Image dehazing using window-based integrated means filter

  • Dilbag Singh
  • Vijay Kumar
  • Manjit KaurEmail author


Image acquisition is generally susceptible to poor environmental conditions such as fog, smog, haze, etc. However, designing an efficient image dehazing technique is still an ill posed problem. Extensive review of the competitive haze removal approaches reveal that the texture preservation and computational speed are still a challenging issues. Therefore, in this paper, initially, a mask is utilized to decompose an input image into low and high frequency regions based on image gradient magnitude. Thereafter, a Gradient sensitive loss (GSL) is designed to obtain the depth information from an input hazy image. Thereafter, transmission map is refined by designing an efficient filter named as Window-based integrated means filter (WIMF). Finally, the restoration model is utilized to recover the hazy images. Experimental analysis reveals that the proposed dehazing technique achieves considerable results beyond the prototypes of the benchmarks. Additionally, the proposed technique outperforms the state-of-the-arts in single image dehazing approaches.


Dehazing Gradient sensitive loss Restoration model Transmission map WIMF 



  1. 1.
    Alajarmeh A, Salam R, Abdulrahim K, Marhusin M, Zaidan A, Zaidan B (2018) Real-time framework for image dehazing based on linear transmission and constant-time airlight estimation. Inform Sci 436–437:108–130. MathSciNetCrossRefGoogle Scholar
  2. 2.
    Bala J, Lakhwani K (2019) Performance evaluation of various desmogging techniques for single smoggy images. Modern Phys Lett B: 1950056CrossRefGoogle Scholar
  3. 3.
    Bouguelia M-R, Nowaczyk S, Santosh K, Verikas A (2018) Agreeing to disagree: active learning with noisy labels without crowdsourcing. Int J Machine Learn Cybern 9(8):1307–1319CrossRefGoogle Scholar
  4. 4.
    Chen B-H, Huang S-C (2016) Edge collapse-based dehazing algorithm for visibility restoration in real scenes. J Disp Technol 12(9):964–970CrossRefGoogle Scholar
  5. 5.
    Choi LK, You J, Bovik AC (2015) Referenceless prediction of perceptual fog density and perceptual image defogging. IEEE Trans Image Process 24(11):3888–3901MathSciNetCrossRefGoogle Scholar
  6. 6.
    Cosmin Ancuti CDV, Ancuti CO (2016) D-hazy: a dataset to evaluate quantitatively dehazing algorithms. In: IEEE international conference on image processing (ICIP), ICIP’16, pp 2226–2230Google Scholar
  7. 7.
    Dong C, Loy CC, He K, Tang X (2014) Learning a deep convolutional network for image super-resolution. In: European conference on computer vision. Springer, pp 184–199Google Scholar
  8. 8.
    Emberton S, Chittka L, Cavallaro A (2018) Underwater image and video dehazing with pure haze region segmentation. Comput Vision Image Understand 168:145–156. special Issue on Vision and Computational Photography and Graphics. CrossRefGoogle Scholar
  9. 9.
    Fattal R (2014) Dehazing using color-lines. ACM Trans Graphics (TOG) 34(1):13CrossRefGoogle Scholar
  10. 10.
    Ge G, Wei Z, Zhao J (2015) Fast single-image dehazing using linear transformation. Optik 126(21):3245–3252. CrossRefGoogle Scholar
  11. 11.
    Gibson KB, Vo DT, Nguyen TQ (2012) An investigation of dehazing effects on image and video coding. IEEE Trans Image Process 21(2):662–673MathSciNetCrossRefGoogle Scholar
  12. 12.
    Hautiere N, Tarel J-P, Aubert D, Dumont E (2011) Blind contrast enhancement assessment by gradient ratioing at visible edges. Image Anal Stereology 27(2):87–95MathSciNetCrossRefGoogle Scholar
  13. 13.
    He K, Sun J, Tang X (2011) Single image haze removal using dark channel prior. IEEE Trans Pattern Anal Mach Intell 33(12):2341–2353CrossRefGoogle Scholar
  14. 14.
    Hu H, Li B, Liu Q (2016) Removing mixture of gaussian and impulse noise by patch-based weighted means. J Sci Comput 67(1):103–129MathSciNetCrossRefGoogle Scholar
  15. 15.
    Jiang Y, Sun C, Zhao Y, Yang L (2017) Image dehazing using adaptive bi-channel priors on superpixels. Comput Vision Image Understand 165:17–32. CrossRefGoogle Scholar
  16. 16.
    Jung S-W (2013) Enhancement of image and depth map using adaptive joint trilateral filter. IEEE Trans Circuits Syst Video Technol 23(2):258–269MathSciNetCrossRefGoogle Scholar
  17. 17.
    Kede Ma WL, Wang Z (2015) Perceptual evaluation of single image dehazing algorithms. In: Image processing, Proc. IEEE, Citeseer, pp 3600–3604Google Scholar
  18. 18.
    Koschmieder H (1938) Luftlicht und sichtweite. Naturwissenschaften 26(32):521–528CrossRefGoogle Scholar
  19. 19.
    Kushwaha AKS, Srivastava R (2015) Framework for dynamic background modeling and shadow suppression for moving object segmentation in complex wavelet domain. Journal Electron Imaging 24(5):051005CrossRefGoogle Scholar
