Skip to main content
SpringerLink
Log in

An Edge-Preserving Image Denoising Framework by Adaptive Thresholding-Based DWT and Modified Deep Structured Architecture

  • Published:
Neural Processing Letters Aims and scope Submit manuscript

Abstract

Edge preserving denoising is a realistic procedure in most image-editing methodologies such as privacy protection, action movie creation, and visual aesthetic enhancement. But, the existing image-edge smoothening methods are developed without being semantically aware and content-aware. Earlier developed denoising methods are efficient in reducing Gaussian noise, yet suffer from maintaining the denoised image quality, and also image edges have been blurred. The main intent of this work is to introduce a new denoising approach of a modified Deep Convolutional Neural Network (DCNN) to protect image edges. Initially, the noisy image is decomposed and denoised by the Adaptive thresholding functions-based Discrete Wavelet Transform, in which the thresholding functions of the wavelet are optimized by a hybridized optimization algorithm named Dragonfly-Harris Hawks Optimization (D-HHO). It is used for enhancing the image denoising with the MDCNN. Where the constraints of Deep CNN are tuned by the same D-HHO to minimize the multi-objective function in terms of joint loss representing both MSE loss and perpetual loss. Once the images are decomposed, denoising is performed which ensures the preservation of image edges. The experimental results confirm that the suggested network attains enriched performances.

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

Similar content being viewed by others

References

  1. Li P, Liang J, Zhang M, Fan W, Yu G (2022) Joint image denoising with gradient direction and edge-preserving regularization. Pattern Recogn 125:108506

    Google Scholar 

  2. Evangelista RC, Salvadeo DHP, Mascarenhas NDA (2022) A new bayesian Poisson denoising algorithm based on nonlocal means and stochastic distances. Pattern Recogn 122:108363

    Google Scholar 

  3. Sun T, Li D (2022) General nonconvex total variation and low-rank regularizations: model, algorithm and applications. Pattern Recogn 130:108692

    Google Scholar 

  4. Jain P, Tyagi V (2015) LAPB: Locally adaptive patch-based wavelet domain edge-preserving image denoising. Inf Sci 294:164–181

    MathSciNet  MATH  Google Scholar 

  5. Moreno R, Garcia MA, Puig D, Julià C (2011) Edge-preserving color image denoising through tensor voting. Comput Vis Image Underst 115(11):1536–1551

    Google Scholar 

  6. Chen S, Liu M, Zhang W, Liu J (2013) Edge preserving image denoising with a closed form solution. Pattern Recogn 46(3):976–988

    MATH  Google Scholar 

  7. Xu Z, Li X, Stojanovic V (2021) Exponential stability of nonlinear state-dependent delayed impulsive systems with applications. Nonlinear Anal Hybrid Syst 42:1

    MathSciNet  MATH  Google Scholar 

  8. Song X, Sun P, Song S, Stojanovic V (2022) Event-driven NN adaptive fixed-time control for nonlinear systems with guaranteed performance. J Franklin Inst 359(9):4138–4159

    MathSciNet  MATH  Google Scholar 

  9. Stojanovic V, Nedic N (2016) Robust identification of OE model with constrained output using optimal input design. J Frankl Inst 353(2):576–593

    MathSciNet  MATH  Google Scholar 

  10. Bhutada GG, Anand RS, Saxena SC (2011) Edge preserved image enhancement using adaptive fusion of images denoised by wavelet and curvelet transform. Digital Signal Processing 21(1):118–130

    Google Scholar 

  11. Lazzaro D, Montefusco LB (2007) Edge-preserving wavelet thresholding for image denoising. J Comput Appl Math 210(1):222–231

    MathSciNet  MATH  Google Scholar 

  12. Riya BG, Lamba SS (2021) An efficient anisotropic diffusion model for image denoising with edge preservation. Comput Math Appl 93:106–119

    MathSciNet  MATH  Google Scholar 

  13. Shi M, Zhang F, Wang S, Zhang C, Li X (2021) Detail preserving image denoising with patch-based structure similarity via sparse representation and SVD. Comput Vis Image Underst 206:103173

