Advertisement

Multimedia Tools and Applications

, Volume 77, Issue 23, pp 30595–30613 | Cite as

Efficient non-local means denoising for image sequences with dimensionality reduction

  • Hemalata Bhujle
  • Basavaraj H. Vadavadagi
  • Shivanand Galaveen
Article
  • 78 Downloads

Abstract

The aim of this paper is to improve both accuracy and computational efficiency of non-local means video (NLMV) denoising algorithm. A technique of principal component analysis (PCA) is used to reduce the heavy dimensionality of patches. A pre-processing step of shot boundary detection is used to split the video sequence into different shots having content-wise similar frames. Further PCA is computed globally for these shots. To speed-up the denoising process, weights are computed in reduced subspace. In the proposed method, we modify the original histogram difference (HD) technique such that content-wise similar frames are separated more systematically and accurately. We have achieved improvement with respect to accuracy and computational speed compared to standard NLM. Moreover, qualitative and quantitative comparisons show that the proposed method is consistently superior compared to that of NLM and some of its variants.

Keywords

Nonlocal means Shot boundary Principal component analysis 

References

  1. 1.
    Almahdi R, Hardie RC (2016) Recursive non-local means filter for video denoising with Poisson-Gaussian noise. IEEE National Aerospace and Elect Conf (NAECON) and Ohio Inn Summ (OIS) 318-322Google Scholar
  2. 2.
    Azzabou N, Paragios N, Guichard F (2007) Image denoising based on adapted dictionary Computation. In Proc., IEEE Int’l Conf. on Image Process, vol 3, p 109–112Google Scholar
  3. 3.
    Balster EJ, Zheng YF, Ewing RL (2006) Combined spatial and temporal domain wavelet Shrinkage algorithm for video denoising. IEEE Trans Circuits Syst Video Technol 16(2):220–230CrossRefGoogle Scholar
  4. 4.
    Bhujle H, Chaudhuri S (2014) Novel speed-up strategies for NLM denoising with patch and edge patch based dictionaries. IEEE Trans Image Process 23(1):356–365MathSciNetCrossRefGoogle Scholar
  5. 5.
    Boreczky JS, Rowe LA (1996) Comparison of video shot boundary detection techniques. Journal of Electronic Imaging 5(2):122–128CrossRefGoogle Scholar
  6. 6.
    Boulanger J, Kervrann C, Bouthemy P (2007) Space-time adaptation for patch-based image sequence restoration. IEEE Trans Pattern Anal Mach Intell 29(6):1096–1102CrossRefGoogle Scholar
  7. 7.
    Brailean J, Kleihorst R, Efstratiadis S, Katsaggelos A, Lagendijk R (1995) Noise reduction filters fordynamic image sequences: A review. Proc IEEE 83:1272–1281CrossRefGoogle Scholar
  8. 8.
    Brox T, KleinSchmidt O, Cremers D (2008) Efficient non-local means for denoising of textural Patterns. IEEE Trans Image Process 17(7):1083–1092MathSciNetCrossRefGoogle Scholar
  9. 9.
    Bruni V, Vitulano D (2007) Combined image compression and denoising using wavelets. Signal Process Image Commun 22:86–101CrossRefGoogle Scholar
  10. 10.
    Buades A, Coll B, Morel JM (2005) A non-local algorithm for image denoising. Proc IEEE Comp Vis and Patt Recogn, p 60–65Google Scholar
  11. 11.
    Buades A, Coll B, Morel JM (2008) Nonlocal image and movie denoising. Int J Comput Vis 76(2):123–140CrossRefGoogle Scholar
  12. 12.
    Campisi P, Neri A, Sorgi L (2002) Automatic dissolve and fade detection for video sequences. Proc., Intl. Conf. on Dig Sig Process, vol 2, p 567–570Google Scholar
  13. 13.
    Cernekova Z, Kotropoulos C, Pitas I (2003) Video shot segmentation using singular valuedecomposition. Proc., Acoustics, speech and signprocess, vol 3, p 181–184Google Scholar
  14. 14.
    Cho D, Bui TD (2005) Multivariate statistical modelling for image denoising using wavelet Transforms. Signal Process Image Commun 20:77–89CrossRefGoogle Scholar
  15. 15.
    Dabov K, Foi A, Egiazarian K (2007) Video denoising by space 3D transform-domain collaborative filtering. In Proc., European Signal Process. Conf, p 145-149Google Scholar
  16. 16.
    Dekeyser F, Bouthemy P, Perez P (2000) Spatiotemporal Wiener filtering of image sequences usinga parametric motion model. Proc IEEE Int’l Conf. on Image Process, vol 1, p 208–211Google Scholar
  17. 17.
    Dugad R, Ahuja N (1999) Video denoising by combining Kalman and Wiener estimates. Intl. Conf. on Image Process, vol 4, p 152–156Google Scholar
