Double-channel cyclic image deblurring algorithm based on edge features

Abstract

Photographs taken in daily life often became blurred due to shaking, out-of-focus, changes in depth of field, and movement of photographed objects. Aiming at this problem, a double-channel cyclic image deblurring method based on edge features was proposed. Firstly, image edge gradient operator was introduced as a threshold based on the rule that the maximum value of the image edge gradient will decrease after the blurring process, making the blurred image be divided into two channels: edge channel and non-edge channel. Secondly, a double-channel loop iteration network was designed, where the edge gradient was used in the edge channel to sample the main edge structure and bilateral filtering was used in the non-edge channel to extract the detailed texture feature information. Finally, the feature information extracted from two channels was cyclically iterated to obtain a clear image using the deblurring model with maximum a posteriori probability. The experimental results showed that the image evaluation indexes obtained by the proposed deblurring model were superior to those of other algorithms, and the edge structure and texture details of the image were effectively recovered with better performance.

Keywords

double-channel loop iteration / bilateral filtering / image edge gradient / maximum a posteriori probability / image deblurring

References

[1] FERGUS R, SINGH B, HERTZMANN A, et al. Removing camera shake from a single photograph//ACM SIGGRAPH 2006 Papers, July 30, 2006, Boston, Massachusetts, USA. New York: ACM, 2006: 787-794.

[2] LEVIN A, WEISS Y, DURAND F, et al. Efficient marginal likelihood optimization in blind deconvolution//CVPR 2011, June 20-25, 2011, Colorado Springs, CO, USA. New York: IEEE, 2011: 2657-2664.

[3] KRISHNAN D, TAY T, FERGUS R. Blind deconvolution using a normalized sparsity measure//2011 IEEE Conference on Computer Vision and Pattern Recoggnition, June 20-25, 2011, Colorado Springs, CO, USA. New York: IEEE, 2011: 233-240.

[4] XU L, ZHENG S C, JIA J Y. Unnatural L0 sparse representation for natural image deblurring//2013 IEEE Conference on Computer Vision and Pattern Recognition, June 23-28, 2013, Portland, OR, USA. New York: IEEE, 2013: 1107-1114.

[5] CAO S F, HU H P, WANG W K. Blind image deblurring method based on l₁/l₂-norm regularization. Journal of Measurement Science and Instrumentation, 2023, 14(2): 182-188.

[6] JIA J Y. Single image motion deblurring using transparency//2007 IEEE Conference on Computer Vision and Pattern Recognition, June 17-22, 2007, Minneapolis, MN, USA. New York: IEEE, 2007: 1-8.

[7] DING M N. An edge-directed diffusion equation-based image restoration approach for font generation. IEEE Access, 2023, 11: 141435-141444.

[8] YANG C Y, WANG W W, FENG X C. Joint image restoration and edge detection in cooperative game formulation. Signal Processing, 2022, 191: 108363.

[9] CHOI J K, DONG B, ZHANG X Q. An edge driven wavelet frame model for image restoration. Applied and Computational Harmonic Analysis, 2020, 48(3): 993-1029.

[10] LI R Q, CANG Y. A lightweight blind super resulotion network based on generative adversarial network. Applied Science and Technology, 2024, 51(2): 112-119.

[11] ZHANG J W, PAN J S, REN J, et al. Dynamic scene deblurring using spatially variant recurrent neural networks//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 18-23, 2018, Salt Lake City, UT, USA. New York: IEEE, 2018: 2521-2529.

[12] SHAO W Z, LIU Y Y, YE L Y, et al. DeblurGAN+: Revisiting blind motion deblurring using conditional adversarial networks. Signal Processing, 2020, 168: 107338.

[13] CAI J R, ZUO W M, ZHANG L. Dark and bright channel prior embedded network for dynamic scene deblurring. IEEE Transactions on Image Processing, 2020, 29: 6885-6897.

[14] CAO H J, LI Y F, ZHANG Q A. An improved fundus image repair algorithm Criminisi. Journal of North University of China (Natural Science Edition), 2023, 44(2): 176-181.

[15] SHAN Q, JIA J Y, AGARWALA A. High-quality motion deblurring from a single image. ACM Transactions on Graphics, 2008, 27(3): 1-10.

[16] FERGUS R, SINGH B, HERTZMANN A, et al. Removing camera shake from a single photograph//ACM SIGGRAPH 2006 Papers, July 30, 2006, Boston, Massachusetts. New York: ACM, 2006: 787-794.

[17] ZHANG K, ZUO W M, CHEN Y J, et al. Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising. IEEE Transactions on Image Processing, 2017, 26(7): 3142-3155.

[18] YOUNG W H. On the multiplication of successions of Fourier constants. Proceedings of the Royal Society of London Series A, Containing Papers of a Mathematical and Physical Character, 1912, 87(596): 331-339.

[19] PAN J S, LIU R S, SU Z X, et al. Motion blur kernel estimation via salient edges and low rank prior//2014 IEEE International Conference on Multimedia and Expo, July 14-18, 2014, Chengdu, China. New York: IEEE, 2014: 1-6.

[20] LEVIN A, WEISS Y, DURAND F, et al. Efficient marginal likelihood optimization in blind deconvolution//2011 IEEE Conference on Computer Vision and Pattern Recognition, June 20-25, 2011, Colorado Springs, CO, USA. New York: IEEE, 2011: 2657-2664.

[21] PAN J S, SUN D Q, PFISTER H, et al. Blind image deblurring using dark channel prior//2016 IEEE Conference on Computer Vision and Pattern Recognition, June 27-30, 2016, Las Vegas, NV, USA. New York: IEEE, 2016: 1628-1636.

[22] WEN F, YING R D, LIU Y P, et al. A simple local minimal intensity prior and an improved algorithm for blind image deblurring. IEEE Transactions on Circuits and Systems for Video Technology, 2021, 31(8): 2923-2937.

[23] ZHANG Y Z, SHI Y, MA L, et al. Blind natural image deblurring with edge preservation based on L0-regularized gradient prior. Optik, 2021, 225: 1657.