Additive White Gaussian Noise Level Estimation for Natural Images Using Linear Scale-Space Features

Noise in images is often modelled with additive white Gaussian noise (AWGN). An accurate estimation of noise level without any prior knowledge of noisy input image leads to effective blind image denoising methods. The performance of certain image denoising methods under AWGN model is dependent on the accuracy of noise level estimation (NLE). Hence, there is a need to develop an effective NLE method in order to achieve better performance in image denoising. Even though the existing NLE methods perform well on natural images, these methods involve complex segmentation tasks such as homogeneous regions extraction and super-pixel decomposition. Hence, a simple, fast, and accurate NLE method for AWGN is proposed in this paper. In the presented NLE method, the statistical features of high-frequency details of noisy input image are obtained at multiple linear (Gaussian) scale-space which are used to construct a feature vector. It is perceived that the features obtained are almost linear and separable. Hence, supervised linear regression (LR) models that are trained globally and locally are suggested for NLE. The proposed method estimates the noise level in two stages. In stage-1, a globally trained LR model is used to estimate the noise level. It is observed that the accuracy of the noise level obtained through stage-1 can be further improved in stage-2 by adopting the proposed locally trained LR model. The proposed NLE method is evaluated with artificially generated noisy natural images using AWGN model. The high-quality natural images from Waterloo and BSD500 datasets are selected using image quality selection module and then used in training and testing phases. The average absolute deviation (AAD) is evaluated from each selected image in the datasets over a wide range of noise levels ([0 100]). The average AAD for selected images in Waterloo (BSD500) dataset is 0.21 (0.18), and execution time required to estimate the noise level is 0.04 s per image. From the obtained results, it is clear that the proposed method is simple, fast, and accurate as compared to several existing NLE methods. The effectiveness of the proposed NLE method is illustrated with fast and flexible denoising convolutional neural network using standard test images at randomly selected noise levels.

[1]  Shaoping Xu,et al.  A Two-Stage Noise Level Estimation Using Automatic Feature Extraction and Mapping Model , 2019, IEEE Signal Processing Letters.

[2]  Jiang Ping,et al.  No-reference Image Quality Assessment Based on Local Maximum Gradient , 2015 .

[3]  Xuelong Li,et al.  Lazy Random Walks for Superpixel Segmentation , 2014, IEEE Transactions on Image Processing.

[4]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[5]  Xiang Zhu,et al.  A no-reference sharpness metric sensitive to blur and noise , 2009, 2009 International Workshop on Quality of Multimedia Experience.

[6]  David Dagan Feng,et al.  Image noise level estimation based on a new adaptive superpixel classification , 2014, 2014 IEEE International Conference on Image Processing (ICIP).

[7]  Xinhao Liu,et al.  Single-Image Noise Level Estimation for Blind Denoising , 2013, IEEE Transactions on Image Processing.

[8]  Youlun Xiong,et al.  Impulse Noise Removal Using Directional Difference Based Noise Detector and Adaptive Weighted Mean Filter , 2009, IEEE Signal Processing Letters.

[9]  Fan Zhang,et al.  Brief review of image denoising techniques , 2019, Visual Computing for Industry, Biomedicine, and Art.

[10]  Herng-Hua Chang,et al.  Superpixel-based image noise variance estimation with local statistical assessment , 2015, EURASIP J. Image Video Process..

[11]  Shaoping Xu,et al.  A Multiple Image-Based Noise Level Estimation Algorithm , 2017, IEEE Signal Processing Letters.

[12]  Lei Zhang,et al.  FFDNet: Toward a Fast and Flexible Solution for CNN-Based Image Denoising , 2017, IEEE Transactions on Image Processing.

[13]  Lei Zheng,et al.  Image Noise Level Estimation by Principal Component Analysis , 2013, IEEE Transactions on Image Processing.

[14]  D. R. K. Brownrigg,et al.  The weighted median filter , 1984, CACM.

[15]  John Immerkær,et al.  Fast Noise Variance Estimation , 1996, Comput. Vis. Image Underst..

[16]  Mohadeseh Mazhari,et al.  Suppression of noise in SEM images using weighted local hysteresis smoothing filter. , 2016, Scanning.

