A novel natural image noise level estimation based on flat patches and local statistics
- 27 Downloads
This paper proposes a high-precision algorithm for noise level estimation. Different from existing algorithms, we present a new noise level estimation algorithm by linearly combining the overestimated and underestimated results using combinatorial coefficients that can be tailored to the problem at hand. The algorithm has two distinct features: it avoids the underestimation of noise level estimation algorithms that employ the minimum eigenvalue and demonstrates higher accuracy and robustness for a large range of visual content and noise conditions. The experimental results that are obtained in this study demonstrate that the proposed algorithm is effective for various scenes with various noise levels. The software release of the proposed algorithm is available online at https://ww2.mathworks.cn/matlabcentral/fileexchange/64519-natural-image-noise-level-estimation-based-on-flat-patches-and-local-statistics.
KeywordsNoise level estimation Flat patches Gaussian noise Eigenvalue Covariance matrix
This study was supported by the National Natural Science Foundation of China (Grant no. 11671307, 61561019, 61763009 and 11761030), the Nature Science Foundation of Hubei Province (Grant no. 2015CFB262), and the Doctoral Scientific Fund Project of Hubei University for Nationalities (Grant no. MY2015B001). We would like to express our gratitude to the anonymous reviewers and editors for their valuable comments and suggestions, which led to the improvement of the original manuscript.
- 4.Callet PL, Autrusseau F (2005) Subjective quality assessment irccyn/ivc database. http://www.irccyn.ec-nantes.fr/ivcdb/
- 5.Chen G, Zhu F, Heng PA (2015) An efficient statistical method for image noise level estimation. In: 2015 I.E. international conference on computer vision (ICCV), pp 477–485Google Scholar
- 6.Colom M, Lebrun M, Buades A, Morel JM (2015) A non-parametric approach for the estimation of intensity-frequency dependent noise. In: 2015 IEEE international conference on image processing, pp 4261–4265Google Scholar
- 12.Ghazi MM, Erdogan H (2016) Image noise level estimation based on higher-order statistics. Multimed Tools Appl 76(2):1–19Google Scholar
- 23.Ponomarenko P, Lukin V, Zelensky A, Egiazarian K, Carli M, Battisti F (2009) Tid2008-a database for evaluation of full-reference visual quality assessment metrics. Adv Modern Radioelectron 10(4):30–45Google Scholar
- 25.Royston JP (1982) Algorithm as 177: Expected normal order statistics (exact and approximate). J R Stat Soc 31(2):161–165Google Scholar
- 27.Sheikh HR, Sabir MF, Bovik AC (2005) Live image quality assessment database release2. http://live.ece.utexas.edu/research/quality. Accessed 3 May 2017
- 34.Zoran D, Weiss Y (2009) Scale invariance and noise in natural images. In: 2009 I.E. international conference on computer vision (ICCV), pp 2209–2216Google Scholar