COMPRESSED SENSING MRI WITH BAYESIAN DICTIONARY LEARNING.
|
|
- Mervyn Carpenter
- 6 years ago
- Views:
Transcription
1 COMPRESSED SENSING MRI WITH BAYESIAN DICTIONARY LEARNING Xinghao Ding 1, John Paisley 2, Yue Huang 1, Xianbo Chen 1, Feng Huang 3 and Xiao-ping Zhang 1,4 1 Department of Communications Engineering, Xiamen University, Fujian, China 2 Department of EECS, University of California, Berkeley, USA 3 Philips Research China, Shanghai, China 4 Department of Electrical and Computer Engineering, Ryerson University, Toronto, Canada dxh@xmu.edu.cn ABSTRACT We present an inversion algorithm for magnetic resonance images (MRI) that are highly undersampled in k-space. The proposed method incorporates spatial finite differences (total variation) and patch-wise sparsity through in situ dictionary learning. We use the beta-bernoulli process as a Bayesian prior for dictionary learning, which adaptively infers the dictionary size, the sparsity of each patch and the noise parameters. In addition, we employ an efficient numerical algorithm based on the alternating direction method of multipliers (ADMM). We present empirical results on two MR images. Index Terms compressed sensing, MRI reconstruction, dictionary learning, Bayesian models 1. INTRODUCTION Magnetic resonance (MR) imaging is a widely used technique for visualizing the anatomical structure and physiological functioning of the body. A limitation of MR imaging is its slow scan speed during data acquisition, which is a drawback especially in dynamic imaging applications. Recent advances in signal reconstruction from measurements sampled below the Nyquist rate, called compressed sensing [1, 2], have had a major impact on MRI imaging [3]. CS-MRI allows for significant undersampling in k-space, where each k-space measurement is a Fourier transform coefficient of the MR image. MRI reconstruction using undersampled k-space data is a case of an ill-posed inverse problem. However, compressed sensing (CS) theory has shown that it is possible to reconstruct a signal from significantly fewer measurements than mandated by traditional Nyquist sampling if the signal is sparse in a particular transform domain [1, 2]. CS-MRI reconstruction algorithms tend to fall into two categories: Those which enforce sparsity withing an imagelevel transform domain (e.g., [3] [7]), and those which en- This project is supported by NSFC (No.9003, ), the Natural Science Foundation of Fujian Province of China (NO: 12J05160), The National Key Technology R&D Program (12BAI07B06), the Fundamental Research Funds for the Central Universities (No.: ). force sparsity on a patch-level (e.g., [8] [11]). Most CS-MRI reconstruction algorithms belong to the first category. For example Sparse MRI [3], the leading study in CS-MRI, performs MR image reconstruction by enforcing sparsity in both the wavelet domain and the total variation (TV) of the reconstructed image. Algorithms with image-level sparsity constraints such as Sparse MRI typically employ off-the-shelf dictionaries, which can usually capture only one feature of the image. The second group of algorithms learn a sparse basis on image subregions called patches that is adapted to the image class of interest. One approach to adapted basis learning is dictionary learning. Recent studies in the image processing literature have shown that dictionary learning can find sparse representations of images on the patch-level [12] [13], [18]. These algorithms learn a patch-level basis (i.e., dictionary) by exploiting structural similarities between patches extracted from images within a class of interest (for example K-SVD [13]). Among these approaches, adaptive dictionary learning usually outperforms analytical dictionary approaches in denoising, super-resolution reconstruction, interpolation, inpainting, classification and other applications, since the adaptively learned dictionary suits the signals of interest [13] [15]. Dictionary learning has been applied to CS-MRI as a sparse basis for reconstruction (e.g., LOST [9] and DLMRI [10]). Results using this approach demonstrate a significant improvement when compared with previous CS-MRI