  18. 18.
    Feng H, Fang W, Liu S, Fang Y (2005) A new general framework for shot boundary detection andkey-frame extraction. Proc., ACM Sig intl. work on Mult., p 121–126Google Scholar
  19. 19.
    Gargi U, Kasturi R, Strayer S (2000) Performance characterization of video-shot-change detection methods. IEEE Trans Circuits Syst Video Technol 10(1):1–13CrossRefGoogle Scholar
  20. 20.
    Ghosh S, Chaudhuri KN (2016) Fast separable non-local means. Journal of Electronic Imaging 25(2):023026CrossRefGoogle Scholar
  21. 21.
    Gordienko Y, Kochura Y, Alienin O, Rokovyi O, Stirenko S, Gang P, Hui J, Zeng W (2018) Dimensionality Reduction in Deep Learning for Chest X-Ray Analysis of Lung Cancer. International Conference on Advanced Computational Intelligence arXiv preprint arXiv:1801.06495Google Scholar
  22. 22.
    Guo L, Au OC, Ma M, Liang Z (2010) Fast Multi-Hypothesis Motion Compensated Filter for video Denoising. J Signal Process Syst 60(3):273–290CrossRefGoogle Scholar
  23. 23.
    Hanjalic A (2002) Shot-boundary detection: unraveled and resolved? IEEE Trans Circuits Syst Video Technol 12(2):90–105CrossRefGoogle Scholar
  24. 24.
    Hao B, Li M, Feng X (2008) Wavelet iterative regularization for image restoration with varying scale Parameter. Signal Process Image Commun 23:433–441CrossRefGoogle Scholar
  25. 25.
    Heng W, Ngan K (1999) The implementation of object-based shot boundary detection using edge tracing and tracking. Proc., IEEE Intl. Symp on Circ and Sys, vol 4, p 439–442Google Scholar
  26. 26.
    Hosseini H, Marvasti F (2013) Fast restoration of natural images corrupted by high-density impulse noise. EURASIP J Image Video Process 2013:15CrossRefGoogle Scholar
  27. 27.
    Hu J, Zhou J, Wu X (2016) Non-local MRI denoising using random sampling. Magn Reson Imaging 34:990–999CrossRefGoogle Scholar
  28. 28.
    Kalra GS, Singh S (2016) Efficient digital image denoising for gray scale images. Journal of Multimedia Tools and Applications 75(8):4467–4484CrossRefGoogle Scholar
  29. 29.
    Kervrann C, Boulanger J, Coupe P (2007) Bayesian non-local means filter, image redundancy and adaptive dictionaries for noise removal. In Proc., Conf. on Scale-Space and Var Meth in Compu Vis, p 520–532Google Scholar
  30. 30.
    Khazron PA, Selesnick IW (2010) Spatiotemporal wavelet maximum a posteriori estimation for video denoising. Journal of Electronic Imaging 19(4):043015.  https://doi.org/10.1117/1.3514739
  31. 31.
    Kleihorst RP, Lagendijk RL, Biemond J (1995) Noise reduction of image sequences using motion Compensation and signal decomposition. IEEE Trans Image Process 4(3):274–284CrossRefGoogle Scholar
  32. 32.
    Lee CM, Ip MC (1994) A robust approach for camera break detection in color video sequence. Proc., IAPR work on mach vis appl, p 502–505Google Scholar
  33. 33.
    Lee SH, Kang MG (1998) Spatiotemporal video filtering algorithm based on 3D anisotropic diffusion equation. Proc IEEE Intl Conf Image Process, vol 2, p 447–450Google Scholar
  34. 34.
    Lee TH, Kang JK, Song BC (2012) Video denoising using overlapped motion compensation and advanced collaborative filtering. Journal of Electronic Imaging 21(2):023004.  https://doi.org/10.1117/1.JEI.21.2.023004 CrossRefGoogle Scholar
  35. 35.
    Lelescu D, Schonfeld D (2003) Statistical sequential analysis for real-time video scene change detection on compressed multimedia bit stream. IEEE Transactions on Multimedia 5(1):106–117CrossRefGoogle Scholar
  36. 36.
    Li X, Zheng Y (2009) Patch-based video processing: A variational Bayesian approach. IEEE Trans Circuits Syst Video Technol 19(1):27–40CrossRefGoogle Scholar
  37. 37.
    Li W, Yin X, Liu Y, Zhang M (2016) Robust video denoising for mixed Poisson, Gaussian and impulse noise. IEEE Intl. Conf. on Image Vision and Computing, vol 318, p 322Google Scholar
  38. 38.
    Lia W, Zhang J, Dai Q (2011) Video denoising using shape-adaptive sparse representation over Similar spatio-temporal patches. Signal Process Image Commun 26(4):250–265CrossRefGoogle Scholar
  39. 39.
    Liu Z, Wang T (2016) An adaptive image denoising algorithm based on wavelet transform and independent component analysis. In Proc., IEEE Intl. Conf. on Intell. Sys Design and Engg. Appl., p 104-107Google Scholar
  40. 40.
