. IEEE Trans Pattern Anal Mach Intell. https://doi.org/10.1109/TPAMI.2020.3041332

    Article  Google Scholar 

  19. Lu X, Wang W, Shen J, Crandall D (2020) Zero-shot video object segmentation with co-attention siamese networks. IEEE Trans Pattern Anal Mach Intell. https://doi.org/10.1109/TPAMI.2020.3040258

  20. Lu X, Chao Ma C, Ni B, Yang X (2021) Adaptive region proposal with channel regularization for robust object tracking. IEEE Trans Circuits Syst Video Technol. https://doi.org/10.1109/TCSVT.2019.2944654

  21. Maffei A, Haut JM, Paoletti ME, Plaza J, Bruzzone L, Plaza A (2020) A single model CNN for hyperspectral image denoising. IEEE Trans Geosci Remote Sens. https://doi.org/10.1109/TGRS.2019.2952062

    Article  Google Scholar 

  22. Paul A, Chaki N (2019) Dimensionality reduction of hyperspectral images using pooling. Pattern Recognit Image Anal 29(1):72–78

    Article  Google Scholar 

  23. Paul A, Chaki N (2020) Supervised data-driven approach for hyperspectral band selection using quantization. Geocarto Int. https://doi.org/10.1080/10106049.2020.1822929

    Article  Google Scholar 

  24. Paul A, Chaki N (2020) Dimensionality reduction of hyperspectral image using signal entropy and spatial information in genetic algorithm with discrete wavelet transformation. Evol Intel. https://doi.org/10.1007/s12065-020-00460-2

    Article  Google Scholar 

  25. Paul A, Sahoo P, Chaki N (2020) Dimensionality reduction of hyperspectral images: a data-driven approach for band selection. In: Advanced computing and systems for security. Springer, pp 11–27

  26. Paul A, Chaki N (2021) Dimensionality reduction using band correlation and variance measure from discrete wavelet transformed hyperspectral imagery. Ann Data Sci 8(2):261–274

    Article  Google Scholar 

  27. Paul A, Bhoumik S, Chaki N (2021) SSNET: an improved deep hybrid network for hyperspectral image classification. Neural Comput Appl. https://doi.org/10.1007/s00521-020-05069-1

    Article  Google Scholar 

  28. Paul A, Bhoumik S (2021) Classification of hyperspectral imagery using spectrally partitioned HyperUnet. Neural Comput & Applic. https://doi.org/10.1007/s00521-021-06532-3

  29. Paul A, Bhattacharya S, Dutta D, Sharma JR, Dadhwal VK (2015) Band selection in hyperspectral imagery using spatial cluster mean and genetic algorithms. GISci Remote Sens 52(6):643–659

  30. Quesada P, Heras DB, Aguello F (2016) Exploring the impact of wavelet-based denoising in the classification of remote sensing hyperspectral images. Image and Signal Processing for Remote Sensing XXII. https://doi.org/10.1117/12.2240854

  31. Rasti B, Scheunders P, Ghamisi P, Licciardi G, Chanussot J (2018) Noise reduction in hyperspectral imagery: Overview and application. Remote Sens. https://doi.org/10.3390/rs10030482

  32. Reddy ASB, D Juliet (2019) Transfer learning with ResNet-50 for malaria cell-image classification. International Conference on Communication and Signal Processing (ICCSP). https://doi.org/10.1109/ICCSP.2019.8697909

  33. Ronnebergar O, Fischer P, Brox T (2015) U-Net: convolutional networks for biomedical image segmentation. Springer, Cham. https://doi.org/10.1007/978-3-319-24574-4_28

  34. Sagar GV, Barker SY, Raja KB, Babu KS, Venugopal KR (2015) Convolution based Face Recognition using DWT and feature vector compression. 2015 Third International Conference on Image Information Processing. https://doi.org/10.1109/ICIIP.2015.7414814

  35. Shan W, Liu P, Mu L, Cao C, He G (2019) Hyperspectral image denoising with dual deep CNN. IEEE Access. https://doi.org/10.1109/ACCESS.2019.2955810

    Article  Google Scholar 

  36. Sharma A, Singh J (2013) Image denoising using spatial domain filters: A quantitative study. 2013 6th International Congress on Image and Signal Processing (CISP). https://doi.org/10.1109/CISP.2013.6744005

  37. Song Y, Zhu Y, Du X (2019) Dyanamic residual dense learning for image denoising. Sensors. https://doi.org/10.3390/s19173809

  38. Su H, Du Q, Chen G, Du P (2014) Optimized hyperspectral band selection using particle swarm optimization. IEEE J Sel Topics Appl Earth Observ Remote Sens. https://doi.org/10.1109/JSTARS.2014.2312539

    Article  Google Scholar 

  39. Tomasi C, Manduchi R (1998) Bilateral filtering for gray and color images. Abstracts of the sixth international conference on computer vision IEEE. https://doi.org/10.1109/ICCV.1998.710815

