Skip to main content
SpringerLink
Log in

Separable property-based super-resolution of lousy image data

  • Short paper
  • Published:
Pattern Analysis and Applications Aims and scope Submit manuscript

Abstract

This paper presents a novel wavelet-based approach for single-image super-resolution. Our technique integrates wavelet transform and the learned locally regularized anchored neighborhood regression model for more robust frequency estimation and image restoration. First, we decomposed the low-resolution input image into four frequency sub-bands by applying discrete wavelet transform and then processed these frequency sub-bands based on separable property of neighborhood filtering to achieve a fast parallel and vectorized operation by reducing computational burden resulting from computing the weighted function of every pixel for each pixel in an image. We then applied inverse discrete wavelet transform to reconstruct the original image. Super-resolution is achieved using the learned model to predict the high-resolution image features. Lastly, we explicitly unified both the locality structure and nonlocal self-similarity properties in natural image and incorporated them into our super-resolution framework to regularize the nonlinear correlation between low-resolution and high-resolution space and improve the reconstructed results. Experiments on standard images validate the effectiveness of our proposed method for effective denoising, deblurring and super-resolution reconstruction tasks compared to other top performing state-of-the-art methods both quantitatively and qualitatively.

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

References

  1. Xu G, Zhang A, Li J, Li S, Jing B (2014) A self-adaptive super-resolution method based on dictionary library. In: IEEE the 7th international congress on image and signal processing

  2. Tsai R, Huang TS (1984) Multiframe image restoration and registration. Adv Comput Vis Image Process 1(2):317–339

    Google Scholar 

  3. Zhang Y, Liu J, Yang W, Guo Z (2015) Image super-resolution based on structure-modulated sparse representation. IEEE Trans Image Process 24(9):2797–2810

    Article  MathSciNet  Google Scholar 

  4. Roshna NR, Naveen S (2017) Multimodal Low-resolution Face Recognition using SVD. In: IEEE circuit, power and computing technologies (ICCPCT)

  5. Li J, Chen Z, Liu C (2016) Low-resolution face recognition of multi-scale blocking CS-LBP and weighted PCA. World Sci Int J Pattern Recog Artif Intell 30(8):1656005

    Article  MathSciNet  Google Scholar 

  6. Obara K, Yoshimura H, Nishiyama M, Iwai Y (2017) Low-resolution person recognition using image downsampling. In: IEEE machine vision applications (MVA)

  7. El Meslouhi O, Benaddy M, El Habil B, El Ouali M, Krit SD, El Garrai Z, Nassiri K (2017) Low-resolution face recognition using unimodal data fusion. IEEE engineering & MIS (ICEMIS)

  8. Zeng D, Chen H, Zhao Q (2016) Towards resolution invariant face recognition in uncontrolled scenarios. In: IEEE biometrics (ICB)

  9. JSatiro J, Nasrollahi K, Correia PL, Moeslund TB (2015) Super- resolution of Facial Images in Forensics Scenarios. In: IEEE International conference on image processing theory, tools and applications (IPTA)

  10. Raghavendra R, Busch C (2015) Face image resolution enhancement based on weighted fusion of wavelet decomposition. In: IEEE 18th international conference on information fusion Washington, DC—July 6–9

  11. Aouada D, Al Ismaeil K, Idris KK, Ottersten B (2014) Surface UP- SR for an improved face recognition using low resolution depth cameras. In: IEEE international conference on advanced video and signal based surveillance (AVSS)

  12. Tanaka M, Okutomi M (2007) A fast algorithm for reconstruction-based super resolution and evaluation of its accuracy. Syst Comput Jpn 38(7):44–52

    Article  Google Scholar 

  13. Haghighat M, Abdel-Mottaleb M (2017) Low resolution face recognition in surveillance systems using discriminant correlation analysis. In: IEEE automatic face & gesture recognition (FG 2017)

  14. Zhu H, Li F, Ye J, Wang J (2016) Super-resolution reconstruction of face image with improved sparse constraint. In: IEEE 6th international conference on digital home

  15. Zhao D, Chen Z, Liu C, Peng Y (2017) Two-dimensional linear discriminant analysis for low-resolution face recognition. In: IEEE Chinese automation congress (CAC)

  16. Lu T, Yang W, Zhang Y, Li X, Xiong Z (2016) Very low-resolution face recognition via semi-coupled locality- constrained representation. In: IEEE parallel and distributed systems (ICPADS)

