DOI: 10.17586/1023-5086-2020-87-05-63-76

Directional smoothing model-based image denoising algorithm

Zhao, Xiaoming, Bai, Yashuo, Liu, Xin, Gao Miao, Cheng Kun, Ma Shengcun, Dong Lei

Publication in Journal of Optical Technology

For Russian citation (Opticheskii Zhurnal):

Zhao Xiaoming, Bai Yashuo, Liu Xin, Gao Miao, Cheng Kun, Ma Shengcun , Dong Lei. Алгоритм снижения шумов изображения на основе сглаживания, использующего ориентированные модели // Оптический журнал. 2020. Т. 87. № 5. С. 63–76. http://doi.org/10.17586/1023-5086-2020-87-05-63-76

Zhao Xiaoming, Bai Yashuo, Liu Xin, Gao Miao, Cheng Kun, Ma Shengcun , Dong Lei. Directional smoothing model-based image denoising algorithm [in Russian] // Opticheskii Zhurnal. 2020. V. 87. № 5. P. 63–76. http://doi.org/10.17586/1023-5086-2020-87-05-63-76

For citation (Journal of Optical Technology):

X. Zhao, Y. Bai, X. Liu, M. Gao, K. Cheng, S. Ma, and L. Dong, "Directional-smoothing-model-based image denoising algorithm," Journal of Optical Technology . 87(5), 299-309 (2020). https://doi.org/10.1364/JOT.87.000299

Abstract:

This study focuses on edge preservation and noise smoothing in the process of denoising. To achieve the two aims, the image has to be processed in such a way that the noise is removed to give people a pleasing vision without reducing the perceptibility of edges and details. In the proposed algorithm, edge orientations are taken into account by using directional templates during edge extraction. The results of convolution would be adopted to control coefficients of the corresponding denoising filter. These two steps play a leading role to guarantee the preservation of edges. Finally, flat regions distinguished from edges and details by local standard deviation would be further operated by incorporating the preliminary filtering result and mean filtering result to make better vision perception. Its great performance with lower complexity is validated by the experiential results, which provides an important opportunity for hardware implementation.

Keywords:

reduction of image noise, selection of boundaries, preservation of sharpness, Gaussian filtering

OCIS codes: 100.2000

References:

1. Lindenbaum M., Fischer M., Bruckstein A. On Gabor's contribution to image enhancement // Pattern Recognition. 1994. V. 27. № 1. P. 1–8.

2. Tomasi C., Manduchi R. Bilateral filtering for gray and color images // IEEE Sixth Internat. Conf. Computer Vision. 1998. № 98CH. P. 839–846.

3. Durand F., Dorsey J. Fast bilateral filtering for the display of high-dynamic-range images // ACM TOG. 2002. V. 21. № 3. P. 257–266.

4. Bae S., Paris S., Durand F. Two-scale tone management for photographic look // ACM TOG. 2006. V. 25. № 3. P. 637–645.

5. Buades A., Coll B., Morel J.M. A non-local algorithm for image denoising // IEEE Computer Soc. Conf. Computer Vision. 2005. V. 2. № 7. P. 60–65.

6. Zhang F., Cai N., Wu J., et al. Image denoising method based on a deep convolution neural network // IET Image Proc. 2018. V. 12. № 4. P. 485–493.

7. Coifman R.R., Donoho D.L. Translation-invariant de-noising // Wavelets & Statistics. 1995. V. 103. № 2. P. 125–150.

8. Donoho D.L. De-noising by soft-thresholding // IEEE Trans. Information Theory. 2018. V. 41. № 3. P. 613–627.

9. Donoho D.L., Johnstone I.M. Adapting to unknown smoothness via wavelet shrinkage // J. American Statistical Association. 1995. V. 90. № 432. P. 1200–1224.

10. Chang S.G., Yu B., Vetterli M. Adaptive wavelet thresholding for image denoising and com-pression // IEEE Trans. Image Proc. 2000. V. 9. № 9. P. 1532–1546.

11. Chipman H.A., Kolaczyk E.D., McCulloch R.E. Adaptive Bayesian wavelet shrinkage // J. American Statistical Association. 1997. V. 92. № 440. P. 1413–1421.

12. Moulin P., Liu J. Analysis of multiresolution image denoising schemes using generalized Gaussian and complexity priors // IEEE Trans. Information Theory. 1999. V. 45. № 3. P. 909–919.

13. Romberg J.K., Choi H., Baraniuk R.G. Bayesian tree-structured image modeling using wavelet-domain hidden Markov models // EEE Trans. Image Proc. 2001. V. 10. № 7. P. 1056–1068.

14. Dabov K., Katkovnik V., Foi A., et al. Image denoising by sparse 3D transformation-domain collaborative filtering // IEEE Internat. Conf. Image Proc. 2007. V. 16. № 7. P. 1–16.

15. Jain V., Seung H.S. Natural image denoising with convolutional networks // Internat. Conf. Neural Information Proc. Systems. 2008. P. 769–776.

16. Burger H.C., Schuler C.J., Harmeling S. Image denoising: Can plain neural networks compete with BM3D? // Computer Vision and Pattern Recognition. 2012. V. 157. № 10. P. 2392–2399.

17. Wang X., Wang L., Tao Q., et al. Deep convolutional architecture for natural image denoising // Internat. Conf. Wireless Communications & Signal Proc. 2015. V. 5. № 53. P. 1–4.

18. Koziarski M., Cyganek B. Deep neural image denoising // Internat. Conf. Computer Vision and Graphics. 2016. P. 163–173.

19. Lefkimmiatis S. Non-local color image denoising with convolutional neural networks // IEEE Conf. Computer Vision and Pattern Recognition. 2017. P. 5882–5891.

20. Zhang F., CaiN., Wu J., et al. Image denoising method based on a deep convolution neural network // IET Image Proc. 2018. V. 12. № 4. P. 485–493.

21. Wang Z., Bovik A.C., Sheikh H.R., and Simoncell E.P. Image quality assessment: From error visibility to structural similarity // IEEE Trans. 2004. V. 13. № 4. P. 600–612.

22. Xue W., Zhang L., Mou X., Bovik A. Gradient magnitude similarity deviation: A highly efficient perceptual image quality index // IEEE Trans. Image Proc. 2014. V. 23. № 2. P. 684–695. 23. Barrett H.H. Objective assessment of image quality: Effects of quantum noise and object variability // JOSA. 1990. V. 7. № 7. P. 1266–1278.