    Mahmoudi M, Sapiro G (2005) Fast image and video denoising via nonlocal means of similar Neighbourhoods. IEEE Sign Process Lett 12:839–842CrossRefGoogle Scholar
  41. 41.
    Mélange T, Nachtegael M, Kerre EE, Zlokolica V, Schulte S, Witte VD, Pižurica A, Philips W (2008) Video denoising by fuzzy motion and detail adaptive averaging. Journal of Electronic Imaging 19(4):043005.  https://doi.org/10.1117/1.2992065 CrossRefGoogle Scholar
  42. 42.
    Mohamadi N, Soheili AR, Toutounian F (2017) A new hybrid denoising model based on PDEs. Journal of Multimedia Tools and Applications 74(24):1–16Google Scholar
  43. 43.
    Muresan DD, Parks TW (2003) Adaptive principal components and image denoising. Proc. Intl. Conf. Image Process, vol 1, p 101–104Google Scholar
  44. 44.
    Naser AM (2016) Color to grayscale image conversion based dimensionality reduction with stationary wavelet transform. In Proc., IEEE Intl. Conf. on Mult in IT and Com Sci and Appl., p 1-5Google Scholar
  45. 45.
    Orchard J, Ebrahim M, Wang A (2008) Efficient nonlocal means denoising using the SVD. In Proc., IEEE Int’l Conf. on Image Process, p 1732-735Google Scholar
  46. 46.
    Pierrick C, Pierre Y, Christian B (2006) Fast non local means denoising for 3D MR images. In Proc., Intl. Conf. on Med Image Compu and Compu-Ass Int, p 33–40Google Scholar
  47. 47.
    Selesnick IW, Li KY (2003) Video denoising using 2D and 3D dual- tree complex wavelet transforms. Proc Wavelet Appl on Sig and Image Process, p 607–618Google Scholar
  48. 48.
    Tasdizen T (2008) Principal components for nonlocal means image denoising. In Proc., IEEE Int’l Conf. on Image Process, p 1728–1731Google Scholar
  49. 49.
    Tomasi C, Manduchi R (1998) Bilateral filtering for gray and color images. In Proc., Sixth Intl. Conf. on Computer Vision, p 839–846Google Scholar
  50. 50.
    Vignesh R, Byung OT, Kuo CC (2010) Fast non-local means computation with probabilistic early termination. IEEE Sign Process Lett 17(3):277–280CrossRefGoogle Scholar
  51. 51.
    Wang XY, Liu YC, Zhang N, Wu CJ, Yang HY (2015) An edge preserving adaptive image Denoising. Journal of Multimedia Tools and Applications 74(24):11703–11720CrossRefGoogle Scholar
  52. 52.
    Wang Y, Yao H, Zhao S (2016) Auto-encoder based dimensionality reduction. Neurocomputing 184:232–242CrossRefGoogle Scholar
  53. 53.
    Xu D, Wang X, Sun G, Li H (2015) Towards a novel image denoising method with edge preserving sparse representation based on Laplacian of B-Spline edge detection. Journal of Multimedia Tools and Applications l76(17):17839–17854CrossRefGoogle Scholar
  54. 54.
    Xu BH, Gang Y, Wei Z, Cen Y, Zhao RZ, Miao ZJ, Yao Z, Wilson R (2016) Video restoration based on Patch Match and reweighted low-rank mat x recovery. Journal of Multimedia Tools and Applications 75(5):2681–2696CrossRefGoogle Scholar
  55. 55.
    Yuan J, Li J, Lin F, Zhang B (2005) An unified shot boundary detection framework based on graph partition model. Proc., the 13th annual ACM intl. conf. on Mult., p 539–542Google Scholar
  56. 56.
    Zhang HJ, Kankanhalli A, Smoliar SW (2001) Automatic partitioning of full motion video. Read in multcompu and net, p 321–338Google Scholar
  57. 57.
    Zhang J, Li M, He Y (2015) \( {S}_2^1 \) norm based sparse and low-rank decomposition scheme for video denoising. Journal of Electronic Imaging 24(4):043013.  https://doi.org/10.1117/1.JEI.24.4.043013 CrossRefGoogle Scholar
  58. 58.
    Zhu Z, You X, Chen CL, Tao D, Ou W, Tiang X, Zou T (2015) An adaptive hybrid pattern for noise-robust texture analysis. Pattern Recogn 48:2592–2608CrossRefGoogle Scholar
  59. 59.
    Zlokolica V, Philips W (2004) Motion and detail adaptive denoising of video. In Proc IS&T/SPIE Sym on Electr Imag, p 1417–421Google Scholar
  60. 60.
    Zlokolica V, Pižurica A, Philips W, Schulte S, Kerre E (2006) Fuzzy logic recursive motion detection and denoising of video sequence. Journal of Electronic Imaging 15(2):023008.  https://doi.org/10.1117/1.2201548 CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  • Hemalata Bhujle
    • 1
  • Basavaraj H. Vadavadagi
    • 1
  • Shivanand Galaveen
    • 2
  1. 1.Department of Electronics & Communication EngineeringSDM College of Engineering & TechnologyDharwadIndia
  2. 2.Indian Institute of Technology BombayMumbaiIndia

Personalised recommendations