methods. However, these methods still have restrictions in that the dictionary size, patch sparsity and noise levels must be preset. In addition, algorithms such as dictionary learning that are based on only local image sparsity do not take into account additional image-level constraints, such as total variation, which can improve reconstruction. In this paper, we address the issues discussed above by proposing a new inversion framework for CS-MRI. Our work makes two contributions: 1) We propose a combination of in situ dictionary learning and total variation as a sparsity constraint for the inverse CS-MRI problem. We use the alternating direction method of multipliers (ADMM) to derive an /13/$ IEEE 2319 ICIP 13
2 efficient optimization procedure [21]; 2) We use a Bayesian approach to dictionary learning based on the beta-bernoulli process [16] [18]. This approach has three advantages: (i) it can learn the size of the dictionary from the data, (ii) it can learn the sparsity pattern on a patch-by-patch level, (iii) it can adaptively learn regularization weights, which correspond to noise variance in the Bayesian framework. 2. COMPRESSED SENSING MRI WITH BPFA In this section, we briefly review the problem of CS-MRI. We then present our CS inversion approach that uses a Bayesian method for dictionary learning called beta process factor analysis (BPFA). Let x R N be a N N image in vectorized form. Let F u C u N, u < N, be the under-sampled Fourier encoding matrix and y = F u x be the sub-sampled set of k-space measurements. The goal is to estimate x from the small fraction of k-space measurements y. For dictionary learning, let R i be the ith patch extraction operator. The operator R i is a P N matrix of all zeros except for a one in each row that extracts a vectorized P P patch from the image, x i = R i x R P for i = 1,..., N. We represent the CS-MRI inversion problem as optimizing an unconstrained function of the form arg min x h(x) + λ 2 F ux y 2 2, (1) where F u x y 2 2 is a data fidelity term, λ > 0 is a regularization parameter and h(x) is a regularization function that controls desired properties of the image specifically, that the reconstruction is sparse in the selected domain. As our regularization scheme for CS-MRI inversion, we propose a combination of total variation and Bayesian dictionary learning. We write this optimization problem as arg min x,ϕ λ gh g (x) + h l (x) + λ 2 F ux y 2 2, (2) h g (x) := T V (x), h l (x) := i γ ε 2 R i x Dα i f(ϕ). For the patch-wise regularization function h l (x) we use BPFA as given in Algorithm 1 [16]-[18]. This is a Bayesian model for generating images from dictionaries that are sparsely used; the optimization problem is equivalently an inference problem in Bayesian terms. The parameters to be optimized for BPFA are contained in the set ϕ = {D, s, z, γ ε, π}, and are defined in Algorithm 1. The regularization term γ ε is a model variable that corresponds to an inverse variance parameter of the multivariate Gaussian likelihood. In (2), the function f can be expanded to include the negative log likelihood from Algorithm 1, which we omit here. This term acts as the sparse basis for the image and also aids in producing a denoised reconstruction [16]. Algorithm 1 Generating an image with BPFA 1. Construct a dictionary D = [d 1,..., d K ]: d k N(0, P 1 I P ), k = 1,..., K. 2. Draw a probability π k [0, 1] for each d k : π k Beta(a 0, b 0 ), k = 1,..., K. 3. Draw precision values γ ε Gamma(g 0, h 0 ) and γ s Gamma(e 0, f 0 ). 4. For the ith patch in x: (a) Draw the vector s i N(0, γs 1 I K ). (b) Draw the binary vector z ik Bernoulli(π k ). (c) Define α i = s i z i by an element-wise product. (d) Construct the patch R i x = Dα i + ε i with noise ε i N(0, γε 1 I P ). 