Deep Learning Approach for Image Denoising and Image Demosaicing

Prakash, V. N. V. Satya; Prasad, K. Satya; Prasad, T. Jayachandra

doi:10.5120/ijca2017914500

Cited by 9 publications

(3 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…G represents a spatial Gaussian kernel given by (32). The above criterion value becomes small if the residuals are small and smooth.…”

Section: Step 2: Adaptive Selection Of Iteration Numbermentioning

confidence: 99%

“…Besides the local interpolation based algorithms mentioned above, many more sophisticated techniques have been introduced: the "non-local" algorithms based on the grouping of similar patches [26,6,7,42,10,11], wavelet-based algorithms [25,2,40], dictionary learning based algorithms [17,4,26]. Finally the recent deep learning methods [14,34,32,33,23] work very well for natural images.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Mathematical Analysis and Implementation of Residual Interpolation Demosaicking Algorithms

Jin¹,

Guo²,

Morel³

et al. 2021

Image Processing on Line

View full text Add to dashboard Cite

Demosaicking is the process of reconstructing the full color image from its mosaic version on a Bayer pattern. It is an integral part of the image processing pipeline for single sensor digital color cameras. Demosaicking algorithms based on residual interpolation are interesting because they produce competitive results with a low computational complexity. In this article, we provide an analysis and careful implementation of the most relevant residual based demosaicking algorithms. Our contribution is twofold. First, we present an analysis of the mathematical principles of demosaicking algorithms from the Hamilton-Adams interpolation to the recent "adaptive residual interpolation". Our analysis untangles the relations of these algorithms and how each is improving on the preceding ones. Lastly, we provide a comparison between most recent state of the art methods on several image data sets and discuss their performances.

show abstract

“…G represents a spatial Gaussian kernel given by (32). The above criterion value becomes small if the residuals are small and smooth.…”

Section: Step 2: Adaptive Selection Of Iteration Numbermentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Mathematical Analysis and Implementation of Residual Interpolation Demosaicking Algorithms

Jin¹,

Guo²,

Morel³

et al. 2021

Image Processing on Line

View full text Add to dashboard Cite

show abstract

“…In that case, we also need more efforts to supplement the missing information during the SR process. Deep learning with powerful image processing ability has been applied to many tasks like image denoising, demosaicing [37] and reconstruction [38]. Zhang et al [29] designed a deep convolutional neural network (CNN) for image Gaussian denoising, which is called DnCNN.…”

Section: Super-resolution Frameworkmentioning

confidence: 99%

Infrared Image Super Resolution by Combining Compressive Sensing and Deep Learning

Zhang

Meng

et al. 2018

Sensors

View full text Add to dashboard Cite

Super resolution methods alleviate the high cost and high difficulty in applying high resolution infrared image sensors. In this paper we present a novel single image super resolution method for infrared images by combining compressive sensing theory and deep learning. Low resolution images can be regarded as the compressed sampling results of the high resolution ones in compressive sensing. With sparsity in this theory, higher resolution images can be reconstructed. However, because of diverse level of sparsity for different images, the output contains noise and loss of high frequency information. Deep convolutional neural network provides a solution to relieve the noise and supplement some missing high frequency information. By concatenating two methods, we manage to produce better results in super resolution tasks for infrared images than SRCNN and ScSR. PSNR and SSIM values are used to quantify the performance. Applying our method to open datasets and actual infrared imaging experiments, we also find better visual results are preserved.

show abstract

Multi-scale dilated dense reconstruction network for limited-angle computed tomography

et al. 2023

View full text Add to dashboard Cite

Objective. Due to the incomplete projection data, the image reconstructed by limited-angle computed tomography (CT) usually suffers from significant artifacts, by which the structural details are heavily blurred. In this study, we aim to develop a novel approach to improve the limited-angle CT reconstruction performance, especially for the narrow scanning angular range. Approach. A deep learning (DL) based iterative framework for limited-angle tomography is proposed, which is named multi-scale dilated dense reconstruction network (MSDDRNet). The MSDDRNet utilizes a multi-scale dilated dense convolution neural network (MSDD-CNN) with conventional reconstruction algorithm for predicting image from incomplete projection data. The MSDD-CNN enhances the image features in the network by merging the DenseNet-Like structure, which serves to restore invisible singularities and reduce artifacts, as well as introducing constraints on the projection domain data into the iterative process to achieve better image detail recovery. Additionally, to improve the training speed of the network, we use a strategy of pre-training and model migration. Main results. Numerical experiments demonstrate that the proposed MSDDRNet performs well in terms of artifact correction, noise reduction and structure recovery compared to existing methods with limited scan angles, and we also extend the proposed method to more general scanning condition and other application such as dental CT data. Significance. The proposed method is a general framework, which can be applied to other CT problems, such as low dose CT, sparse-data CT and spectral CT.

show abstract

Deep Learning Approach for Image Denoising and Image Demosaicing

Cited by 9 publications

References 36 publications

A Mathematical Analysis and Implementation of Residual Interpolation Demosaicking Algorithms

A Mathematical Analysis and Implementation of Residual Interpolation Demosaicking Algorithms

Infrared Image Super Resolution by Combining Compressive Sensing and Deep Learning

Multi-scale dilated dense reconstruction network for limited-angle computed tomography

Contact Info

Product

Resources

About