  20. 20.
    Li B, Liu Q, Xu J, Luo X (2011) A new method for removing mixed noises. Sci China Inform Sci 54(1):51–59CrossRefGoogle Scholar
  21. 21.
    Li B, Ren W, Fu D, Tao D, Feng D, Zeng W, Wang Z (2017) Reside: a benchmark for single image dehazing, arXiv:1712.04143
  22. 22.
    Li Z, Zheng J (2015) Edge-preserving decomposition-based single image haze removal. IEEE Trans Image Process 24(12):5432–5441MathSciNetCrossRefGoogle Scholar
  23. 23.
    Ling Z, Fan G, Gong J, Wang Y, Lu X (2017) Perception oriented transmission estimation for high quality image dehazing. Neurocomputing 224:82–95. CrossRefGoogle Scholar
  24. 24.
    McCartney EJ (1976) Optics of the atmosphere: scattering by molecules and particles. Wiley, New York, p 1976.421Google Scholar
  25. 25.
    Nair D, Sankaran P (2018) Color image dehazing using surround filter and dark channel prior. J Visual Commun Image Representation 50:9–15. CrossRefGoogle Scholar
  26. 26.
    Obaidullah SM, Bose A, Mukherjee H, Santosh K, Das N, Roy K (2018) Extreme learning machine for handwritten indic script identification in multiscript documents. J Electron Imaging 27(5):051214CrossRefGoogle Scholar
  27. 27.
    Qi M, Hao Q, Guan Q, Kong J, Zhang Y (2015) Image dehazing based on structure preserving. Optik 126(22):3400–3406. CrossRefGoogle Scholar
  28. 28.
    Rong Z, Jun WL (2014) Improved wavelet transform algorithm for single image dehazing. Optik 125(13):3064–3066. CrossRefGoogle Scholar
  29. 29.
    Saini R, Kumar P, Kaur B, Roy PP, Dogra DP, Santosh K (2018) Kinect sensor-based interaction monitoring system using the blstm neural network in healthcare. Int J Mach Learn Cybern: 1–12Google Scholar
  30. 30.
    Shi L-F, Chen B-H, Huang S-C, Larin AO, Seredin OS, Kopylov AV, Kuo S-Y (2018) Removing haze particles from single image via exponential inference with support vector data description. IEEE Trans Multimed 20(9):2503–2512CrossRefGoogle Scholar
  31. 31.
    Shu Q, Wu C, Zhong Q, Liu RW (2019) Alternating minimization algorithm for hybrid regularized variational image dehazing. Optik 185:943–956. CrossRefGoogle Scholar
  32. 32.
    Singh D, Kumar V (2018) Single image haze removal using integrated dark and bright channel prior. Modern Phys Lett B: 1850051MathSciNetCrossRefGoogle Scholar
  33. 33.
    Singh D, Kumar V (2019) Image dehazing using moore neighborhood-based gradient profile prior. Signal Process Image Commun 70:131–144CrossRefGoogle Scholar
  34. 34.
    Song Y, Li J, Wang X, Chen X (2017) Single image dehazing using ranking convolutional neural network. IEEE Trans MultimedGoogle Scholar
  35. 35.
    Tarel J-P, Hautiere N, Caraffa L, Cord A, Halmaoui H, Gruyer D (2012) Vision enhancement in homogeneous and heterogeneous fog. IEEE Intell Transp Syst Mag 4(2):6–20CrossRefGoogle Scholar
  36. 36.
    Tarel J-P, Hautiere N, Cord A, Gruyer D, Halmaoui H (2010) Improved visibility of road scene images under heterogeneous fog. In: Intelligent vehicles symposium (IV), 2010 IEEE, Citeseer, pp 478–485Google Scholar
  37. 37.
    Ukil S, Ghosh S, Obaidullah SM, Santosh K, Roy K, Das N (2019) Improved word-level handwritten indic script identification by integrating small convolutional neural networks. Neural Comput Appl: 1–16Google Scholar
  38. 38.
    Xia P, Liu X (2016) Image dehazing technique based on polarimetric spectral analysis. Optik 127(18):7350–7358. CrossRefGoogle Scholar
  39. 39.
    Xu L, Zhao D, Yan Y, Kwong S, Chen J, Duan L-Y (2019) Iders: iterative dehazing method for single remote sensing image. Inform Sci 489:50–62. CrossRefGoogle Scholar
  40. 40.
    Zhang K, Gao X, Tao D, Li X (2012) Single image super-resolution with non-local means and steering kernel regression. IEEE Trans Image Process 21 (11):4544–4556MathSciNetCrossRefGoogle Scholar
  41. 41.
    Zhao D, Xu L, Yan Y, Chen J, Duan L-Y (2019) Multi-scale optimal fusion model for single image dehazing. Signal Process Image Commun 74:253–265. CrossRefGoogle Scholar
  42. 42.
    Zuo W, Zhang L, Song C, Zhang D, Gao H (2014) Gradient histogram estimation and preservation for texture enhanced image denoising. IEEE Trans Image Process 23(6):2459–2472MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Department of Computer Science and Engineering, School of Computing and Information TechnologyManipal University JaipurJaipurIndia
  2. 2.Department of Computer Science and EngineeringNational Institute of Technology HamirpurHamirpurIndia
  3. 3.Department of Computer and Communication Engineering, School of Computing and Information TechnologyManipal University JaipurJaipurIndia

Personalised recommendations