Export file:

Format

  • RIS(for EndNote,Reference Manager,ProCite)
  • BibTex
  • Text

Content

  • Citation Only
  • Citation and Abstract

An effcient motion deblurring based on FPSF and clustering

Department of Computer Science and Information Engineering, National Formosa University, Huwei, Yunlin 632, Taiwan

Special Issues: Intelligent Computing

A blurry photograph is a type of degradation of image quality. Blur could be modeled with convolutional operation of an image with a blurring kernel, also known as the point spread function (or PSF). Image deconvolution is the process of recovering the unknown image from its blurred version, given a blurring kernel. It is quite time-consuming by using the recursive process to estimate the kernel. The work proposes an approach to the blurred image into a sharp image using the intelligent computing integrating with linear image degradation process, Fourier transforms, and Fourier spectrum. Based on the model built from the information of the blurry image, a linear degradation process, we estimate the kernel power spectrum and compute phase-retrieval applied the intelligent computing for Fourier theorem and Wiener-Khinchin theorem. Then, the optimal blur kernel can be estimated by using kernel clustering and kernel integration under fast point spread function (FPSF). Finally, the sharp image is achieved by using a deconvolution process, inverse Fourier transform. The approach to deblurring is applied the intelligent computing on the estimated image and Peak signal-to-noise ratio (PSNR) to evaluate the performance. By rebuild an improved PSF, the computing strategy leads a kernel estimation of the caught image and reduces the computational time. Experimental results demonstrate that the proposed method with intelligent computing applied can decrease computational time and achieve good visual quality for deblurring images.
  Figure/Table
  Supplementary
  Article Metrics

Keywords image deblurring; blur kernel; point spread function(PSF); image restoration; phase retrieval

Citation: Hui-Yu Huang, Wei-Chang Tsai. An effcient motion deblurring based on FPSF and clustering. Mathematical Biosciences and Engineering, 2019, 16(5): 4036-4052. doi: 10.3934/mbe.2019199

