• P-ISSN 0974-6846 E-ISSN 0974-5645

Indian Journal of Science and Technology

Article

Adaptive Sparsity through Hybrid Regularization for Effective Image Deblurring
  • VIEWS 1394
  • PDF 258

Indian Journal of Science and Technology

DOI: 10.17485/IJST/v14i24.604

Year: 2021, Volume: 14, Issue: 24, Pages: 2051-2068

Original Article

Adaptive Sparsity through Hybrid Regularization for Effective Image Deblurring

S Pooja1, S Mallikarjunaswamy2*, N Sharmila3

1Research Scholar, Department of ECE, Research Scholar, Department of ECE, Bangalore,
560060, Karnataka, India
2Associate Professor, Department of ECE, JSS Academy of Technical Education, Bangalore,
560060, Karnataka, India
3Assistant Professor, Department of EEE, RNS Institute of Technology, Bangalore, 560060,
Karnataka, India

*Corresponding Author
Email: [email protected]

Received Date:17 April 2021, Accepted Date:06 June 2021, Published Date:16 July 2021

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Abstract

Objectives: To develop image deblurring algorithm to effectively recover the original image from the captured blurry and noisy image. Methods: A novel image deblurring algorithm using adaptive priors is proposed. The adaptive priors vary the sparsity induced based on factors such as the type of blur affecting the image, image region, statistical parameters regarding the blur kernel and/or statistical predictions on the blur kernel. The proposed algorithm using adaptive priors improves the quality of the deblurred result, when compared with various recent image deblurring algorithms. Finding: the work contains a case study with regard to certain standard parameters. It is observed that proposed method is better in terms of frequency response, Peak signal-tonoise ratio (PSNR) and Structural Similarity Index (SSIM) values in comparison with other priors. Novelty: the proposed priors lead to the most effective results for image deblurring using the Bayesian framework. The proposed method improves the performance by 30% in PSNR and 45% in SSIM values in dB with uniform kernel size 12 * 12 and improves performance by 30 % in PSNR and 32% SSIM with a standard deviation of 3.5. The proposed method enhances the frequency response of the real-time image restoration process. Applications: Some important applications include the restoration of medical images such as MRI images, CT images where the intensity of these radiations is maintained to avoid damage to human organs. Remote sensing images captured through drones at a specified time cannot be retaken and hence restoring such images is very important. Similarly restoring images from CCTV footage, astronomical images.

Keywords: Blind Image Deblurring; Maximum a Posteriori Estimation; Image priors; Regularization; Structural Similarity Index (SSIM) and Peak signal-to-noise ratio (PSNR)

References

  1. Mohan K, Chandrasekhar P, Jilani SAK. Object Face Liveness Detection with Combined HOGlocal Phase Quantization using Fuzzy based SVM Classifier. Indian Journal of Science and Technology. 2017;10(3):1–10. Available from: https://dx.doi.org/10.17485/ijst/2017/v10i3/109035
  2. Kumaravel S, Sundar KJA, Vaithiyanathan V. Super Resolution Image Reconstruction for Bone Images. Indian Journal of Science and Technology. 2019;12(26):1–6.
  3. Saffari V, Ghazimoradi A, Alirezanejad M. Effect of Laplacian of Gaussian Filter on Watermark Retrieval in Spatial domain Watermarking. Indian Journal of Science and Technology. 2015;8(33):1–4. Available from: https://dx.doi.org/10.17485/ijst/2015/v8i1/71226
  4. Fairag F, Chen K, Brito-Loeza C, Ahmad S. A two-level method for image denoising and image deblurring models using mean curvature regularization. International Journal of Computer Mathematics. 2021;p. 1–21. Available from: https://dx.doi.org/10.1080/00207160.2021.1929939
  5. Yu X, Xie W. Single Image Blind Deblurring Based on Salient Edge-Structures and Elastic-Net Regularization. Journal of Mathematical Imaging and Vision. 2020;62(8):1049–1061. Available from: https://dx.doi.org/10.1007/s10851-020-00949-6
  6. Zhao C, Wang Y, Jiao H. Lp-Norm-Baesd Sparse Regularization Model for Liscence Plate Deblurring. IEEE Access. 2020;8:22072–22081.
  7. Anger J, Facciolo G, Delbracio M. Blind image deblurring using the lo gradient prior, Image Process. On Line. 2019;9:124–142. Available from: 10.5201/ipol.2019.243
  8. Xu Z, Chen H, Li Z. Blind image deblurring using group sparse representation. Digital Signal Processing. 2020;102(1-8):1–8. Available from: 10.1016/j.dsp.2020.102736
  9. Wen-Ze S, Yuan-Yuan L, YLY. DeblurGAN+: Revisiting blind motion deblurring using conditional adversarial networks. Signal Processing. 2020;168:1–10. Available from: 10.1016/j.sigpro.2019.107338
  10. Dong F, Ma Q. Single image blind deblurring based on the fractional-order differential. Computers & Mathematics with Applications. 1960;78(6):1960–1977. Available from: 10.1016/j.camwa.2019.03.033
  11. Blomgren P, Chan TF, Mulet P, Wong CK. Total variation image restoration: numerical methods and extensions. Proceedings of IEEE International Conference on Image Processing. 1997;(3) 384–387. Available from: 10.1109/ICIP.1997.632128
  12. Cai JF, Ji H, Liu C, Shen Z. Framelet-Based Blind Motion Deblurring From a Single Image. IEEE Transactions on Image Processing. 2012;21(2):562–572. Available from: https://dx.doi.org/10.1109/tip.2011.2164413
  13. Candes EJ, Wakin MB, Boyd SP. Enhancing sparsity by reweighted l1 minimization. J. Fourier Anal. Appl. 2008;14:877–905. Available from: 10.1007/s00041-008-9045-x
  14. Chambolle A, Lions PL. Image recovery via total variation minimization and related problems. Numerische Mathematik. 1997;76(2):167–188. Available from: https://dx.doi.org/10.1007/s002110050258
  16. Mohan SC. Adaptive Super-Resolution Image Reconstruction with Lorentzian Error Norm”. Indian Journal of Science and Technology. 2017;10(16):1–6. Available from: 10.17485/ijst/2017/v10i16/106780
  17. Rajkumar S, Malathi G. A Comparative Analysis on Image Quality Assessment for Real Time Satellite Images. Indian Journal of Science and Technology. 2016;9(34):1–11. Available from: https://dx.doi.org/10.17485/ijst/2016/v9i34/96766
  18. Mamta R, Dutta M, , . GA based Blind Deconvolution Technique of Image Restoration using Cepstrum Domain of Motion Blur. Indian Journal of Science and Technology. 2017;10(16):1–8. Available from: https://dx.doi.org/10.17485/ijst/2017/v10i16/114303
  19. Janani P, Premaladha J, Ravichandran KS. Image Enhancement Techniques: A Study. Indian Journal of Science and Technology. 2015;8(22):1–12. Available from: https://dx.doi.org/10.17485/ijst/2015/v8i22/79318
  20. Suresh G, Rao CS. RST Invariant Image Forgery Detection. Indian Journal of Science and Technology. 2016;9(22):1–8. Available from: https://dx.doi.org/10.17485/ijst/2016/v9i22/89227
  21. Uma K, Pallavi AR, Srilatha S. Comparision of Blur Detection and Segmentation Techniques. Indian Journal of Science and Technology. 2016;9(S1):1–7. Available from: https://dx.doi.org/10.17485/ijst/2016/v9is1/107619
  22. Singh R, Singh S. Navjot Kaur “A Review: Techniques of Vehicle Detection in Fog. Indian Journal of Science and Technology. 2016;9(47):1–4. Available from: 10.17485/ijst/2016/v9i45/106793
  23. Umashankar ML, Ramakrishna MV, Mallikarjunaswamy S. Design of High Speed Reconfigurable Deployment Intelligent Genetic Algorithm in Maximum Coverage Wireless Sensor Network. 2019 International Conference on Data Science and Communication (IconDSC). 2019;p. 1–6. Available from: https://doi.org/10.1109/IconDSC.2019.8816930
  24. Alam MZ, Qian Q, Gunturk BK. Space-variant blur kernel estimation and image deblurring through kernel clustering. Signal Processing: Image Communication. 2019;76:41–55. Available from: https://dx.doi.org/10.1016/j.image.2019.04.014
  25. Zhang H, Wu Y, Zhang L, Zhang Z, Li Y. Image deblurring using tri-segment intensity prior. Neurocomputing. 2020;398:265–279. Available from: https://dx.doi.org/10.1016/j.neucom.2020.02.082