5. Construct the image x as the average of all R i x that overlap on a given pixel. The regularization function h g (x) is the total variation of the image. This term encourages homogeneity within contiguous regions of the image, while still allowing for sharp jumps in pixel value at edges due to the underlying l 1 penalty. For the total variation penalty T V (x) we use the isotropic TV model []. To review, let ψ i be the 2 N difference operator for pixel i. Each row of ψ i contains a 1 centered on pixel i, and 1 on the pixel directly above (for the first row of ψ i ) or to the right (for the second row of ψ i ) of pixel i, and zeros elsewhere. Let Ψ = [ψ1 T,..., ψn T ]T be the resulting 2N N difference matrix for the entire image. The TV coefficients are β = Ψx R 2N, and the isotropic TV penalty is β2i β2 2i, where i ranges T V (x) = i ψ ix 2 = i over the pixels in the MR image. Several algorithms have been proposed for TV minimization, for example using Newton s method [22] or graph cuts [23]. Recently, a simple and efficient method based on the alternating direction method of multipliers (ADMM) [21], also called the split Bregman method, has been proposed [19] for TV denoising models. We adopt this approach in our optimization algorithm. 3. ALGORITHM We sketch an algorithm for finding a local optimal solution to the non-convex objective function given in (2). This involves a stochastic optimization (inference) portion for updating the BPFA parameters, and an ADMM algorithm for the total variation penalty. Our use of ADMM for total variation minimization follows []. Also, a general introduction to the ADMM algorithm is given in [21]. Recall from the discussion in Section 2 that the total variation part of the objective is T V (x) = λ g i ψ ix 2. We use the ADMM algorithm to split x from this TV penalty. We begin by defining the TV coefficients for the ith pixel as 23
3 β i := ψ i x and we insert β for ψ i x in the objective under the constraint that they are equal. For each β i, we introduce a vector of Lagrange multipliers η i. We then split β i from ψ i x by relaxing their equality via an augmented Lagrangian. This results in the objective function L(x, β, η, ϕ) = λ g i β i 2 + ηi T (ψ ix β i ) + ρ 2 ψ ix β i γ ε i 2 R i x Dα i f(ϕ) + λ 2 F ux y 2 2. (3) The first line is the ADMM expansion of the TV penalty, which contains a Lagrangian term plus a squared error term. From the ADMM theory, holding everything else fixed, this objective will have optimal values β i and x with β i = ψ ix, and so the equality constraints will be satisfied. As written in (3), optimizing this function can be split into three separate sub-problems: one for the TV penalty β i, one for BPFA ϕ = {D, s, z, γ ε, π} and one for the image reconstruction x. Following the discussion in [21], we simplify the ADMM part by defining u i = (1/ρ)η i and completing the square in the first line of (3). We then cycle through the following three sub-problems using the current values of all parameters: (P 1) β i = arg min β λ g β i 2 + ρ 2 ψ ix β i + u i 2 2, (P 2) ϕ = arg min ϕ i γ ε 2 R i x Dα i f(α i, D), (P 3) x ρ = arg min x i 2 ψ ix β i + u i γ ε i 2 R i x D α i λ 2 F ux y 2 2, u i = u i + ψ i x β i, i = 1,..., N. P 1 has a simple, globally optimal and closed form solution that can be found in, e.g., []. The update for u i follows from the general ADMM algorithm [, 21]. Since P 2 is non-convex, we cannot perform the desired minimization, and so an approximation is required. Furthermore, this problem requires iterating through several parameters. Our approach is to use stochastic optimization for problem P 2 by Gibbs sampling each variable in BPFA conditioned on current values for all other variables. A Gibbs sampling algorithm for this model can be found in [18]. P 3 is a least squares problem with a closed form solution. However, we observe that P 3 requires the inversion of a prohibitively large matrix as written. Instead, we work in the Fourier domain as done in [], which results in the inverted matrix being diagonal. We update each Fourier coefficient one-by-one, and then take to inverse transform to obtain x. 4. EXPERIMENTS We perform experiments using our CS-MRI inversion approach on two 6 6 MR images as shown in Figure 2b Fig. 1. Example masks for sub-sampling % of k-space. (left) Cartesian mask, (middle) random mask, (right) radial mask. The Cartesian mask is the most practical, followed by the radial mask. and 3b. We consider sub-sampling 10%, %, %, % and 35% of k-space. We also consider three sub-sampling