Color image denoising using a hybrid algorithm based on singular spectrum analysis and principal component analysis methods

Document Type : Original Scientific Paper

Authors

Department of Statistics‎, ‎University of Payame Noor‎, ‎Tehran‎, ‎Iran

Abstract

In this paper, a hybrid algorithm based on singular spectrum analysis and principal component analysis is proposed for denoising color images. The main novelty of this approach lies in the simultaneous utilization of singular spectrum analysis's capability to separate signal and noise in the time-series domain, along with principal component analysis's ability to remove correlations among the red, green, and blue channels of color images. To validate the effectiveness of the proposed method, peak signal-to-noise ratio and structural similarity index are employed on reference images that are contaminated with random noise at different levels. The experimental results indicate that the proposed algorithm achieves superior performance, particularly at higher noise levels. Specifically, the results demonstrate higher peak signal-to-noise ratio and structural similarity values when compared with principal component analysis-based bootstrapping methods and eigenvalue-based denoising approaches.

Keywords

Main Subjects

References

 
Buades, A., Coll, B. and Morel, J.M. (2005). A non-local algorithm for image denoising. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2:60–65.
Chen, R., Pu, D., Tong, Y. and Wu, M. (2022). Image-denoising algorithm based on improved K-singular value decomposition and atom optimization. CAAI Transactions on Intelligence Technology, 7(1):117–127.
Dabov, K., Foi, A., Katkovnik, V. and Egiazarian, K. (2007). Image denoising by sparse 3-D transform-domain collaborative filtering. IEEE Transactions on Image Processing, 16(8):2080–2095.
Donoho, D.L. and Gavish, M. (2014). The optimal hard threshold for singular values is $4/\sqrt{3}$. IEEE Transactions on Information Theory, 60(8):5040–5053.
Ghasemi, R. (2023). Improving the stability of color image denoising using eigenvector analysis and weighted averaging. Quarterly Journal of Software Engineering and Intelligent Systems, 11(4):22–35.
Ghasemi, R. and Safariyan, A. (2024). Optimal denoising of color images by combining singular-vector analysis and weighted bootstrap sampling. Third Seminar on Data Science and Its Applications, Ferdowsi University of Mashhad, 1–9.
Ghasemi, R. and Yousefinejad, M. (2025). An efficient fuzzy filter for impulsive noise reduction in color images. Journal of Soft Computing and Information Technology, 14(1):27–36.
Ghasemi, R., Morillas, S., Nezakati, A. and Rabiei, M. (2022). Image noise reduction by means of bootstrapping-based fuzzy numbers. Applied Sciences, 12(19):9445.
Golyandina, N. and Korobeynikov, A. (2014). Basic singular spectrum analysis and forecasting with R. Computational Statistics & Data Analysis, 71:934–954.
Golyandina, N., Korobeynikov, A. and Zhigljavsky, A. (2018). Singular Spectrum Analysis with R. Berlin, Heidelberg: Springer Berlin Heidelberg.
Golyandina, N., Nekrutkin, V. and Zhigljavsky, A. (2001). Analysis of Time Series Structure: SSA and Related Techniques. Chapman & Hall/CRC.
Horé, A. and Ziou, D. (2010). Image quality metrics: PSNR vs. SSIM. 20th International Conference on Pattern Recognition, 2366–2369.
Latorre-Carmona, P., Miñana, J.J. and Morillas, S. (2020). Colour image denoising by eigenvector analysis of neighbourhood colour samples. Signal, Image and Video Processing, 14(3):483–490.
Li, H. and Wu, D. (2025). Hybrid-Domain Synergistic Transformer for Hyperspectral Image Denoising. Applied Sciences, 15(17):9735.
Mafi, M., Martin, H., Cabrerizo, M., Andrian, J., Barreto, A. and Adjouadi, M. (2019). A comprehensive survey on impulse and Gaussian denoising filters for digital images. Signal Processing, 157:236–260.
Momot, A., Spodarev, E. and Zhigljavsky, A. (2005). Bayesian weighted averaging for image denoising. Mathematical Methods in Applied Sciences, 28(14):1761–1776.
Monagi, H.A. and El-Sakka, M.R. (2017). Patch-based models and algorithms for image denoising: a comparative review between patch-based images denoising methods for additive noise reduction. EURASIP Journal on Image and Video Processing, 2017(1):1–22.
Moreno López, M., Frederick, J.M. and Ventura, J. (2021). Evaluation of MRI denoising methods using unsupervised learning. Frontiers in Artificial Intelligence, 4:642731.
Peng, J., Shi, C., Laugeman, E., Hu, W., Zhang, Z., Mutic, S. and Cai, B. (2020). Implementation of the structural similarity (SSIM) index as a quantitative evaluation tool for dose distribution error detection. Medical Physics, 47(4):1907–1919.
Rodríguez-Aragon, L. and Zhigljavsky, A. (2010). Singular spectrum analysis for image processing. Statistics and Its Interface, 3(3):419–426.
Saeedi-Zarandi, M. (2021). A comprehensive review of digital image denoising methods in the transform domain using statistical models and their comparison. Iranian Journal of Electrical and Computer Engineering, 18(1):55–70.
Shakeri, M., Hosseini, S. and Nouri, M. (2019). Noise reduction in cone-beam CT images using independent component analysis. Iranian Journal of Medical Imaging, 10(2):33–45.
Wang, M., Wang, S., Ju, X. and Wang, Y. (2023). Image denoising method relying on iterative adaptive weight-mean filtering. Symmetry, 15(6):1181.
Yang, M., Wang, H., Hu, K., Yin, G. and Wei, Z. (2022). IA-Net: An inception-attention-module-based network for classifying underwater images. IEEE Journal of Oceanic Engineering, 47(3):704–717.
Zhang, Y., Ding, H., Wang, K. and Li, P. (2023). Hyperspectral image classification based on super pixel-based spatial-spectral PCA fusion, 1D-2D spectral analysis, and random patch network. Remote Sensing, 15(5):1234.
Zou, Y., Yan, C. and Fu, Y. (2023). Iterative denoiser and noise estimator for self-supervised image denoising. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 13265–13274.
Journal of Statistical Modelling: Theory and Applications
Volume 6, Issue 1
January 2025
Pages 115-131

Files

History

  • Receive Date: 22 September 2025
  • Revise Date: 02 December 2025
  • Accept Date: 27 December 2026

Share

How to cite

Statistics