  26. Mahendra HN, Mallikarjunaswamy S, Rekha V, Puspalatha V, Sharmila N. Performance Analysis of Different Classifier for Remote Sensing Application”. International Journal of Engineering and Advanced Technology. 2019;9(1):7153–7158. Available from: http://dx.doi.org/10.35940/ijeat.A1879.109119
  27. N MH, Mallikarjunaswamy S, GKS, MK, NS. Evolution of real-time onboard processing and classification of remotely sensed data. Indian Journal of Science and Technology. 2020;13(20):2010–2020. doi: 10.17485/ijst/v13i20.459
  28. Thazeen S, Mallikarjunaswamy S, Siddesh GK, Sharmila N. Conventional and Subspace Algorithms for Mobile Source Detection and Radiation Formation. Traitement du Signal. 2021;38(1):135–145. Available from: https://dx.doi.org/10.18280/ts.380114
  29. Chaitra S, Rekha V, Harisha AM, Madhu TA, Mallikarjunaswamy S. A comprehensive review of parallel concatenation of LDPC code techniques. Indian Journal of Science and Technology. 2021;14(5):432–444. Available from: https://doi.org/10.17485/IJST/v13i20.459
  30. Umashankar ML, Anitha TN, Mallikarjunaswamy S. An efficient hybrid model for cluster head selection to optimize wireless sensor network using simulated annealing algorithm. Indian Journal of Science and Technology. 2021;14(3):270–288. Available from: https://doi.org/10.17485/IJST/v14i3.2318
  31. Raj KS, Siddesh GK, Mallikarjunaswamy S, Raj KV. Interference resilient stochastic prediction based dynamic resource allocation model for cognitive MANETs”. Indian Journal of Science and Technology. 2020;13(41):4332–4350. Available from: https://doi.org/ 10.17485/IJST/v13i41.687
  32. Cui G, Ye X, Zhao J, Zhu L, Chen Y. Multi-frame motion deblurring using coded exposure imaging with complementary fluttering sequences. Optics & Laser Technology. 2020;126(106119). Available from: https://dx.doi.org/10.1016/j.optlastec.2020.106119
  33. Cheng S, Liu R, He Y, Fan X, Luo Z. Blind image deblurring via hybrid deep priors modeling. Neurocomputing. 2020;387:334–345. Available from: https://dx.doi.org/10.1016/j.neucom.2020.01.004
  34. fang F, MDQ. Single image blind deblurring based on the fractional-order differential. Computers & Mathematics with Applications. 2019;78(6):1960–1977. Available from: https://doi.org/10.1016/j.camwa.2019.03.033
  35. Shao WZ, Lin YZ, Liu YY, Wang LQ, Ge Q, Bao BK, et al. Gradient-based discriminative modeling for blind image deblurring. Neurocomputing. 2020;413:305–327. Available from: https://dx.doi.org/10.1016/j.neucom.2020.06.093
  36. Qi Q, Guo J, Jin W. EGAN: Non-uniform image deblurring based on edge adversarial mechanism and partial weight sharing network. Signal Processing: Image Communication. 2020;88(115952). Available from: https://dx.doi.org/10.1016/j.image.2020.115952
  37. Koh J, Lee J, Yoon S. Single-image deblurring with neural networks: A comparative survey. Computer Vision and Image Understanding. 2021;203:1–19. Available from: https://dx.doi.org/10.1016/j.cviu.2020.103134
  38. Zhang D, Liang Z, Shao J. Joint image deblurring and super-resolution with attention dual supervised network. Neurocomputing. 2020;412:187–196. Available from: https://dx.doi.org/10.1016/j.neucom.2020.05.069
  39. Zhang Y, Li W, Li Z, Ning T. Dual attention per-pixel filter network for spatially varying image deblurring. Digital Signal Processing. 2021;113:1–22. Available from: https://dx.doi.org/10.1016/j.dsp.2021.103008
  40. Chen X, Liu D, Zhang Y, Liu X, Xu Y, Shi C. Robust motion blur kernel parameter estimation for star image deblurring. Optik. 2021;230:1–23. Available from: https://dx.doi.org/10.1016/j.ijleo.2021.166288
  41. Zhang Y, Shi Y, Ma L, Wu J, Wang L, Hong H. Blind natural image deblurring with edge preservation based on L0-regularized gradient prior. Optik. 2021;225:165735. doi: 10.1016/j.ijleo.2020.165735
  42. Peng J, Shao Y, Sang N, Gao C. Joint image deblurring and matching with feature-based sparse representation prior. Pattern Recognition. 2020;103:1–23. Available from: https://dx.doi.org/10.1016/j.patcog.2020.107300
  43. Mallikarjunaswamy S, Sharmila N, Maheshkumar D, Komala M, Mahendra HN. Implementation of an effective hybrid model for islanded microgrid energy management. Indian Journal of Science and Technology. 2020;13(27):2733–2746. Available from: https://dx.doi.org/10.17485/ijst/v13i27.982
  44. Sree PH, Rao KS, , . A Novel Approach for Blurred Face Recognition System Using GLDA Features with LCDR Classification. Indian Journal of Science and Technology. 2019;12(29):1–8. Available from: https://dx.doi.org/10.17485/ijst/2019/v12i29/146975
  45. Liu J, Ma R, Zeng X, Liu W, Wang M, Chen H. An efficient non-convex total variation approach for image deblurring and denoising. Applied Mathematics and Computation. 2021;397:1–19. Available from: https://dx.doi.org/10.1016/j.amc.2021.125977
  46. Xu N. Adaptively Sparse Regularization for Blind Image Restoration. Electrical Engineering and Systems Science. 2021

Copyright

© 2021 Pooja et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Published By Indian Society for Education and Environment (iSee)

  • 16 July 2021

Year: 2021, Volume: 14, Issue: 24

Article Metrics


Post Graduate Fellowship in Research Communication

More articles

DON'T MISS OUT!

Subscribe now for latest articles and news.