Quaternion Quasi-Chebyshev Non-local Means for Color Image Denoising

XU Xudong; ZHANG Zhihua; M. James C. Crabbe

doi:10.23919/cje.2022.00.138

Volume 32 Issue 3

May 2023

Turn off MathJax

Article Contents

Article Navigation > Chinese Journal of Electronics > 2023 > 32(3): 397-414

XU Xudong, ZHANG Zhihua, M. James C. Crabbe, “Quaternion Quasi-Chebyshev Non-local Means for Color Image Denoising,” Chinese Journal of Electronics, vol. 32, no. 3, pp. 397-414, 2023, doi: 10.23919/cje.2022.00.138

Citation:

XU Xudong, ZHANG Zhihua, M. James C. Crabbe, “Quaternion Quasi-Chebyshev Non-local Means for Color Image Denoising,” Chinese Journal of Electronics, vol. 32, no. 3, pp. 397-414, 2023, doi: 10.23919/cje.2022.00.138

Citation:

PDF( 10927 KB)

Quaternion Quasi-Chebyshev Non-local Means for Color Image Denoising

doi: 10.23919/cje.2022.00.138

1.
School of Mathematics, Shandong University, Jinan 250100, China
2.
Wolfson College, University of Oxford, Oxford OX1 2JD, UK

Funds: This work was supported by European Commission Horizon 2020’s Flagship Project (861584) and Taishan Distinguished Professor Fund.

More Information

Author Bio:
Xudong XU was born in 1995. She received the B.S. degree from Beijing University of Technology and Industry, China, and M.S. degree from University of Science and Technology Beijing, China. She is currently a Ph.D. student in the School of Mathematics at Shandong University, China. Her research interests include image processing and remote sensing image classification. (Email: 202120281@sdu.edu.cn)

Zhihua ZHANG (corresponding author) is a Taishan Distinguished Professor of Big Data in School of Mathematics, Shandong University, Jinan, China. He has published 6 first-authored monographs and over 50 first-authored articles. Prof. Zhang is an Associate Editor of EURASIP Journal on Advances in Signal Processing. (Email: zhangzhihua@sdu.edu.cn)

M. James C. Crabbe is a Professor and Fellow at Oxford University, Oxford, UK and a Visiting Professor at the University of Reading, UK. He was on the Executive Committee of the UK Deans of Science and was elected a Distinguished Fellow of the Institute of Data Science and Artificial Intelligence. (Email: james.crabbe@wolfson.ox.ac.uk)
Received Date: 2022-03-17
Accepted Date: 2023-01-07

Available Online: 2023-02-23

Publish Date: 2023-05-05

Abstract

Abstract

Quaternion non-local means (QNLM) denoising algorithm makes full use of high degree self-similarities inside images to suppress the noise, so the similarity metric plays a key role in its denoising performance. In this study, two improvements have been made for the QNLM: 1) For low level noise, the use of quaternion quasi-Chebyshev distance is proposed to measure the similarity of image patches and it has been used to replace the Euclidean distance in the QNLM algorithm. Since the quasi-Chebyshev distance measures the maximal distance in all color channels, the similarity of color images measured by quasi-Chebyshev distance can capture the structural similarity uniformly for each color channel; 2) For high level noise, quaternion bilateral filtering has been proposed as the preprocessing step in the QNLM algorithm. Denoising simulations were performed on 110 images of landscape, people, and architecture at different noise levels. Compared with QNLM, quaternion non-local total variation (QNLTV), and non-local means (NLM) variants (NLTV, NLM after wavelet threshold preprocessing, and the color adaptation of NLM), our novel algorithm not only improved PSNR/SSIM (peak signal to noise rate/structural similarity) and figure of merit values by an average of 2.77 dB/8.96% and 0.0491 respectively, but also reduced processing time.
- Color image denoising,
- Quaternion quasi-Chebyshev non-local means,
- Quaternion bilateral filter,
- Quaternion non-local means

https://github.com/sepidsh/Image_denoising_NLM

https://github.com/Tinrry/BOS_NLTV_v1

https://github.com/xavirema/nlmc

https://github.com/helderc/WaveletTransformShrinkThreshold

https://sourceforge.net/projects/qtfm/

FullText(HTML)

References(34)

References

[1]	J. B. Martens and L. Meesters, “Image dissimilarity,” Signal Processing, vol.70, no.3, pp.155–176, 1998. doi: 10.1016/S0165-1684(98)00123-6
[2]	T. Huang, G. Yang, and G. Tang, “A fast two-dimensional median filtering algorithm,” IEEE Transactions on Acoustics, Speech, and Signal Processing, vol.27, no.1, pp.13–18, 1979. doi: 10.1109/TASSP.1979.1163188
[3]	Y. Ephraim and D. Malah, “Speech enhancement using a minimum-mean square error short-time spectral amplitude estimator,” IEEE Transactions on Acoustics, Speech, and Signal Processing, vol.32, no.6, pp.1109–1121, 1984. doi: 10.1109/TASSP.1984.1164453
[4]	J. S. Goldstein, I. S. Reed, and L. L. Scharf, “A multistage representation of the Wiener filter based on orthogonal projections,” IEEE Transactions on Information Theory, vol.44, no.7, pp.2943–2959, 1998. doi: 10.1109/18.737524
[5]	K. Ito and K. Xiong, “Gaussian filters for nonlinear filtering problems,” IEEE Transactions on Automatic Control, vol.45, no.5, pp.910–927, 2000. doi: 10.1109/9.855552
[6]	C. Tomasi and R. Manduchi, “Bilateral filtering for gray and color images,” in Proceedings of the 6th International Conference on Computer Vision, Bombay, India, pp.839–846, 2002.
[7]	A. Buades, B. Coil, and J. M. Morel, “A review of image denoising algorithms, with a new one,” Multiscale Modeling & Simulation, vol.4, no.2, pp.490–530, 2005. doi: 10.1137/040616024
[8]	G. Gilboa and S. Osher, “Nonlocal evolutions for image regularization,” in Proceedings of SPIE 6498, Computational Imaging V, San Jose, United States, pp.64980U, 2007.
[9]	B. Goossens, H. Luong, J. Aelterman, et al., “A GPU-accelerated real-time NLMeans algorithm for denoising color video sequences,” in Proceedings of the 12th International Conference on Advanced Concepts for Intelligent Vision Systems, Sydney, Australia, pp.46–57, 2010.
[10]	A. Khmag, S. A. R. Al Haddad, R. A. Ramlee, et al., “Natural image noise removal using nonlocal means and hidden Markov models in transform domain,” The Visual Computer, vol.34, no.12, pp.1661–1675, 2018. doi: 10.1007/s00371-017-1439-9
[11]	M. Diwakar and M. Kumar, “CT image denoising using NLM and correlation-based wavelet packet thresholding,” IET Image Processing, vol.12, no.5, pp.708–715, 2018. doi: 10.1049/iet-ipr.2017.0639
[12]	K. N. Plataniotis and A. N. Venetsanopoulos, Color Image Processing and Applications. Springer, Berlin, Heidelberg, 2000.
[13]	H. Y. Yang, Y. Zhang, P. Wang, et al., “A geometric correction based robust color image watermarking scheme using quaternion exponent moments,” Optik, vol.125, no.16, pp.4456–4469, 2014. doi: 10.1016/j.ijleo.2014.02.028
[14]	X. Y. Wang, Z. F. Wu, L. Chen, et al., “Pixel classification based color image segmentation using quaternion exponent moments,” Neural Networks, vol.74, pp.1–13, 2016. doi: 10.1016/j.neunet.2015.10.012
[15]	C. J. Chen, Y. Xu, and X. K. Yang, “User tailored colorization using automatic scribbles and hierarchical features,” Digital Signal Processing, vol.87, pp.155–165, 2019. doi: 10.1016/j.dsp.2019.01.021
[16]	Ö. N. Subakan and B. C. Vemuri, “A quaternion framework for color image smoothing and segmentation,” International Journal of Computer Vision, vol.91, no.3, pp.233–250, 2011. doi: 10.1007/s11263-010-0388-9
[17]	B. J. Chen, H. Z. Shu, H. Zhang, et al., “Quaternion Zernike moments and their invariants for color image analysis and object recognition,” Signal Processing, vol.92, no.2, pp.308–318, 2012. doi: 10.1016/j.sigpro.2011.07.018
