Content may be subject to copyright.

# Comparison of the proposed approach on the same test images with Deep Learning approaches and blur kernels

Source publication
Article
Full-text available
The paper focuses on the Enhanced Augmented Lagrangian method with sparse regularization for image deblurring. The method suggested by ALTERNATING LOW RANK AUGMENTED LAGRANGIAN WITH ITERATIVE A PRIOR is novel in the following ways. (i) Faster convergence leading to speeder execution through rank regulations (ii) using derivatives and low rank toget...

## Context in source publication

Context 1
... various current prior-based deblurring approaches also deep learning-based deblurring methods, the planned algorithm is checked for performance and efficiency. Table 1 show that our method outperformed Deep learning-based deblurring algorithms in terms of PSNR and SSIM values. ...

## Similar publications

Preprint
Full-text available
In this note we demonstrate provable convergence of SGD to the global minima of appropriately regularized $\ell_2-$empirical risk of depth $2$ nets -- for arbitrary data and with any number of gates, if they are using adequately smooth and bounded activations like sigmoid and tanh. We build on the results in [1] and leverage a constant amount of Fr...
Article
Full-text available
The initial‐boundary value problem for the heat equation on x>0,t>0$$\left\{x>0,t>0\right\}$$ with nonzero Dirichlet boundary data is studied rigorously, with emphasis on the behavior of the solution along the boundary of the spatiotemporal domain, that is, in the limits x→0+$$x\to {0}^{+}$$ or t→0+$$t\to {0}^{+}$$, including the case (x,t)→(...
Article
Full-text available
In this paper, we study consensus behavior based on the local application of the majority consensus algorithm (a generalization of the majority rule) over four-connected bi-dimensional networks. In this context, we characterize theoretically every four-vicinity network in its capacity to reach consensus (every individual at the same opinion) for an...
Article
Full-text available
In this paper, some new algorithms based on the iteratively reweighted least squares (IRLS) method are proposed for sparse recovery problem. There are two important parameters in the IRLS method: a weighted parameter and a regularization parameter. On the one hand, in order to improve the performance of IRLS method, a new way is given to update the...
Conference Paper
Full-text available
The study was undertaken for three years during 2010-11 to 2012-13 on 15 years old mango trees of Pairi variety at Main Garden, Department of Horticulture, Dr. Panjabrao Deshmukh Krishi Vidyapeeth, Akola for induction of regular bahar in mango. The treatments were consisted of Cycocel-2500, 5000, 7500 ppm, KNO 3-0.5 %, 1.0 %, 1.5 %, Ethrel-200 ppm,...