    Google Scholar 

  14. Fang Y, Zeng T (2020) Learning deep edge prior for image denoising. Comput Vis Image Underst 200(103044):1

    Google Scholar 

  15. Ma H, Nie Y (2016) An edge fusion scheme for image denoising based on anisotropic diffusion models. J Vis Commun Image Represent 40:406–417

    Google Scholar 

  16. Vallabhaneni RB, Rajesh V (2018) Brain tumour detection using mean shift clustering and GLCM features with edge adaptive total variation denoising technique. Alex Eng J 57(4):2387–2392

    Google Scholar 

  17. Jain P, Tyagi V (2017) An adaptive edge-preserving image denoising technique using patch-based weighted-SVD filtering in wavelet domain. Multimed Tools Appl 76:1659–1679

    Google Scholar 

  18. Jain P, Tyagi V (2015) An adaptive edge-preserving image denoising technique using tetrolet transforms. Vis Comput 31:657–674

    Google Scholar 

  19. da Silva RD, Minetto R, Schwartz WR, Pedrini H (2013) Adaptive edge-preserving image denoising using wavelet transforms. Pattern Anal Appl 16:567–580

    MathSciNet  MATH  Google Scholar 

  20. Tang L, Fang Z (2016) Edge and contrast preserving in total variation image denoising. EURASIP J Adv Signal Process 2016(13):2016

    Google Scholar 

  21. Shahdoosti HR, Rahemi Z (2019) Edge-preserving image denoising using a deep convolutional neural network. Signal Process 159:20–32

    Google Scholar 

  22. Xu D, Wang X, Sun G, Li H (2017) Towards a novel image denoising method with edge-preserving sparse representation based on laplacian of B-spline edge-detection. Multimed Tools Appl 76:17839–17854

    Google Scholar 

  23. Bhandari AK, Kumar D, Kumar A, Singh GK (2016) Optimal sub-band adaptive thresholding based edge preserved satellite image denoising using adaptive differential evolution algorithm. Neurocomputing 174:698–721

    Google Scholar 

  24. Routray S, Ray AK, Mishra C, Palai G (2018) Efficient hybrid image denoising scheme based on SVM classification. Optik 157:503–511

    Google Scholar 

  25. Wang X-Y, Yang H-Y, Fu Z-K (2013) Edge structure preserving image denoising using OAGSM/NC statistical model. Digital Signal Process 23(1):200–212

    MathSciNet  Google Scholar 

  26. Chen X, Zhan S, Ji D, Xu L, Wu C, Li X (2018) Image denoising via deep network based on edge enhancement. J Ambient Intell Humaniz Comput 1:1

    Google Scholar 

  27. Zhu H, Huang TC (2020) A novel deep quality-aware CNN for image edge smoothening. Futur Gener Comput Syst 113:468–473

    Google Scholar 

  28. Juneja M, Saini SK, Kaul S, Acharjee R, Thakur N, Jindal P (2021) Denoising of magnetic resonance imaging using Bayes shrinkage based fused wavelet transform and autoencoder based deep learning approach. Biomed Signal Process Control 69(102844):1

    Google Scholar 

  29. Li Z, Liu Y, Li K, Chen Y, Shu H, Kang J, Lu J, Gui Z (2022) Edge feature extraction-based dual CNN for LDCT denoising. J Opt Soc Am A 39(10):1929–1938

    Google Scholar 

  30. Shodiq MN, Yuniarno EM, Nugroho J, Purnama IKE (2022) Ultrasound image segmentation for deep vein thrombosis using Unet-CNN based on denoising filter. In: 2022 IEEE international conference on imaging systems and techniques (IST)

  31. Luo Y, Ma Y, O’Brien H, Jiang K, Kohli V, Maidelin S, Saeed M, Deng E, Pushparajah K, Rhode KS (2022) Edge-enhancement densenet for X-ray fluoroscopy image denoising in cardiac electrophysiology procedures. Int J Med Phys Res Pract 49(2):1262–1275