  40. Tsai F, Chen WW (2008) Striping noise detection and correction of remote sensing images. IEEE Trans Geosci Remote Sens. https://doi.org/10.1109/TGRS.2008.2000646

  41. Vidal M, Amigo JM (2012) Pre-processing of hyperspectral images. Essential steps before image analysis. Chemometr Intell Lab Syst. https://doi.org/10.1016/j.chemolab.2012.05.009

    Article  Google Scholar 

  42. Wang Z, Bovik A, Sheikh H, Simoncelli E (2004) Image quality assessment: From error visibility to structural similarity. IEEE Trans Image Process. https://doi.org/10.1109/TIP.2003.819861

  43. Xiao F, Zhang Y (2011) A comparative study on thresholding methods in wavelet-based image denoising. Procedia Eng 15. https://doi.org/10.1016/j.proeng.2011.08.749

  44. Xiao P, Guo Y, Zhuang P (2018) Removing stripe noise from infrared cloud images via deep convolutional networks. IEEE Photonics J. https://doi.org/10.1109/JPHOT.2018.2854303

    Article  Google Scholar 

  45. Xie J, Xu L, Chen E (2012) Image denoising and inpainting with deep neural networks. Adv Neural Inf Process Syst

  46. Xie W, Li Y (2017) Hyperspectral imagery denoising by deep learning with trainable nonlinearity function. IEEE Geosci Remote Sens Lett. https://doi.org/10.1109/LGRS.2017.2743738

    Article  Google Scholar 

  47. Xie W, Li Y, Jia X (2018) Deep convolutional networks with residual learning for accurate spectral-spatial denoising. Neurocomputing. https://doi.org/10.1016/j.neucom.2018.05.115

    Article  Google Scholar 

  48. Xu J, Huang Y, Liu L, Zhu F, Hou X, Shao L (2019) noisy-as-clean: learning unsupervised denoising from the corrupted image. arXiv:1906.06878v3 [cs.CV]

  49. Yang H et. al (2012) Application and evaluation of wavelet-based denoising method in hyperspectral imagery data. International Conference on Computer and Computing Technologies in Agriculture. https://doi.org/10.1007/978-3-642-27278-3_47

  50. Yuan Q, Zhang Q, Li J, Shen H, Zhang L (2018) Hyperspectral image denoising employing a spatial-spectral deep residual convolutional neural network. IEEE Trans Geosci Remote Sens. https://doi.org/10.1109/TGRS.2018.2865197

    Article  Google Scholar 

  51. Zhang L, Dong W, Zhang D, Shi G (2010) Two-stage image denoising by principal component analysis with local pixel grouping. Pattern Recogn. https://doi.org/10.1016/j.patcog.2009.09.023

    Article  MATH  Google Scholar 

  52. Zhang K, Zuo W, Chen Y, Meng D, Zhang L (2017) Beyond a gaussian denoiser: residual learning of deep CNN for image denoising. IEEE Trans Image Process. https://doi.org/10.1109/TIP.2017.2662206

    Article  MathSciNet  MATH  Google Scholar 

  53. Zhang Q, Yuan Q, Li J, Liu X, Shen H, Zhang L (2019) Hybrid noise removal in hyperspectral imagery with a spatial-spectral gradient network. IEEE Trans Geosci Remote Sens. https://doi.org/10.1109/TGRS.2019.2912909

    Article  Google Scholar 

  54. Zhang Q, Yuan Q, Li J, Sun F, Zhang L (2020) Deep spatio-spectral Bayesian posterior for hyperspectral image non-i.i.d. noise removal. ISPRS J Photogramm Remote Sens. https://doi.org/10.1016/j.isprsjprs.2020.04.010

    Article  Google Scholar 

  55. Zoran D, Weiss Y (2011) From learning models of natural image patches to whole image restoration. IEEE International Conference on Computer Vision. https://doi.org/10.1109/ICCV.2011.6126278

Download references

Author information

Authors and Affiliations

  1. Regional Remote Sensing Centre – East, NRSC, ISRO, Kolkata, India

    Arati Paul & Dibyendu Dutta

  2. Department of Computer Science and Engineering, University of Calcutta, Kolkata, India

    Ahana Kundu & Nabendu Chaki

  3. Regional Centres, NRSC, ISRO, Hyderabad, India

    C. S. Jha

Authors
  1. Arati Paul
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ahana Kundu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Nabendu Chaki
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Dibyendu Dutta
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. C. S. Jha
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Arati Paul.

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

Paul, A., Kundu, A., Chaki, N. et al. Wavelet enabled convolutional autoencoder based deep neural network for hyperspectral image denoising. Multimed Tools Appl 81, 2529–2555 (2022). https://doi.org/10.1007/s11042-021-11689-z

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-021-11689-z

Keywords

Search

Navigation