References

  • 1. M. Egmont-Petersen, D. De Ridder and H. Handels, Image processing with neural networks a review, Pattern Recogn., 35 (2002), 2279–2301.
  • 2. D. De Didder, R. P. Duin, M. Egmont-Petersen, et al., Nonlinear image processing using artificial neural networks, . Imag. Elect. Phys., 126 (2003), 352–450.
  • 3. C. J. Schuler, M. Hirsch, S. Harmeling, et al., IEEE T. Pattern Anal., 38 (2016), 1439–1451.
  • 4. A. Levin, Blind motion deblurring using image statistics, Proc. Adv. Neural Infor. Process. Sys., (2006), 841–848.
  • 5. A. Goldstein and R. Fattal, Blur-kernel estimation from spectral irregularities, European Conference on Computer Vision, (2012), 622–635.
  • 6. W. Hu, J. Xue and N. Zheng, PSF estimation via gradient domain correlation, IEEE T. Image Process., 21 (2012), 386–392.
  • 7. H. Y. Huang and W. C. Tsai, Blurred image restoration using fast blur-kernel estimation, 10th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, (2014), 435–438.
  • 8. Y. Liao, W. Li, J. Cui, et al., Blur kernel estimation model with combined constraints for blind image deblurring, Digital Image Computing: Techniques and Applications, (2018), 1–8.
  • 9. W. H. Richardson, Bayesian-based iterative method of image restoration, J. Opt. Soc. Am., 62 (1972), 55–59.
  • 10. Y. W. Tai, P. Tan and M. S. Brown, Richardson-Lucy deblurring for scenes under a projective motion path, IEEE T. Pattern Anal., 33 (2011), 1603–1618.
  • 11. H. L. Yang, P. H. Huang and S. H. Lai, A novel gradient attenuation Richardson-lucy algorithm for image motion deblurring, Signal Process., 103 (2014), 399–414.
  • 12. M. Welk, P. Raudaschl, T. Schwarzbauer, et al., Fast and robust linear motion deblurring, Signal Image Video P., 9 (2015), 1221–1234.
  • 13. M. Dobeˇs, L. Machala and T. F¨urst, Blurred image restoration:A fast method of finding the motion length and angle, Digit. Signal Process., 20 (2010), 1677–1686.
  • 14. G. Liu, S. Chang and Y. Ma, Blind image deblurring using spectralproperties of convolution operators, IEEE T. Image Process., 23 (2014), 5047–5056.
  • 15. T. Yue, S. Cho, J. Wang, et al., Hybrid image deblurring by fusing edge and power spectrum information, Process of European Conference on Computer Vision, (2014).
  • 16. A. M. Deshpande and S. Patnaik, Single image motion deblurring: An accurate PSF estimation and ringing reduction, Optik, 125 (2014), 3612–3618.
  • 17. W. A. Shao, Q. Ge, H. S. Deng, et al., Motion deblurring using non-stationary image modeling, J. Math. Imaging Vis., 52 (2015), 234–248.
  • 18. N. He, K. Lu, B. K. Bao, et al., Single-image motion deblurring using an adaptive image prior, Inform. Science, 281 (2015), 736–749.
  • 19. J. Jia, Single image motion deblurring using transparency, Process of IEEE Conference on Computer Vision and Pattern Recognition, (2007), 1–7.
  • 20. A. Levin, Y. Weiss, F. Durand, et al., Understanding and evaluating blind deconvolution algorithms, Process of IEEE Conference on Computer Vision and Pattern Recognition, (2009), 1964– 1971.
  • 21. A. Levin, Y. Weiss, F. Durand, et al., Understanding blind deconvolution algorithms, IEEE T. Pattern Anal., 33 (2011), 2354–2367.
  • 22. L. Xu, S. Zheng and J. Jia, Unnatural L0 sparse representation for natural image deblurring, Process of IEEE Conference on Computer Vision and Pattern Recognition, (2013).
  • 23. T. S. Cho, C. Paris, B. K. P. Horn, et al., Blur kernel estimation using the Radon transform, Process of IEEE Conference on Computer Vision and Pattern Recognition, (2011), 241–248.
  • 24. D. Krishnan, T. Tay and R. Fergus, Blind deconvolution using a normalized sparsity measure, Process of IEEE Conference on Computer Vision and Pattern Recognition, (2011), 223–240.
  • 25. M. Ljubenovi´c and M. A. T. Figueiredo, Blind image deblurring using class-adapted image priors, Process of IEEE Conference on Image Processing, (2017), 490–494.
  • 26. J. Pan, D. Sun, H. Pfister, et al., Deblurring images via dark channel prior, IEEE T. Pattern Anal., 10 (2018), 2315–2328.
  • 27. D. J. Field, Relations between the statistics of natural images and the response properties of cortical cells, J. Opt. Soc. Am. A, 4 (1987), 2379–2394.
  • 28. G. J. Burton and I. R. Moorhead, Color and spatial structure in natural scenes, Appl. Optics, 26 (1987), 157–170.
  • 29. L. Cohen, The generalizaton of the Wiener-Khinchin theorem, IEEE Signal Proc. Let., 5 (1998), 292–294.
  • 30. J. R. Fienup, Phase retreival algorithms: A comparsion, Appl. Opt., 21 (1982), 2758–2769.
  • 31. S. Watanabe, H. Shioya and K. Gohara, Phase retrieval based on an evolution multicriterion optimisation method, Process of IEEE Conference on Evolutionary Computation, (2012), 1–8.
  • 32. Z. Wang, A. C. Bovik, H. R. Sheikh, et al., Image quality assessment: from error visibility to structural similarity, Process of IEEE Conference on Image Processing, 13 (2004), 600–612.
  • 33. M. Sonka, V. Hlavac and Roger Boyle, Image processing, Analysis, and Machine Vision, 3rd Ed., Thomson Learning Pub., 2008.
  • 34. D. Krishnan and R. Fergus, Fast image deconvolution using hyper-Laplacian priors, Proc. Conf. NIPS, (2009), 1033–1041.

 

Reader Comments

your name: *   your email: *  

© 2019 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution Licese (http://creativecommons.org/licenses/by/4.0)

Download full text in PDF

Export Citation

Copyright © AIMS Press All Rights Reserved