    Google Scholar 

  32. Wang C, Pan S, Yu CP, Hu R, Long G, Zhang C (2022) Deep neighbor-aware embedding for node clustering in attributed graphs. Pattern Recogn 122:108230

    Google Scholar 

  33. Shen H, Zhao Z-Q, Liao W, Tian W, Huang D-S (2022) Joint operation and attention block search for lightweight image restoration. Pattern Recogn 132:108909

    Google Scholar 

  34. Huang C, Li Z, Liu Y, Wu T, Zeng T (2022) Quaternion-based weighted nuclear norm minimization for color image restoration. Pattern Recogn 128:108665

    Google Scholar 

  35. Kanika DN, Sharama K (2012) Comparative analysis of discrete wavelet transform and fast wavelet transform on image compression. Int J Eng Res Technol 1(5):1–7

    Google Scholar 

  36. Ali MN (2019) A wavelet-based method for MRI liver image denoising. Biomed Tech (Berl) 64(6):699–709

    Google Scholar 

  37. Li Y, Li Z, Zheng C, Wu S (2022) Adaptive weighted guided image filtering for depth enhancement in shape-from-focus. Pattern Recogn 131:108900

    Google Scholar 

  38. Heidari AA, Mirjalili S, Faris H, Aljarah I, Mafarja M, Chen H (2019) Harris hawks optimization: Algorithm and applications. Futur Gen Comput Syst 97:849–872

    Google Scholar 

  39. Illuri B, Jose D (2021) Design and implementation of hybrid integration of cognitive learning and chaotic countermeasures for side channel attacks. J Ambient Intell Humaniz Comput 12:5427–5441

    Google Scholar 

  40. Jafari M, Chaleshtari MHB (2017) Using dragonfly algorithm for optimization of orthotropic infinite plates with a quasi-triangular cut-out. Eur J Mech A/Solids 66:1–14

    MathSciNet  MATH  Google Scholar 

  41. Yang J, Shen Y, Shi Y (2020) Visual fixation prediction with incomplete attention map based on brain storm optimization. Appl Soft Comput 96(106653):1

    Google Scholar 

  42. Dey S, De S, Deb A, Debnath S (2021) Multilevel image segmentation using modified red deer algorithm. In: International conference on cloud computing, data science & engineering (confluence), pp 362–368

  43. Lyu Z, Chen Y, Zhang YHC (2022) NSTBNet: toward a nonsubsampled shearlet transform for broad convolutional neural network image denoising. Digital Signal Processing 123:103407

    Google Scholar 

  44. He X, Wang C, Zheng R, Sun Z, Li X (2022) GPR image denoising with NSST-UNET and an improved BM3D. Digital Signal Process 123:103402

    Google Scholar 

  45. Ito T, Maeno T, Tsuchikame H, Shishido M, Nishi K, Kojima S, Hayashi T, Suzuki K (2022) Adapting a low-count acquisition of the bone scintigraphy using deep denoising super-resolution convolutional neural network. Physica Med 100:18–25

    Google Scholar 

  46. Liu P, Zhang H, Wang J, Wang Y, Ren D, Zuo W (2022) Robust deep ensemble method for real-world image denoising. Computer Vision and Pattern Recognition

Download references

Author information

Authors and Affiliations

  1. ECE, Jawaharlal Nehru Technological University Kakinada, Kakinada, Andhra Pradesh, India

    Srinivasa Rao Thamanam &  K. Satya Prasad

  2. EECE, GITAM (Deemed to be University), Hyderabad Campus, India

    Srinivasa Rao Thamanam &  K. Manjunathachari

Authors
  1. Srinivasa Rao Thamanam
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. K. Manjunathachari
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. K. Satya Prasad
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Srinivasa Rao Thamanam.

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

Srinivasa Rao Thamanam, K. Manjunathachari & K. Satya Prasad An Edge-Preserving Image Denoising Framework by Adaptive Thresholding-Based DWT and Modified Deep Structured Architecture. Neural Process Lett 55, 9353–9386 (2023). https://doi.org/10.1007/s11063-023-11205-4

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11063-023-11205-4

Keywords

Search

Navigation