Results 171 to 180 of about 3,041 (214)
IEEE Transactions on Image Processing, 2021 This work considers noise removal from images, focusing on the well known K-SVD denoising algorithm. This sparsity-based method was proposed in 2006, and for a short while it was considered as state-of-the-art. However, over the years it has been surpassed by other methods, including the recent deep-learning-based newcomers.
Meyer Scetbon, Michael Elad
exaly +4 more sources
Some of the next articles are maybe not open access.
Related searches:
Related searches:
K-SVD Meets Transform Learning: Transform K-SVD
IEEE Signal Processing Letters, 2014Recently there has been increasing attention directed towards the analysis sparsity models. Consequently, there is a quest for learning the operators which would enable analysis sparse representations for signals in hand. Analysis operator learning algorithms such as the Analysis K-SVD have been proposed.
Ender M Ekşioğlu
exaly +2 more sources
IEEE Signal Processing Letters, 2017
The problem of dictionary learning (DL) for sparse representations can be approximately solved by several algorithms. Regularization of the optimization objective (representation error) was proved useful, since it avoids possible bottlenecks due to nearly linearly dependent atoms.
Bogdan Dumitrescu, Paul Irofti
openaire +1 more source
The problem of dictionary learning (DL) for sparse representations can be approximately solved by several algorithms. Regularization of the optimization objective (representation error) was proved useful, since it avoids possible bottlenecks due to nearly linearly dependent atoms.
Bogdan Dumitrescu, Paul Irofti
openaire +1 more source
2013 IEEE International Conference on Acoustics, Speech and Signal Processing, 2013
Dictionary learning algorithms design a dictionary that is specifically tailored to enable sparse representation of a given set of training signals. In turn, the increased sparsity of the signals with respect to this dictionary enables significantly improved performance in a variety of state-of-the-art signal processing tasks, e.g. compressive sensing.
Farhad Pourkamali-Anaraki +1 more
openaire +1 more source
Dictionary learning algorithms design a dictionary that is specifically tailored to enable sparse representation of a given set of training signals. In turn, the increased sparsity of the signals with respect to this dictionary enables significantly improved performance in a variety of state-of-the-art signal processing tasks, e.g. compressive sensing.
Farhad Pourkamali-Anaraki +1 more
openaire +1 more source
Information filtering using the Riemannian SVD (R-SVD)
1998The Riemannian SVD (or R-SVD) is a recent nonlinear generalization of the SVD which has been used for specific applications in systems and control. This decomposition can be modified and used to formulate a filtering-based implementation of Latent Semantic Indexing (LSI) for conceptual information retrieval.
Eric P. Jiang, Michael W. Berry
openaire +1 more source
A general framework for SVD flows and joint SVD flows
2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)., 2003The paper presents a general framework for the development of continuous algorithms for SVD and joint SVD problems. The framework for SVD is derived based on gradient flows on unitary groups. Two previous examples of SVD flows discovered heuristically are derived systematically using the framework.
openaire +1 more source
A Systolic Array for SVD Updating
SIAM Journal on Matrix Analysis and Applications, 1993A singular value decomposition (SVD) updating algorithm supplemented with a certain re-orthogonalization scheme is implemented on a systolic array with \(O(n^ 2)\) parallelism for \(O(n^ 2)\) complexity, by combining systolic implementations for the matrix-vector product, the QR updating and the SVD. It is shown that a main computational bottleneck for
Marc Moonen +2 more
openaire +1 more source
ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019
Pairwise, or separable, dictionaries are suited for the sparse representation of 2D signals in their original form, without vectorization. They are equivalent with enforcing a Kronecker structure on a standard dictionary for 1D signals. We present a dictionary learning algorithm, in the coordinate descent style of Approximate K-SVD, for such ...
Paul Irofti, Bogdan Dumitrescu
openaire +1 more source
Pairwise, or separable, dictionaries are suited for the sparse representation of 2D signals in their original form, without vectorization. They are equivalent with enforcing a Kronecker structure on a standard dictionary for 1D signals. We present a dictionary learning algorithm, in the coordinate descent style of Approximate K-SVD, for such ...
Paul Irofti, Bogdan Dumitrescu
openaire +1 more source
2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, 2011
Noise is an important concern in high-angular resolution diffusion imaging studies because it can lead to errors in downstream analyses of white matter structure. To address this issue, we investigate a new approach for denoising diffusion-weighted data sets based on the K-SVD algorithm.
Vishal Patel +3 more
openaire +1 more source
Noise is an important concern in high-angular resolution diffusion imaging studies because it can lead to errors in downstream analyses of white matter structure. To address this issue, we investigate a new approach for denoising diffusion-weighted data sets based on the K-SVD algorithm.
Vishal Patel +3 more
openaire +1 more source
Bisection and twisted SVD on GPU
2015 IEEE High Performance Extreme Computing Conference (HPEC), 2015Singular value decomposition (SVD) is one of the most important factorizations in matrix computation. However, computing SVD is still time-consuming, especially when the dimension of matrices exceeds tens of thousands. In this paper, we present a high performance approach called “Bisection and Twisted” (BT) for solving bidiagonal SVD. As modern general
Lu He +6 more
openaire +1 more source