scholarly journals Adaptive Block-Based Approach to Image Noise Level Estimation in the SVD Domain

Electronics ◽  
2018 ◽  
Vol 7 (12) ◽  
pp. 397 ◽  
Author(s):  
Emir Turajlic
Keyword(s):  
Noise Level ◽  
Additive White Gaussian Noise ◽  
Block Size ◽  
Tail Length ◽  
Low Noise ◽  
Singular Value ◽  
Computational Time ◽  
Noise Levels ◽  
Noise Level Estimation ◽  
Block Based

Estimation of additive white Gaussian noise levels in images has a variety of image processing applications including image enhancement, segmentation and feature extraction. Designing an algorithm with a consistent performance across a range of noise levels and image contents is a challenging problem; without any prior information, it is difficult to differentiate the noise signal from the underlying image signal. In this paper, an adaptive block-based noise level estimation algorithm in the singular value decomposition domain is proposed. The algorithm has the ability to change the singular value tail length according to the observed noise levels. A number of different choices of block size are considered and, for each choice, a mathematical model is proposed to describe how to adjust the singular value tail length as a function of the initial noise level estimates. In comparison with a seminal fixed singular value tail length algorithm, the proposed algorithm significantly improves the noise level estimation accuracy at low noise levels at the expense of a small increase in computational time; for example, for the block size of 64 × 64 and AWGN level σ = 1 , the MSE is reduced by 65%, whilst the computational time is increased by less than 1.3%.

scholarly journals Application of Artificial Neural Network for Image Noise Level Estimation in the SVD domain

Electronics ◽  
2019 ◽  
Vol 8 (2) ◽  
pp. 163 ◽  
Author(s):  
Emir Turajlic ◽  
Alen Begović ◽  
Namir Škaljo
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Noise Level ◽  
Low Noise ◽  
Singular Value ◽  
Fine Tuning ◽  
Noise Levels ◽  
Noise Level Estimation ◽  
Artificial Neural ◽  
Block Based

The blind additive white Gaussian noise level estimation is an important and a challenging area of digital image processing with numerous applications including image denoising and image segmentation. In this paper, a novel block-based noise level estimation algorithm is proposed. The algorithm relies on the artificial neural network to perform a complex image patch analysis in the singular value decomposition (SVD) domain and to evaluate noise level estimates. The algorithm exhibits the capacity to adjust the effective singular value tail length with respect to the observed noise levels. The results of comparative analysis show that the proposed ANN-based algorithm outperforms the alternative single stage block-based noise level estimating algorithm in the SVD domain in terms of mean square error (MSE) and average error for all considered choices of block size. The most significant improvements in MSE levels are obtained at low noise levels. For some test images, such as “Car” and “Girlface”, at σ = 1 , these improvements can be as high as 99% and 98.5%, respectively. In addition, the proposed algorithm eliminates the error-prone manual parameter fine-tuning and automates the entire noise level estimation process.

scholarly journals Analysis of Skid Resistance and Noise Characteristics for Varieties of Concrete Pavement

2020 ◽  
Vol 2020 ◽  
pp. 1-8
Author(s):  
Jinmiao Fang ◽  
Jinsong Tu ◽  
Kunming Wu
Keyword(s):  
Noise Level ◽  
Evaluation Criteria ◽  
Sound Intensity ◽  
Low Noise ◽  
Concrete Pavement ◽  
Skid Resistance ◽  
Concrete Pavements ◽  
Noise Levels ◽  
Cement Concrete ◽  
Noise Characteristics

To establish evaluation criteria for the pavement skid resistance and noise level in tunnels pavements, the zoning and control standards for skid resistance and concrete pavement noise were examined. Transverse friction coefficient (TFC) test equipment and the on-board sound intensity (OBSI) method were used to evaluate the antisliding characteristics and noise levels of several tunnel pavements. The results indicated poor antisliding characteristics and noise levels in ordinary grooved cement concrete pavement, whereas new types of cement concrete pavements, such as exposed concrete pavements and polymer-modified cement concrete pavements, had good antisliding characteristics and achieved low noise levels. Combined with the cluster analysis method, a zoning method for the antisliding and noise level in concrete pavement is proposed. The antisliding characteristics and noise levels of the pavement are divided into three zones. To ensure safety and comfort during driving, the antisliding value (SFC) of the tunnel pavement should be more than 50, and the noise level should not exceed 105 dB. Finally, the correlation between the antisliding and noise levels for pavement was analyzed. The results indicated that the antiskiding value of pavement has a strong correlation to the noise level.

Paper 16: A Study of Tractor Noise Control

1969 ◽  
Vol 184 (17) ◽  
pp. 149-169
Author(s):  
J. Matthews ◽  
J. D. C. Talamo
Keyword(s):  
Hearing Loss ◽  
Diesel Engine ◽  
Noise Reduction ◽  
Noise Level ◽  
Exhaust System ◽  
Low Noise ◽  
Acoustic Features ◽  
Noise Levels ◽  
Engine Design ◽  
High Incidence

A high incidence of hearing loss has been encountered among tractor drivers, and noise levels are shown to be further increased by the addition of cabs, particularly those which are structurally strong to resist crushing if the vehicle overturns. Some reductions in the noise level of the operator's environment can be obtained by covering the engine or by exhaust system modifications, while possible future improvements to diesel engine design may effect a significant improvement. However, it is proposed that noise reduction is likely to be achieved by attention to acoustic features of the operator's cab. The inclusion of resilient mounts, substantial floors and bulkheads, and acoustically absorbent linings are all shown to provide worthwhile improvements and, in combination, these measures can reduce noise levels from more than 100 dBA to 90 dBA or less. Where the tractor is fitted with a safety frame only, a low noise fabric cladding is shown to be feasible.

scholarly journals A Filter for SAR Image Despeckling Using Pre-Trained Convolutional Neural Network Model

2019 ◽  
Vol 11 (20) ◽  
pp. 2379 ◽  
Author(s):  
Ting Pan ◽  
Dong Peng ◽  
Wen Yang ◽  
Heng-Chao Li
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Noise Level ◽  
Multiplicative Noise ◽  
Single Channel ◽  
State Of The Art ◽  
Additive White Gaussian Noise ◽  
Training Data ◽  
Noise Levels ◽  
Sar Images

Despeckling is a longstanding topic in synthetic aperture radar (SAR) images. Recently, many convolutional neural network (CNN) based methods have been proposed and shown state-of-the-art performance for SAR despeckling problem. However, these CNN based methods always need many training data or can only deal with specific noise level. To solve these problems, we directly embed an efficient CNN pre-trained model for additive white Gaussian noise (AWGN) with Multi-channel Logarithm with Gaussian denoising (MuLoG) algorithm to deal with the multiplicative noise in SAR images. This flexible pre-trained CNN model takes the noise level as input, thus only a single pre-trained model is needed to deal with different noise levels. We also use a detector to find the homogeneous region automatically to estimate the noise level of image as input. Embedded with MuLoG, our proposed filter can despeckle not only single channel but also multi-channel SAR images. Finally, both simulated and real (Pol)SAR images were tested in experiments, and the results show that the proposed method has better and more robust performance than others.

Sign in / Sign up

Export Citation Format

Share Document