[17]  Bernard Fertil,et al.  Head detection based on skeleton graph method for counting people in crowded environments , 2016, J. Electronic Imaging.

[18]  Giuseppe Messina,et al.  Fast method for noise level estimation and integrated noise reduction , 2005, IEEE Transactions on Consumer Electronics.

[19]  Jean-Michel Morel,et al.  A Review of Image Denoising Algorithms, with a New One , 2005, Multiscale Model. Simul..

[20]  Sunil Agrawal,et al.  Image denoising review: From classical to state-of-the-art approaches , 2020, Inf. Fusion.

[21]  Stefan Harmeling,et al.  Image denoising: Can plain neural networks compete with BM3D? , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[22]  Syed Abdul Rahman Al-Haddad,et al.  Natural image noise removal using nonlocal means and hidden Markov models in transform domain , 2017, The Visual Computer.

[23]  Reza P. R. Hasanzadeh,et al.  A novel image noise reduction technique based on hysteresis processing , 2015 .

[24]  Kang Ryoung Park,et al.  Real-Time Image Restoration for Iris Recognition Systems , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[25]  James S. Walker,et al.  Combined Image Compressor and Denoiser based on Tree-adapted Wavelet Shrinkage , 2002 .

[26]  Ram M. Narayanan,et al.  Noise estimation in remote sensing imagery using data masking , 2003 .

[27]  Lingyan Hu,et al.  Quality-aware features-based noise level estimator for block matching and three-dimensional filtering algorithm , 2016, J. Electronic Imaging.

[28]  Chee-Onn Chow,et al.  Detection of Gaussian noise and its level using deep convolutional neural network , 2017, TENCON 2017 - 2017 IEEE Region 10 Conference.

[29]  Zhiming Wang,et al.  Image Noise Level Estimation by Neural Networks , 2015 .

[30]  R. Unbehauen,et al.  Estimation of image noise variance , 1999 .

[31]  Lei Zhang,et al.  Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising , 2016, IEEE Transactions on Image Processing.

[32]  Lei Zhang,et al.  Waterloo Exploration Database: New Challenges for Image Quality Assessment Models , 2017, IEEE Transactions on Image Processing.

[33]  Martin Vetterli,et al.  Adaptive wavelet thresholding for image denoising and compression , 2000, IEEE Trans. Image Process..

[34]  Jean-Michel Morel,et al.  A non-local algorithm for image denoising , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[35]  Min-Cheol Hong,et al.  Filtering-Based Noise Estimation for Denoising the Image Degraded by Gaussian Noise , 2011, PSIVT.

[36]  Reza P. R. Hasanzadeh,et al.  Fuzzy Hysteresis Smoothing: A New Approach for Image Denoising , 2021, IEEE Transactions on Fuzzy Systems.

[37]  Meisam Rakhshanfar,et al.  Estimation of Gaussian, Poissonian–Gaussian, and Processed Visual Noise and Its Level Function , 2016, IEEE Transactions on Image Processing.

[38]  W. B. Collis,et al.  Training Methods for Image Noise Level Estimation on Wavelet Components , 2004, EURASIP J. Adv. Signal Process..

[39]  Alessandro Foi,et al.  Image Denoising by Sparse 3-D Transform-Domain Collaborative Filtering , 2007, IEEE Transactions on Image Processing.

[40]  Sumohana S. Channappayya,et al.  Blind image quality evaluation using perception based features , 2015, 2015 Twenty First National Conference on Communications (NCC).

[41]  N. Ichise,et al.  Practical method for noise removal in scanning electron microscopy , 2006 .

[42]  Seungjoon Yang,et al.  Block-based noise estimation using adaptive Gaussian filtering , 2005, 2005 Digest of Technical Papers. International Conference on Consumer Electronics, 2005. ICCE..

[43]  Gwanggil Jeon,et al.  Noise Level Estimation for Image Processing , 2012, ICHIT.

[44]  Roberto Manduchi,et al.  Bilateral filtering for gray and color images , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[45]  Kede Ma,et al.  Waterloo Exploration Database: New Challenges for Image Quality Assessment Models. , 2017, IEEE transactions on image processing : a publication of the IEEE Signal Processing Society.