[18]	A. Buades, B. Coil, and J. M. Morel, “Non-local means denoising,” Image Processing on Line, vol.1, pp.208–212, 2011. doi: 10.5201/ipol.2011.bcm_nlm
[19]	A. Buades, B. Coll, and J. M. Morel, “Image processing on line: nonlocal means denoising,” Available at: http://www.ipol.im/pub/algo/bcm non local means denoising/, 2022.
[20]	Q. Li, J. F. Teng, Q. M. Zhao, et al., “Wavelet domain wiener filter and its application in signal denoising,” in Proceedings of the 3rd International Conference on Wavelet Analysis and Its Applications (WAA), Chongqing, China, pp.839–846, 2003.
[21]	F. Z. Zhang, “Quaternions and matrices of quaternions,” Linear Algebra and Its Applications, vol.251, pp.21–57, 1997. doi: 10.1016/0024-3795(95)00543-9
[22]	B. J. Chen, Q. S. Liu, X. M. Sun, et al., “Removing Gaussian noise for colour images by quaternion representation and optimisation of weights in non-local means filter,” IET Image Processing, vol.8, no.10, pp.591–600, 2014. doi: 10.1049/iet-ipr.2013.0521
[23]	G. H. Wang, L. Yang, X. Wei, et al., “An improved non-local means filter for color image denoising,” Optik, vol.173, pp.157–173, 2018. doi: 10.1016/j.ijleo.2018.08.013
[24]	Z. G. Jia, Q. Y. Jin, M. K. Ng, et al., “Non-local robust quaternion matrix completion for large-scale color image and video inpainting,” IEEE Transactions on Image Processing, vol.31, pp.3868–3883, 2022. doi: 10.1109/TIP.2022.3176133
[25]	X. Y. Li, Y. C. Zhou, and J. Zhang, “Quaternion non-local total variation for color image denoising,” in Proceedings of 2019 IEEE International Conference on Systems, Man and Cybernetics, Bari, Italy, pp.1602–1607, 2019.
[26]	R. Franzen, “Kodak lossless true color image suite,” Available at: http://r0k.us/graphics/kodak, 1999.
[27]	S. Roth and M. J. Black, “Fields of experts: A framework for learning image priors,” in Proceedings of 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Diego, CA, USA, pp.860–867, 2005.
[28]	L. Zhang, X. L. Wu, A. Buades, et al., “Color demosaicking by local directional interpolation and nonlocal adaptive thresholding,” Journal of Electronic Imaging, vol.20, no.2, article no.023016, 2011. doi: 10.1117/1.3600632
[29]	Z. Wang and A. C. Bovik, “A universal image quality index,” IEEE Signal Processing Letters, vol.9, no.3, pp.81–84, 2002. doi: 10.1109/97.995823
[30]	B. Magnier, “Edge detection evaluation: A new normalized figure of merit,” in Proceedings of 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK, pp.2407–2411, 2019.
[31]	A. Khmag, “Additive Gaussian noise removal based on generative adversarial network model and semi-soft thresholding approach,” Multimedia Tools and Applications, vol.82, no.5, pp.7757–7777, 2023. doi: 10.1007/s11042-022-13569-6
[32]	Y. Peng, “Quantitative method based on cotangent similarity degree in three-valued Łukasiewicz logic,” Chinese Journal of Electronics, vol.30, no.1, pp.134–144, 2021. doi: 10.1049/cje.2020.11.011
[33]	Y. F. Li, Q. J. Zhao, W. B. Zhang, et al., “A simultaneous cartoon-texture image segmentation and image decomposition method,” Chinese Journal of Electronics, vol.29, no.5, pp.906–915, 2020. doi: 10.1049/cje.2020.08.006
[34]	M. Li and C. Xu, “Variational image restoration and decomposition in shearlet smoothness spaces,” Chinese Journal of Electronics, vol.26, no.5, pp.1017–1021, 2017. doi: 10.1049/cje.2017.08.021