access icon free Blind deblurring using coupled convolutional sparse coding regularisation for noisy-blurry images

© The Institution of Engineering and Technology
Received 16/03/2018, Published 07/06/2018

This Letter proposes a novel method to deblur a blurry image corrupted by noise. The authors estimate a noise-free version of the input blurred image and a corresponding noise-free version of the latent image without damaging the blur information, as well as the latent image and blur kernel in an alternating fashion. To this end, they first propose coupled convolutional sparse coding, which incorporates the coupled dictionary concept into convolutional sparse coding. Then they model the noise-free blurred image to share the sparse coefficients with the noise-free latent image using the coupled dictionaries. By utilising these noise-free images as priors in alternating latent image estimation and blur kernel estimation steps, they can estimate a high-quality latent image and blur kernel in the presence of noise. Experimental results demonstrate that the proposed method outperforms previous methods in handling noisy blurred images.

Inspec keywords: deconvolution; image restoration; image denoising

Other keywords: input blurred image; blur information; noise-free blurred image; sparse coefficients; latent image estimation; noise-free latent image; high-quality latent image; blur kernel estimation steps; blurry image; coupled dictionaries; coupled convolutional sparse coding regularisation; corresponding noise-free version; noisy blurred images; coupled dictionary concept; noisy-blurry images; blind deblurring; noise-free images

Subjects: Optical, image and video signal processing; Computer vision and image processing techniques

References

    1. 1)
    2. 2)
    3. 3)
      • 6. Wohlberg, B.: ‘Efficient convolutional sparse coding’. 2014 IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP), Florence, Italy, May 2014, pp. 7173–7177.
    4. 4)
      • 2. Zhong, L., Cho, S., Metaxas, D., et al: ‘Handling noise in single image deblurring using directional filters’. 2013 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), June 2013, pp. 612–619.
    5. 5)
      • 8. Perrone, D., Favaro, P.: ‘Total variation blind deconvolution: the devil is in the details’. 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, OH, USA, June 2014, pp. 2909–2916.
    6. 6)
      • 3. Li, H., Zhang, Y., Zhang, H., et al: ‘Blind image deblurring based on sparse prior of dictionary pair’. 2012 21st Int. Conf. on Pattern Recognition (ICPR), Tsukuba, Japan, November 2012, pp. 3054–3057.
    7. 7)
      • 7. Levin, A., Weiss, Y., Freeman, B., et al: ‘Efficient approximations to the marginal likelihood in blind deconvolution’. Proc. CVPR, Providence, RI, USA, June 2011, vol. 2011, pp. 1–14.
    8. 8)
      • 9. Michaeli, T., Irani, M.: ‘Blind deblurring using internal patch recurrence’. European Conf. on Computer Vision, Zurich, Switzerland, September 2014, pp. 783–798.
    9. 9)
      • 10. Levin, A., Weiss, Y., Durand, F., et al: ‘Understanding and evaluating blind deconvolution algorithms’. 2009. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR, 2009), Miami, FL, USA, June 2009, pp. 1964–1971.
    10. 10)
      • 1. Tai, Y.-W., Lin, S.: ‘Motion-aware noise filtering for deblurring of noisy and blurry images’. 2012 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Providence, RI, USA, June 2012.
http://iet.metastore.ingenta.com/content/journals/10.1049/el.2018.0901
Loading

Related content

content/journals/10.1049/el.2018.0901
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading