Welcome to Francis Academic Press

Academic Journal of Computing & Information Science, 2022, 5(6); doi: 10.25236/AJCIS.2022.050606.

Improved image noise level estimation based on segmentation and block processing


Liwei Han

Corresponding Author:
Liwei Han

School of Electronic and Information Engineering, Anhui University, Hefei, Anhui, 230000, China


Accurate estimation of noise parameters in digital images is of great significance to improve the quality of image processing. Principal component analysis is an important means of image denoising, and the traditional method is to estimate the whole image. Due to the complexity of image content, this paper proposes a preprocessing method based on superpixel segmentation to process the largest possible smooth block in the image. Compared with contrast method, the estimated value of the proposed method is closer to the true value.


Image noise estimation, Superpixel segmentation, Principal component analysis (PCA)

Cite This Paper

Liwei Han. Improved image noise level estimation based on segmentation and block processing. Academic Journal of Computing & Information Science (2022), Vol. 5, Issue 6: 31-36. https://doi.org/10.25236/AJCIS.2022.050606.


[1] Deng D. Research and application of image denoising algorithm for salt and pepper noise. Changsha: Hunan University, 2018.

[2] Chen Z, Hu Z. Remote sensing image denoising with improved wavelet threshold algorithm. Bulletin of Surveying and Mapping, 2018(4): 28-31.

[3] Ren X, Malik J. Learning a classifification model for segmentation. Ninth IEEE International Conference on IEEE, 2003, 1: 10 -17.

[4] Long J, Chen H, Yan Z, Zhu J. Superpixel segmentation algorithm based on local fuzzy clustering. Journal of Chongqing University of Technology (Natural Science), 2021, 35(11): 116-125.

[5] Pyatykh S, Hesser J, Zheng L. Image noise level estimation by principal component analysis. IEEE Trans Image Process, 2013, 22(2):687–699.

[6] Zoran, D., Weiss, Y. Scale invariance and noise in natural images. Proc.IEEE Int. Conf. on Computer Vision, Kyoto, Japan, September 2009, pp. 2209–2216.