Variational PDE based image restoration using neural network

Wu, Yue; Sun, Yu; Zhang, H.-y.; Sun, Shixin

doi:10.1049/iet-ipr:20050383

Cited by 13 publications

(18 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the success of the total variation (TV) in deconvolution [16][17][18][19][20] motivated its incorporation in the MLP. By means of matrix algebra and the approximation of the TV operator with the majorization-minimization (MM) algorithm of [19], we presented a newer version of the MLP [10] for both l 1 and l 2 regularizers and mainly devoted to compare the truncation model with the traditional BCs.…”

Section: Contributionmentioning

confidence: 99%

See 1 more Smart Citation

Boundary reconstruction process of a TV-based neural net without prior conditions

Santiago

Cisneros

Bernués

2011

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

Image restoration aims to restore an image within a given domain from a blurred and noisy acquisition. However, the convolution operator, which models the degradation, is truncated in a real observation causing significant artifacts in the restored results. Typically, some assumptions are made about the boundary conditions (BCs) outside the field of view to reduce the ringing. We propose instead a restoration method without prior conditions which reconstructs the boundary region as well as making the ringing artifact negligible. The algorithm of this article is based on a multilayer perceptron (MLP) which minimizes a truncated version of the total variation regularizer using a back-propagation strategy. Various experiments demonstrate the novelty of the MLP in the boundary restoration process without neither any image information nor prior assumption on the BCs.

show abstract

Section: Contributionmentioning

confidence: 99%

“…In fact, the Hopfield network has been used in the literature to solve the optimization problem (9) and recent studies provide neural network solutions to the TV regularization (10) as in [16,17]. In this article, we present a simple solution to solve the TV-based solution by means of an MLP with back-propagation.…”

Section: Problem Formulationmentioning

confidence: 99%

Boundary reconstruction process of a TV-based neural net without prior conditions

Santiago

Cisneros

Bernués

2011

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

show abstract

“…It is also a block Toeplitz matrix that can be generated by a regular operator. In the traditional image restoration model, this operator is a Laplace operator, which can be approximated as a window operator [1][2][3][4] , i.e.,…”

Section: Problem Formulationmentioning

confidence: 99%

“…In our previous papers [1,2] , we have proposed an image restoration algorithm based on the Harmonic model using neural network. Experimental results demonstrated that the proposed algorithm is more efficient than the conventional Paik's algorithm [3] in terms of restoration quality.…”

Section: Introductionmentioning

confidence: 99%

“…Experimental results demonstrated that the proposed algorithm is more efficient than the conventional Paik's algorithm [3] in terms of restoration quality. However, the computational complexity of the sequential algorithm proposed in [1,2] is O(nxL), where n represents the iteration number and L is the pixel number of an image. By utilizing the parallel ability of neural network, in this paper, we develop a parallel restoration algorithm based on Harmonic model.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A parallel image restoration algorithm based on Harmonic model using neural networks

Zhang

Sun

et al. 2010

2010 3rd IEEE International Conference on Ubi-Media Computing

View full text Add to dashboard Cite

In our previous work [1, 2J, an image restoration algorithm based on modified Hopfield neural network and harmonic model was proposed. But the computational complexity of the algorithm is high. In this paper, a parallel image restoration algorithm based on the Harmonic model using modified Hopfield neural network (MHNN) is de veloped. The proposed algorithm makes fu ll use of the parallel computation performance of neural network and effectively reduces the computational complexity from O(n x L) to O(n). Numerous experimental results de monstrate that the proposed restoration algorithm outperforms the traditional restoration algorithm in terms of computational complexity.

show abstract