  17. Nejad YK, Masnadi-Shirazi M, Yazdi M, Shahvar MZ (2015) Quality enhancement of low-resolution face images. In: IEEE machine vision and image processing (MVIP)

  18. Li Z, Hou Y, Liu H, Li X (2014) Very low-resolution face reconstruction based on multi-output regression. In: IEEE workshop on electronics, computer and applications

  19. Bilgazyev E, Efraty B, Shah SK, Kakadiaris IA (2011) Improved face recognition using super-resolution. In: IEEE biometrics (IJCB)

  20. Li W, Zhang D, Liu Z, Qiao X (2005) Fast block-based image restoration employing the improved best neighborhood matching approach. IEEE Trans Syst Man Cybern Part A Syst Hum 35(4):546–555

    Article  Google Scholar 

  21. Yang J, Wright J, Huang T, Ma Y. Image super-resolution as sparse representation of raw image patches. In: 2008 IEEE conference on computer vision and pattern recognition 2008 Jun 23. IEEE, pp 1–8

  22. Yang F, Yang W, Gao R, Liao Q (2017) Discriminative multidimensional scaling for low-resolution face recognition. IEEE Sig Process Lett 25(3):388–392. https://doi.org/10.1109/LSP.2017.2746658

    Article  Google Scholar 

  23. Shekhar S, Patel VM, Chellappa R (2017) Synthesis-based robust low-resolution face recognition. IEEE Trans Inf Forensics Secur

  24. Wei X, Li Y, Shen H, Xiang W, Murphey YL (2017) Joint learning sparsifying linear transformation for low-resolution image synthesis and recognition. Pattern Recogn 66:412–424

    Article  Google Scholar 

  25. Moutafis P, Kakadiaris IA (2014) Semi-coupled basis and distance metric learning for cross-domain matching: application to low-resolution face recognition. In: IEEE international joint conference on biometrics

  26. Zou WW, Yuen PC (2012) Very low-resolution face recognition problem. In: IEEE transaction on image processing

  27. Yang MC, Wei CP, Yeh YR, Wang YC (2015) Recognition at a long distance: very low-resolution face recognition and hallucination. In: IEEE biometrics (ICB)

  28. Mudunuri SP, Biswas S (2017) Dictionary alignment for low- resolution and heterogeneous face recognition. In: IEEE winter conference on applications of computer vision

  29. Ameur B, Belahcene M, Masmoudi S, Derbel AG, Hamida AB (2017) A new GLBSIF descriptor for face recognition in the uncontrolled environments. In: IEEE advanced technologies for signal and image processing (ATSIP)

  30. Jiang J, Chen C, Ma J, Wang Z, Wang Z, Hu R (2016) SRLSP: a face image super-resolution algorithm using smooth regression with local structure prior. IEEE Trans Multimedia 19(1):27–40

    Article  Google Scholar 

  31. Gao G, Hu Z, Huang P, Yang M, Zhou Q, Wu S, Yue D (2018) Robust low-resolution face recognition via low-rank representation and locality-constrained regression. Comput Electr Eng 70:968–977

    Article  Google Scholar 

  32. Shakeel MS (2016) Recognition of low-resolution face images using sparse coding of local features. In: IEEE signal and information processing association annual summit and conference (APSIPA)

  33. Jiang J, Ma X, Chen C, Lu T, Wang Z, Ma J (2016) Single image super-resolution via locally regularized anchored neighborhood regression and nonlocal means. IEEE Trans Multimed 19(1):15–26

    Article  Google Scholar 

  34. Chang H, Yeung DY, Xiong Y (2004) Super-resolution through neighbor embedding. In: IEEE conference computer vision pattern recognition, Washington, DC, US, Jun/Jul. 2004, pp 1–6

  35. Bevilacqua M, Roumy A, Guillemot C, Alberi-Morel ML (2012) Alberi Morel, Low-complexity single-image super-resolution based on nonnegative neighbor embedding, in British Machine Vision Conference (BMVC) 2012

  36. J. Yang, J. Wright, T. Huang, and Y. Ma, Image super- resolution via sparse representation, Image Processing, IEEE Transactions on, 19(11):2861–2873, 2010. 4321, 4322, 
4323, 4324, 4325, 4326, 4327

  37. Timofte R, Smet VD, Gool LV (2013) Anchored neighborhood regression for fast example-based super resolution. In: ICCV

  38. Junjun J, Fu J, Lu T, Hu R, Wang Z (2015) Locally regularized Anchored Neighborhood Regression for fast super-resolution. In: IEEE international conference on multimedia and expo