masks: Cartesian, (pseudo) random and radial, which determine the sampling pattern in k-space. We show examples of these masks in Figure 1. We compare our algorithm (BPFA+TV) with three other algorithms: (i) BPFA without TV, (ii) FCSA [], (iii) SparseMRI [3]. For FCSA and SparseMRI we use the codes available from the authors websites, as well as their default parameterizations. To measure performance, we use the peak-signal-to-noise ratio (PSNR). In Figures 2 and 3 we show qualitative results from the algorithms. In Figure 2 we consider a shoulder scan with 35% sampling using a Cartesian mask. The inset shows a close-up of a region of the original image and reconstructions. For this example, BPFA+TV is smoother than FCSA, but has a better resolution than SparseMRI. We show similar results for the coronal image in Figure 3 using a random mask that samples % in k space. The results appear to again slightly favor BPFA+TV for this example. In Figure 4 we show PSNR results for all sampling percentages and masks. The performance for the BPFA models is the best for these problems. We also see that in general, adding a total variation term to the penalty improves the reconstruction while not significantly increasing the running time. We report that the model learned a dictionary from the images that captured the salient features in a sparse way. We also note that performance significantly improved as a result of adaptively learning BPFA-related parameters such as regularization weights, rather than fixing them in advance. 5. CONCLUSION We have presented an algorithm for CS-MRI inversion that uses total variation and Bayesian dictionary learning as sparsity constraints. We used the ADMM algorithm for efficient optimization of the total variation penalty and Bayesian model that learns the dictionary from the data during image reconstruction. Results on two MR images show that the proposed algorithm performs favorably compared with other available software for CS-MRI. 2321
4 (a) (b) (c) (d) (e) Fig. 2. Reconstruction of the shoulder image with a 35% sampling in k-space using Cartesian sampling: (a) sampling mask, (b) original image, (c) BPFA+TV, (d) FCSA, (e) SparseMRI. The inset shows a region in more detail. (a) (b) (c) (d) (e) Fig. 3. Reconstruction of the coronal image with a % sampling in k-space using random sampling: (a) sampling mask, (b) original image, (c) BPFA+TV, (d) FCSA, (e) SparseMRI. The inset shows a region in more detail (a) Shoulder/Cartesian (b) Shoulder/Random (c) Shoulder/Radial (d) Coronal/Cartesian 15 (e) Coronal/Random 18 (f) Coronal/Radial Fig. 4. Reconstruction PSNR as a function of percentage sampled in k-space. 2322
5 6. REFERENCES [1] E. Candés, J. Romberg, and T. Tao, Robust Uncertainty Principles: Exact Signal Reconstruction From Highly Incomplete Frequency Information, IEEE Trans. on Information Theory, vol. 52, no. 2, pp , 00. [2] D. Donoho, Compressed sensing, IEEE Trans. on Information Theory, vol. 52, no. 4, pp , 06. [3] M. Lustig, D. Donoho, and J. M. Pauly, Sparse MRI: The Application of Compressed Sensing for Rapid MR Imaging, Magnetic Resonance in Medicine, vol. 58, no. 6, pp , 07. [4] Y. Kim, M. S. Nadar, and A. Bilgin, Wavelet-Based Compressed Sensing Using Gaussian Scale Mixtures, IEEE Trans. on Image Processing, vol. 21, no. 6, pp , 12. [5] X. Qu, W. Zhang, D. Guo, C. Cai, S. Cai, and Z. Chen, Iterative Thresholding Compressed Sensing MRI Based on Contourlet Transform, Inverse Problems Sci. Eng., Jun. 09. [6] J. Trzasko and A. Manduca, Highly Undersampled Magnetic Resonance Image Reconstruction via Homotopic L0- Minimization, IEEE Trans. on Medical Imaging, vol., no. 1, pp , 09. [7] J. C. Ye, S. Tak, Y. Han, and H. W. Park, Projection Reconstruction MR Imaging Using FOCUSS, Magnetic Resonance in Medicine, vol. 57, no. 4, pp , 07. [8] M. Akcakaya, T. A. Basha, B. Goddu, L. A. Goepfert, K. V. Kissinger, V. Tarokh, W. J. Manning, and R. Nezafat, Low- Dimensional-Structure Self-Learning and Thresholding: Regularization beyond Compressed Sensing for MRI Reconstruction, Magnetic Resonance in Medicine, vol. 66, pp , 11. [9] S. Ravishankar and Y. Bresler, MR