Motion blur image deblurring using edge-based color patches

The shaking of a camera can easily cause blurs in an image. Thus, deblurring is a problem that is worth solving and has always been an active research interest. The color information in an image is an important feature and contains clues for image deblurring that have not been widely exploited. In this paper, we present an efficient and stable blurring kernel estimation method by solving an energy function constructed by a weighted color approximation regularization term. The term is derived from a two-color model, and we use a defined weight to alleviate the color change through the blurring process. Then we select salient edges in an effective way to apply the proposed method on the patches centered at these edges. Experiments on synthetic and real-world images show the efficiency and stability of our proposed method.

Keywords:

Two-color model, blind deblurring, edge selection image patches, motion blur,

PDF

___

Shan Q, Jia J, Agarwala A. High-quality motion deblurring from a single image. ACM T Graphic 2008; 3: 1-10.
Xu L, Zheng S, Jia J. Unnatural L0 sparse representation for natural image deblurring. In: IEEE 2013 Conference on Computer Vision and Pattern Recognition; 23–28 June 2013; Portland, OR, USA. New York, NY, USA: IEEE. pp. 1107-1114.
Bahat Y, Irani M. Blind dehazing using internal patch recurrence. In: IEEE 2014 European Conference on Computer Vision; 6–12 September 2014; Zurich, Switzerland. New York, NY, USA: IEEE. pp. 783-798.
Krishnan D, Tay T, Fergus R. Blind deconvolution using a normalized sparsity measure. In: IEEE 2011 Computer Vision and Pattern Recognition; 20–25 June 2011; Colorado, USA. New York, NY, USA: IEEE. pp. 233-240.
Fergus R, Singh B, Hertzmann A, Roweis ST, Freeman WT. Removing camera shake from a single photograph. ACM T Graphic 2006; 25: 787-794.
Levin A, Weiss Y, Durand F, Freeman WT. Understanding and evaluating blind deconvolution algorithms. In: IEEE 2009 Conference on Computer Vision and Pattern Recognition; 20–25 June 2009; Miami, FL, USA. New York, NY, USA: IEEE. pp. 1964-1971.
Levin A, Weiss Y, Durand F, Freeman WT. Efficient marginal likelihood optimization in blind deconvolution. In: IEEE 2011 Conference on Computer Vision and Pattern Recognition; 20-25 June 2011; Colorado, USA. New York, NY, USA: IEEE. pp. 2657-2664.
Krishnan D, Fergus R. Fast image deconvolution using hyper-Laplacian priors. In: International Conference on Neural Information Processing Systems; 1–5 December 2009; Bangkok, Thailand. pp.1033-1041.
Xu L, Jia J. Two-phase kernel estimation for robust motion deblurring. In: IEEE 2010 European Conference on Computer Vision; 5–11 September 2010; Heraklion, Greece. New York, NY, USA: IEEE. pp. 157-170.
Pan J, Liu R, Su Z, Gu X. Kernel estimation from salient structure for robust motion deblurring. Signal Process- Image 2013; 28: 1156-1170.
Joshi N, Szeliski R, Kriegman D. PSF estimation using sharp edge prediction. In: IEEE 2008 Computer Vision and Pattern Recognition; 24–26 June 2008; Anchorage, AK, USA. New York, NY, USA: IEEE. pp. 1-8.
Cho S, Lee S. Fast motion deblurring. ACM Siggraph Asia 2009; 28: 1-8.
Cho TS, Paris S, Horn BKP, Freeman WT. Blur kernel estimation using the radon transform. In: IEEE 2011 Computer Vision and Pattern Recognition; 20–25 June 2011; Colorado, USA. New York, NY, USA: IEEE. pp. 241-248.
Sun L, Cho S, Wang J, Hays J. Edge-based blur kernel estimation using patch priors. In: IEEE 2013 International Conference on Computational Photography; 19–21 April 2013; Cambridge, MA, USA. New York, NY, USA: IEEE. pp. 1-8.
Daniel Z, Yair W. From learning models of natural image patches to whole image restoration. In: IEEE 2011 International Conference on Computer Vision; 6–13 November 2011; Barcelona, Spain. New York, NY, USA: IEEE. pp. 479-486.
Lei L, Ruiting Z, Jiangmin K, Wenbin L. Image deblurring via an adaptive dictionary learning strategy. Telkomnika 2014; 12: 855.
Yin M, Gao J, Tien D, Cai S. Blind image deblurring via coupled sparse representation. J Vis Commun Image R 2014; 25: 814-821.
Elad M, Aharon M. Image denoising via sparse and redundant representations over learned dictionaries. IEEE T Image Process 2006; 15: 3736-3745.
Ayan C, Todd Z. Fast Deconvolution with Color Constraints on Gradients. Technical Report. Cambridge, MA, USA: Harvard University, 2012.
Mairal J, Elad M, Sapiro G. Sparse representation for color image restoration. IEEE T Image Process 2008; 17: 53-69.
Bennett EP, Uyttendaele M, Zitnick CL, Szeliski R, Kang SB. Video and image Bayesian demosaicing with a two color image prior. In: 2006 IEEE European Conference on Computer Vision; 7–13 May 2006; Graz, Austria. New York, NY, USA: IEEE. pp. 508-521.
Omer I, Werman M. Color lines: image specific color representation. In: 2004 IEEE Computer Vision and Pattern Recognition; 27 June-2-July 2004; Washington, DC, USA. New York, NY, USA: IEEE. pp. 946-953.
Dani L., Anat L, Yair W. A closed-form solution to natural image matting. IEEE T Pattern Anal 2008; 30: 228-242.
Joshi N, Zitnick CL, Szeliski R, Kriegman DJ. Image deblurring and denoising using color priors. In: 2009 IEEE Computer Vision and Pattern Recognition; 20–25 June 2009; Miami, FL, USA. New York, NY, USA: IEEE. pp. 1550-1557.
Lai WS, Ding JJ, Lin YY, Chuang YY. Blur kernel estimation using normalized color-line priors. In: 2015 IEEE Computer Vision and Pattern Recognition; 7–12 June 2015; Boston, MA, USA. New York, NY, USA: IEEE. pp. 64-72.
Rudin LI, Osher S, Fatemi E. Nonlinear total variation based noise removal algorithms. Physica D 1992; 60: 259-268.
Kohler R, Hirsch M, Mohler B, Scholkopf B, Harmeling S. Recording and playback of camera shake: benchmarking blind deconvolution with a real-world database. In: 2012 IEEE European Conference on Computer Vision; 7–13 October 2012; Florence, Italy. New York, NY, USA: IEEE. pp. 27-40.
Bahat Y, Irani M. Blind dehazing using internal patch recurrence. In: 2016 IEEE International Conference on Computational Photography; 14–15 May 2016; Evanston, IL, USA. New York, NY, USA: IEEE. pp. 1-9.
Donatelli M. A multigrid for image deblurring with Tikhonov regularization. Numer Linear Algebr 2010; 12: 715- 729.
Pan J, Sun D, Pfister H, Yang MH. Blind image deblurring using dark channel prior. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition; 26 June–1 July 2016; Las Vegas, NV, USA. New York, NY, USA: IEEE. pp. 1628-1636.

Turkish Journal of Electrical Engineering and Computer Science-Cover

ISSN: 1300-0632
Yayın Aralığı: Yılda 6 Sayı
Yayıncı: TÜBİTAK

Arşiv