An improved image blind deblurring based on dark channel prior

Abstract

In order to solve the ringing effect caused by the incorrect estimation of the blur kernel, an improved blind image deblurring algorithm based on the dark channel prior is proposed. First, in the blur kernel estimation stage, high-pass filtering is introduced to enhance the image quality and enhance the edge information to make the blur kernel estimation more accurate. A combination of super Laplacian prior and dark channel prior is introduced to estimate the potential clear image. Then the accurate blur kernel is estimated through alternate iterations from coarse to fine. In the image restoration stage, a weighted least square filter is introduced to suppress the ringing effect of the original clear image to further improve the quality of image restoration. Finally, image deconvolution based on Laplace priors and L₀ regularized priors is used to restore clear images. Experimental results show that our approach improves the peak signal-to-noise ratio (PSNR) by about 0.4 dB and structural similarity (SSIM) by about 0.01, respectively. Compared with the existing image deblurring algorithms, this method can estimate the blur information more accurately, so that the restored image can achieve the effect of keeping the edges and removing ringing.

References

[1] Krishnan D, Tay T and Fergus R, Blind Deconvolution Using a Normalized Sparsity Measure, IEEE Conference on Computer Vision and Pattern Recognition, 233 (2011).

[2] Xu L, Zheng S and Jia J, Unnatural. L₀ Sparse Representation for Natural Image Deblurring, IEEE Conference on Computer Vision and Pattern Recognition, 1107 (2013).

[3] YanJ W, XieT T, PengH, LiuP H. Laser & Optoelectronics Progress, 2017, 54: 156(in Chinese)

[4] FengX C, LiuX, YangC Y, WangW W. Journal of Beijing University of Posts and Telecommunications, 2018, 41: 8(in Chinese)

[5] YuY B, PengN, GanJ Y. Acta Electronica Sinica, 2016, 44: 1168(in Chinese)

[6] Michaeli T and Irani M, Blind Deblurring Using Internal Patch Recurrence, European Conference on Computer Vision, 783 (2014).

[7] PanJ, HuZ, SuZ, YangM H. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39: 342

[8] ZuoW, RenD, ZhangD, GuS, ZhangL. IEEE Transactions on Image Processing, 2016, 25: 1751

[9] PanJ, SunD, PfisterH, YangM H. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40: 2315

[10] ZhangH, WuY, ZhangL, ZhangZ, LiY. Neurocomputing, 2020, 398: 265

[11] J. Sun, W. Cao, Z. Xu and J. Ponce, Learning a Convolutional Neural Network for Non-Uniform Motion Blur Removal, IEEE Conference on Computer Vision and Pattern Recognition, 769 (2015).

[12] S. Nah, T. H. Kim and K. M. Lee, Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring, IEEE Conference on Computer Vision and Pattern Recognition, 257 (2017).

[13] T. M. Nimisha, A. K. Singh and A. N. Rajagopalan, Blur-Invariant Deep Learning for Blind-Deblurring, IEEE International Conference on Computer Vision, 4762 (2017).

[14] Kupyn O, Budzan V and Mykhailych M, DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks, IEEE Conference on Computer Vision and Pattern Recognition, 8183 (2018).

[15] G. Gong and K. Zhang, Local Blurred Natural Image Restoration Based on Self-Reference Deblurring Generative Adversarial Networks, IEEE International Conference on Signal and Image Processing Applications, 231 (2019).

[16] ZuoW, LinZ. IEEE Transactions on Image Processing, 2011, 20: 2748

[17] He K, Sun J and Tang X, Single Image Haze Removal Using Dark Channel Prior, IEEE Computer Vision and Pattern Recognition, 1956 (2009).

[18] ZhangZ, LiQ, XuZ, FengH. Opt. Precision Eng., 2019, 27: 181 in Chinese)

[19] QiuX, DaiM. Opt. Precision Eng., 2017, 25: 2490 in Chinese)

[20] TangJ, ShuX, QiG J, LiZ, WangM, YanS, JainR. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39: 1662

[21] WangY, YangJ, YinW, ZhangY. SIAM Journal on Imaging Sciences, 2008, 1: 248

[22] TaiY W, TanP, BrownM S. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 33: 1603

[23] Krishnan D and Fergus R, Fast Image Deconvolution Using Hyper-Laplacian Priors, International Conference on Neural Information Processing Systems, 1033 (2009).

[24] WangZ, BovikA C, SheikhH R, SimoncelliE P. IEEE Transactions on Image Processing, 2004, 13: 600

[25] Shearer P, Gilbert A C and Iii A O H, Correcting Camera Shake by Incremental Sparse Approximation, IEEE International Conference on Image Processing, 572 (2013).