Abstract
Image restoration is a critical procedure for underwater images, which suffer from serious color deviation and edge blurring. Restoration can be divided into two stages: de-scattering and edge enhancement. First, we introduce a multi-scale iterative framework for underwater image de-scattering, where a convolutional neural network is used to estimate the transmission map and is followed by an adaptive bilateral filter to refine the estimated results. Since there is no available dataset to train the network, a dataset which includes 2000 underwater images is collected to obtain the synthetic data. Second, a strategy based on white balance is proposed to remove color casts of underwater images. Finally, images are converted to a special transform domain for denoising and enhancing the edge using the non-subsampled contourlet transform. Experimental results show that the proposed method significantly outperforms state-of-the-art methods both qualitatively and quantitatively.
Similar content being viewed by others
References
Ancuti C, Ancuti CO, Haber T, et al., 2012. Enhancing underwater images and videos by fusion. IEEE Conf on Computer Vision and Pattern Recognition, p.81–88. https://doi.org/10.1109/CVPR.2012.6247661
Cai BL, Xu XM, Jia K, et al., 2016. DehazeNet: an end-to-end system for single image haze removal. IEEE Trans Image Process, 25(11):5187–5198. https://doi.org/10.1109/TIP.2016.2598681
Carlevaris-Bianco N, Mohan A, Eustice RM, 2010. Initial results in underwater single image dehazing. OCEANS MTS/IEEE SEATTLE, p.1–8. https://doi.org/10.1109/OCEANS.2010.5664428
Chiang JY, Chen YC, 2012. Underwater image enhancement by wavelength compensation and dehazing. IEEE Trans Image Process, 21(4):1756–1769. https://doi.org/10.1109/TIP.2011.2179666
Drews P Jr, do Nascimento E, Moraes F, et al., 2013. Transmission estimation in underwater single images. IEEE Int Conf on Computer Vision Workshops, p.825–830. https://doi.org/10.1109/ICCVW.2013.113
Finlayson GD, Trezzi E, 2004. Shades of gray and colour constancy. The 12th Color Imaging Conf: Color Science and Engineering Systems, Technologies, Applications, p.37–41.
Galdran A, Pardo D, Picón A, et al., 2015. Automatic red-channel underwater image restoration. J Vis Commun Image Represent, 26:132–145. https://doi.org/10.1016/j.jvcir.2014.11.006
Goodfellow IJ, Warde-Farley D, Mirza M, et al., 2013. Maxout networks. https://doi.org/arxiv.org/abs/1302.4389?context=stat
He KM, Sun J, Tang XO, 2011. Single image haze removal using dark channel prior. IEEE Trans Patt Anal Mach Intell, 33(2):2341–2353. https://doi.org/10.1109/TPAMI.2010.168
Iqbal K, Odetayo M, James A, et al., 2010. Enhancing the low quality images using unsupervised colour correction method. IEEE Int Conf on Systems, Man and Cybernetics, p.1703–1709. https://doi.org/10.1109/ICSMC.2010.5642311
Li Y, Hu J, Jia Y, 2014. Automatic SAR image enhancement based on nonsubsampled contourlet transform and memetic algorithm. Neurocomputing, 134:70–78. https://doi.org/10.1016/j.neucom.2013.03.068
Mao BQ, Jin XM, 2010. Application of self-adaptive histogram equalization algorithm to image enhancement processing. J Hebei North Univ (Nat Sci Ed), 26(5):64–68 (in Chinese). https://doi.org/10.3969/j.issn.1673-1492.2010.05.015
Padmavathi G, Subashini P, Kumar MM, 2010. Comparison of filters used for underwater image pre-processing. Int J Comput Sci Netw Secur, 10(1):58–65.
Pan JS, Sun DQ, Pfister H, et al., 2016. Blind image deblurring using dark channel prior. IEEE Conf on Computer Vision and Pattern Recognition, p.1628–1636. https://doi.org/10.1109/CVPR.2016.180
Panetta K, Gao C, Agaian S, 2016. Human-visual-system-inspired underwater image quality measures. IEEE J Ocean Eng, 41(3):541–551. https://doi.org/10.1109/JOE.2015.2469915
Schechner YY, Karpel N, 2006. Recovery of underwater visibility and structure by polarization analysis. IEEE J Ocean Eng, 30(3):570–587. https://doi.org/10.1109/JOE.2005.850871
Tan CS, Sluzek A, Seet GLG, et al., 2007. Range gated imaging system for underwater robotic vehicle. OCEANS Asia Pacific, p.1–6. https://doi.org/10.1109/OCEANSAP.2006.4393938
Tang KT, Yang JC, Wang J, 2014. Investigating haze-relevant features in a learning framework for image dehazing. IEEE Conf on Computer Vision and Pattern Recognition, p.2995–3002. https://doi.org/10.1109/CVPR.2014.383
Tarel JP, Hautiere N, Caraffa L, et al., 2012. Vision enhancement in homogeneous and heterogeneous fog. IEEE Intell Trans Syst Mag, 4(2):6–20. https://doi.org/10.1109/MITS.2012.2189969
Thakur VS, Tripathi N, 2010. On the way towards efficient enhancement of multi-channel underwater images. Int J Appl Eng Res, 5(5):895–903.
Tomasi C, Manduchi R, 1998. Bilateral filtering for gray and color images. Proc 6th Int Conf on Computer Vision, p.839–846.
Treibitz T, Schechner YY, 2009. Active polarization des-cattering. IEEE Trans Patt Anal Mach Intell, 31(3):385–399. https://doi.org/10.1109/TPAMI.2008.85
Vasamsetti S, Mittal N, Neelapu BC, et al., 2017. Wavelet based perspective on variational enhancement technique for underwater imagery. Ocean Eng, 141:88–100. https://doi.org/10.1016/j.oceaneng.2017.06.012
Wang HL, Cai WY, Yang JY, et al., 2015. Design of HD video surveillance system for deep-Sea biological exploration. Proc IEEE 16th Int Conf on Communication Technology, p.908–911. https://doi.org/10.1109/ICCT.2015.7399971
Yang AP, Zhang LY, Qu C, et al., 2017. Underwater images visibility improving algorithm with weighted L1 regularization. J Electron Inform Technol, 39(3):626–633 (in Chinese). https://doi.org/10.11999/JEIT160481
Yang M, Sowmya A, 2015. An underwater color image quality evaluation metric. IEEE Trans Imag Proc, 24(12):6062–6071. https://doi.org/10.1109/TIP.2015.2491020
Zhang SP, Zeng P, Luo XM, et al., 2012. Multi-scale retinex with color restoration and detail compensation. J Xi'an Jiaotong Univ, 46(4):32–37 (in Chinese).
Acknowledgements
We would like to thank Miao YANG of the Department of Electronic and Engineering, Huaihai Institute of Technology, for providing the source code of the UCIQE metric.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Pan, Pw., Yuan, F. & Cheng, E. De-scattering and edge-enhancement algorithms for underwater image restoration. Frontiers Inf Technol Electronic Eng 20, 862–871 (2019). https://doi.org/10.1631/FITEE.1700744
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1631/FITEE.1700744