[46]  L. Rudin,et al.  Nonlinear total variation based noise removal algorithms , 1992 .

[47]  Yuan Yan Tang,et al.  Noise Level Estimation for Natural Images Based on Scale-Invariant Kurtosis and Piecewise Stationarity. , 2017, IEEE transactions on image processing : a publication of the IEEE Signal Processing Society.

[48]  Jung-Hua Wang,et al.  Improved median filter using minmax algorithm for image processing , 1997 .

[49]  I. Johnstone,et al.  Ideal spatial adaptation by wavelet shrinkage , 1994 .

[50]  J. Woods,et al.  Estimation and identification of two-dimensional images , 1983 .

[51]  Armando Manduca,et al.  Adaptive nonlocal means filtering based on local noise level for CT denoising. , 2013, Medical physics.

[52]  Alan C. Bovik,et al.  Making a “Completely Blind” Image Quality Analyzer , 2013, IEEE Signal Processing Letters.

[53]  Richard Szeliski,et al.  Automatic Estimation and Removal of Noise from a Single Image , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[54]  Guangyong Chen,et al.  An Efficient Statistical Method for Image Noise Level Estimation , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[55]  Abd. Rahman Ramli,et al.  Natural image noise level estimation based on local statistics for blind noise reduction , 2018, The Visual Computer.

[56]  R. Ehrich.  A symmetric hysteresis smoothing algorithm that preserves principal features , 1978 .

[57]  Søren I. Olsen,et al.  Estimation of Noise in Images: An Evaluation , 1993, CVGIP Graph. Model. Image Process..

[58]  Xinhao Liu,et al.  Noise level estimation using weak textured patches of a single noisy image , 2012, 2012 19th IEEE International Conference on Image Processing.

[59]  Jitendra Malik,et al.  Scale-Space and Edge Detection Using Anisotropic Diffusion , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[60]  Quan-Sen Sun,et al.  A spatially cohesive superpixel model for image noise level estimation , 2017, Neurocomputing.

[61]  S. Goodman,et al.  Statistical tests, P values, confidence intervals, and power: a guide to misinterpretations , 2016, European Journal of Epidemiology.

[62]  Rafael C. González,et al.  Digital image processing using MATLAB , 2006 .

[63]  Priyanka Kokil,et al.  Computer-aided diagnosis of cataract using deep transfer learning , 2019, Biomed. Signal Process. Control..

[64]  William Puech,et al.  Digital image restoration by Wiener filter in 2D case , 2007, Adv. Eng. Softw..

[65]  Xinhao Liu,et al.  Practical Signal-Dependent Noise Parameter Estimation From a Single Noisy Image , 2014, IEEE Transactions on Image Processing.

[66]  Ning He,et al.  Image Denoising Based on the Wavelet Semi-soft Threshold and Total Variation , 2017, 2017 International Conference on Vision, Image and Signal Processing (ICVISP).

[67]  Michael H. Kutner.  Applied Linear Statistical Models , 1974 .

[68]  Charless C. Fowlkes,et al.  Contour Detection and Hierarchical Image Segmentation , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[69]  Li Dong,et al.  Noise Level Estimation for Natural Images Based on Scale-Invariant Kurtosis and Piecewise Stationarity , 2017, IEEE Transactions on Image Processing.

[70]  Shen-Chuan Tai,et al.  Fast and reliable image-noise estimation using a hybrid approach , 2010, J. Electronic Imaging.

[71]  Andrew P. Witkin,et al.  Uniqueness of the Gaussian Kernel for Scale-Space Filtering , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[72]  Frédéric Truchetet,et al.  Noise Estimation From Digital Step-Model Signal , 2013, IEEE Transactions on Image Processing.

[73]  H. Sebastian Seung,et al.  Natural Image Denoising with Convolutional Networks , 2008, NIPS.

[74]  J. Woods,et al.  Estimation and identification of two dimensional images , 1981, 1981 20th IEEE Conference on Decision and Control including the Symposium on Adaptive Processes.