  39. Shang X, Yang W, Sun S, Tian Y, Chen H, Chen K (2017) Adaptive anchor-point selection for single image super resolution. In: IEEE visual communications and image processing (VCIP)

  40. Akbarzadeh S, Ghassemianz H, Vaezi F (2015), An efficient single image super resolution algorithm based on wavelet transforms. In: IEEE 9th Iranian conference on machine vision and image processing, November 18–19, 2015

  41. Rasti P, Lüsi I, Demirel H, Kiefer R, Anbarjafari G (2014) Wavelet transform based new interpolation technique for Satellite image resolution enhancement. In: IEEE international conference on aerospace electronics and remote sensing technology (ICARES)

  42. Arif F, Sarwar T (2014) Super resolution using edge modification through stationary wavelet transform. In: IEEE international conference on information visualization (IV)

  43. Ahmed J, Gao B, Tian GY (2017) Wavelet domain based directional dictionaries for single image super-resolution. In: IEEE international conference on imaging systems and techniques (IST)

  44. Routray S, Ray AK, Mishra C (2018) Image denoising by preserving geometric components based on weighted bilateral filter and curvelet transform. Optik 159:333–343

    Article  Google Scholar 

  45. Muhammad N, Bibi N, Jahangir A, Mahmood Z (2018) Image denoising with norm weighted fusion estimators. Pattern Anal Appl 21(4):1013–1022

    Article  MathSciNet  Google Scholar 

  46. Rabbouch H, Saâdaoui F (2018) A wavelet-assisted subband denoising for tomographic image reconstruction. J Vis Commun Image Represent 55:115–130

    Article  Google Scholar 

  47. Muhammad N, Bibi N, Wahab A, Mahmood Z, Akram T, Naqvi SR, Oh HS, Kim DG (2018) Image de-noising with subband replacement and fusion process using bayes estimators. Comput Electr Eng 70:413–427

    Article  Google Scholar 

  48. Shin DK, Moon YS (2015) Super resolution image reconstruction using Wavelet based patch and discrete tavelet transform. J Sig Process Syst 81(1):71–81

    Article  Google Scholar 

  49. Suryanarayana G, Dhuli R (2016) Image resolution enhancement using wavelet domain transformation and sparse signal representation. In: Elsevier international conference on intelligent computing, communication & convergence (ICCC)

  50. Lu Z, Zou Q, Zhou F, Liao Q (2017) Wavelet-based single image super-resolution with an overall enhancement procedure. In: IEEE international conference on acoustics, speech and signal processing (ICASSP)

  51. George SN (2018) Robust single image super resolution using neighbor embedding and fusion in wavelet domain. Comput Electr Eng 70:674–689

    Article  Google Scholar 

  52. Darbon J, Cunha A, Chan TF, Osher S, Jensen GJ (2008) Fast nonlocal filtering applied to electron cryomicroscopy. In: IEEE international symposium on biomedical imaging

  53. Zeyde R, Elad M, Protter M (2012) On single image scale-up us-ing sparse-representations, vol 6920. Springer, Berlin, pp 711–730

    MATH  Google Scholar 

  54. Buades A, Coll B, Morel JM (2006) A review of image de-noising algorithms, with a new one. Multiscale Model Simul 4(2):490–530

    Article  Google Scholar 

  55. Wang Z, Bovik A, Sheikh H, Simoncelli E (2004) Im age quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600–612

    Article  Google Scholar 

Download references

Acknowledgements

The author would like to appreciate his project guide Dr. Nazeer Muhammed for his immense support toward the success of this work. Not forgetting all researchers for sharing their respective ideas via journals, papers, videos etc. which collectively helped me in writing this paper. I thank you all.

Author information

Authors and Affiliations

  1. Department of Electronics Engineering, University Putra Malaysia, Kuala Lumpur, Malaysia

    Chidiebere Somadina Ike

  2. Department of Mathematics, COMSATS University Islamabad, Wah Campus, Islamabad, Pakistan

    Nazeer Muhammad

Authors
  1. Chidiebere Somadina Ike
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Nazeer Muhammad
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Nazeer Muhammad.

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

Ike, C.S., Muhammad, N. Separable property-based super-resolution of lousy image data. Pattern Anal Applic 23, 1407–1420 (2020). https://doi.org/10.1007/s10044-019-00854-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10044-019-00854-8

Keywords

Search

Navigation