Exponential linear unit dilated residual network for digital image denoising

2018 ◽  
Vol 27 (05) ◽  
pp. 1
Author(s):  
Aditi Panda ◽  
Ruchira Naskar ◽  
Snehanshu Pal
Keyword(s):  
Image Denoising ◽  
Digital Image ◽  
Residual Network

scholarly journals A well-posed multiscale regularization scheme for digital image denoising

2011 ◽  
Vol 21 (4) ◽  
pp. 769-777 ◽  
Author(s):  
V. Prasath
Keyword(s):  
Image Denoising ◽  
Digital Image ◽  
Regularization Parameter ◽  
Input Image ◽  
Smooth Transition ◽  
Functions Of Bounded Variation ◽  
Edge Preserving ◽  
Regularization Scheme ◽  
Adaptive Parameter ◽  
Well Posed

A well-posed multiscale regularization scheme for digital image denoisingWe propose an edge adaptive digital image denoising and restoration scheme based on space dependent regularization. Traditional gradient based schemes use an edge map computed from gradients alone to drive the regularization. This may lead to the oversmoothing of the input image, and noise along edges can be amplified. To avoid these drawbacks, we make use of a multiscale descriptor given by a contextual edge detector obtained from local variances. Using a smooth transition from the computed edges, the proposed scheme removes noise in flat regions and preserves edges without oscillations. By incorporating a space dependent adaptive regularization parameter, image smoothing is driven along probable edges and not across them. The well-posedness of the corresponding minimization problem is proved in the space of functions of bounded variation. The corresponding gradient descent scheme is implemented and further numerical results illustrate the advantages of using the adaptive parameter in the regularization scheme. Compared with similar edge preserving regularization schemes, the proposed adaptive weight based scheme provides a better multiscale edge map, which in turn produces better restoration.

scholarly journals Denoising Algorithm Based on Generalized Fractional Integral Operator with Two Parameters

2012 ◽  
Vol 2012 ◽  
pp. 1-14 ◽  
Author(s):  
Hamid A. Jalab ◽  
Rabha W. Ibrahim
Keyword(s):  
Visual Perception ◽  
Integral Operator ◽  
Image Denoising ◽  
Digital Image ◽  
Fractional Integral ◽  
Fractional Integral Operator ◽  
Smoothing Filter ◽  
Generalized Fractional Integral ◽  
Two Parameters

In this paper, a novel digital image denoising algorithm called generalized fractional integral filter is introduced based on the generalized Srivastava-Owa fractional integral operator. The structures ofn×nfractional masks of this algorithm are constructed. The denoising performance is measured by employing experiments according to visual perception and PSNR values. The results demonstrate that apart from enhancing the quality of filtered image, the proposed algorithm also reserves the textures and edges present in the image. Experiments also prove that the improvements achieved are competent with the Gaussian smoothing filter.

scholarly journals Modified Perona-Malik Equation and Computer Simulation for Image Denoising

2014 ◽  
Vol 8 (1) ◽  
pp. 37-41
Author(s):  
Zheng Jian Feng ◽  
Huang Chengwei ◽  
Zhang Ji
Keyword(s):  
Differential Equation ◽  
Partial Differential Equation ◽  
Computer Simulation ◽  
Image Denoising ◽  
Digital Image ◽  
Gaussian Noise ◽  
Anisotropic Diffusion ◽  
Difficult Problem ◽  
Experimental Results ◽  
Proposed Model

The edges and textures of a digital image may be destroyed by traditional denoising methods, which is a difficult problem in image denoising. In this paper, anisotropic diffusion algorithm based on Partial differential equation is studied. First, image denoising algorithms based on Perona-Malik model are studied. Second, a modified Perona-Malik model is proposed. In the proposed model, the gradient statistic and edge thresholds are embedded into the Perona-Malik equation. Finally, the effects of this model and some other models are compared and analyzed. The experimental results show that the proposed modified Perona-Malik model outperforms the original Perona-Malik model in removing Gaussian noise, and the edges and textures of the image are well preserved.

scholarly journals A COMPARATIVE STUDY OF VARIOUS WAVELET APPROACHES USED IN IMAGE DENOISING

2021 ◽  
Vol 9 (1) ◽  
pp. 1061-1078
Author(s):  
Vijayaragahvan Veeramani, Laavanya Mohan
Keyword(s):  
Comparative Study ◽  
Image Denoising ◽  
Digital Image ◽  
Gaussian Noise ◽  
Environmental Changes ◽  
Vital Role ◽  
Visual Appearance ◽  
Fine Grain ◽  
Definitive Solution ◽  
Changes Over Time

The world is constantly changing, and vision helps the humans to understand the environmental changes over time. The changes can be seen by, capturing the images. Hence digital image plays a vital role in day to day life. During the process of acquisition of digital image, the qualities of digital pictures are degraded due to additive noise known as adaptive white Gaussian noise. Therefore, the major challenge of image denoising algorithm is to improve the visual appearance while preserving the other details of the image. For the last two decades, wavelet has become an elegant tool in image denoising techniques. Among all wavelet based denoising methods, wavelet thresholding became popular because, wavelet appropriately separates the noisy signal from the image. The wavelet separation leaves the coarse grain noise in approximation sub-band and fine grain noise in detail sub-bands. Therefore, in wavelet based thresholding methods noise in detail sub-bands are threshold and approximate sub-band noise are kept as such. Hence, the efficiency of all wavelet based shrinkage techniques depends on, the choice of threshold parameter, thresholding technique and how the noise in the approximation sub-bands are handled. This paper presents a brief comparative study of denoising techniques proposed in the research articles based on the above parameters for Gaussian noise reduction using various wavelets transform. With the help of these experiments, we are able to identify the strengths and weaknesses of these methods, as well as seek the way ahead towards a definitive solution to the long-standing problem of image denoising.  

scholarly journals A new unsupervised pseudo-siamese network with two filling strategies for image denoising and quality enhancement

2021 ◽  
Author(s):  
Chenxi Huang ◽  
Dan Hong ◽  
Chenhui Yang ◽  
Chunting Cai ◽  
Siyi Tao ◽  
...  
Keyword(s):  
Image Processing ◽  
Image Denoising ◽  
Digital Image ◽  
Qualitative Evaluation ◽  
Training Data ◽  
Siamese Network ◽  
Adjacent Pixel ◽  
Extensive Body ◽  
Digital Image Enhancement ◽  
Processing Techniques

AbstractDigital image noise may be introduced during acquisition, transmission, or processing and affects readability and image processing effectiveness. The accuracy of established image processing techniques, such as segmentation, recognition, and edge detection, is adversely impacted by noise. There exists an extensive body of work which focuses on circumventing such issues through digital image enhancement and noise reduction, but this work is limited by a number of constraints including the application of non-adaptive parameters, potential loss of edge detail information, and (with supervised approaches) a requirement for clean, labeled, training data. This paper, developed on the principle of Noise2Void, presents a new unsupervised learning approach incorporating a pseudo-siamese network. Our method enables image denoising without the need for clean images or paired noise images, instead requiring only noise images. Two independent branches of the network utilize different filling strategies, namely zero filling and adjacent pixel filling. Then, the network employs a loss function to improve the similarity of the results in the two branches. We also modify the Efficient Channel Attention module to extract more diverse features and improve performance on the basis of global average pooling. Experimental results show that compared with traditional methods, the pseudo-siamese network has a greater improvement on the ADNI dataset in terms of quantitative and qualitative evaluation. Our method therefore has practical utility in cases where clean images are difficult to obtain.

Sign in / Sign up

Export Citation Format

Share Document