Image Reconstruction from Highly Undersampled k-space Data by Dictionary Learning, IEEE Trans. on Medical Imaging, vol., no. 5, pp , 11. [10] X. Qu, D. Guo, B. Ning, Y. Hou, Y. Lin, S. Cai, and Z. Chen, Undersampled MRI Reconstruction with the Patch- Based Directional Wavelets, Magnetic Resonance in Imaging, doi: /j.mri , Feb. 12. [11] Z. Yang and M. Jacob, Robust Non-Local Regularization Framework for Motion Compensated Dynamic Imaging without Explicit Motion Estimation, IEEE Int. Symp. Biomedical Imaging, pp , 12. [12] K. Dabov, A. Foi, V. Katkovnik, and K. Egiazarian, Image Denoising by Sparse 3D Transform-Domain Collaborative Filtering, IEEE Trans. on Image Process, vol. 16, no. 8, pp , 07. [13] M. Aharon, M. Elad, A. Bruckstein, and Y. Katz, K-SVD: An Algorithm for Designing of Overcomplete Dictionaries for Sparse Representation, IEEE Trans. on Signal Processing, vol. 54, pp , 06. [14] M. Protter and M. Elad, Image Sequence Denoising via Sparse and Redundant Representations, IEEE Trans. on Image Processing, vol. 18, no. 1, pp , 09. [15] G. Yu, G. Sapiro, and S. Mallat, Solving Inverse Problems with Piecewise Linear Estimators: From Gaussian Mixture Models to Structured Sparsity, IEEE Trans. on Image Processing, vol. 21, issue. 5, pp , 10. [16] J. Paisley, and L. Carin, Nonparametric Factor Analysis with Beta Process Priors, International Conference on Machine Learning, 09. [17] X. Ding, L. He, and L. Carin, Bayesian robust principal component analysis, IEEE Trans. Image Process., vol., no. 12, pp , Dec. 11. [18] M. Zhou, H. Chen, J. Paisley, L. Ren, L. Li, Z. Xing, D. Dunson, G. Sapiro, and L. Carin, Nonparametric Bayesian Dictionary Learning for Analysis of Noisy and Incomplete Images, IEEE Trans. Image Process., vol. 21, no. 1, pp , Jun. 11. [19] W. Yin, S. Osher, D. Goldfarb, and J. Darbon, Bregman Iterative Algorithms for L1 Minimization with Applications to Compressed Sensing, SIAM Journal on Imaging Sciences, vol. 1, no. 1, pp , 08. [] T. Goldstein and S. Osher, The Split Bregman Method for L1 Regularized Problems, SIAM Journal on Imaging Sciences, vol. 2, issue.2, pp , 09. [21] S. Boyd, N. Parikh, E. Chu, B. Peleato and J. Eckstein, Distributed optimization and statistical learning via the alternating direction method of multipliers, Foundations and Trends in Machine Learning, vol. 3, num. 1, pp , 10. [22] T.F. Chan, G.H. Golub and P. Mulet, A nonlinear primaldual method for total variation-based image restoration, SIAM Journal of Scientific Computing, vol., pp , [23] J. Darbon and M. Sigelle, A fast and exact algorithm for total variation minimization, ibpria, Lecture Notes in Computer Science 3522, Springer-Verlag, Berlin, pp , 05. [] J. Huang, S. Zhang, and D. Metaxas, Efficient MR Image Reconstruction for Compressed MR Imaging, Medical Image Analysis, vol. 15, no. 5, pp ,
arxiv: v1 [cs.cv] 12 Feb 2013
1 MR Image Reconstruction from Undersampled k-space with Bayesian Dictionary Learning Yue Huang 1, John Paisley 2, Xianbo Chen 1, Xinghao Ding 1, Feng Huang 3 and Xiao-ping Zhang 4 arxiv:12.2712v1 [cs.cv]
More informationBayesian Nonparametric Dictionary Learning for Compressed Sensing MRI
1 Bayesian Nonparametric Dictionary Learning for Compressed Sensing MRI Yue Huang, John Paisley, Qin Lin, Xinghao Ding, Xueyang Fu and Xiao-ping Zhang, Senior Member, IEEE arxiv:12.2712v3 [cs.cv] 26 Jul
More informationMAGNETIC resonance imaging (MRI) is a widely used
IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 23, NO. 12, DECEMBER 2014 5007 Bayesian Nonparametric Dictionary Learning for Compressed Sensing MRI Yue Huang, John Paisley, Qin Lin, Xinghao Ding, Xueyang
More informationEfficient MR Image Reconstruction for Compressed MR Imaging
Efficient MR Image Reconstruction for Compressed MR Imaging Junzhou Huang, Shaoting Zhang, and Dimitris Metaxas Division of Computer and Information Sciences, Rutgers University, NJ, USA 08854 Abstract.
More informationIMAGE RESTORATION VIA EFFICIENT GAUSSIAN MIXTURE MODEL LEARNING
IMAGE RESTORATION VIA EFFICIENT GAUSSIAN MIXTURE MODEL LEARNING Jianzhou Feng Li Song Xiaog Huo Xiaokang Yang Wenjun Zhang Shanghai Digital Media Processing Transmission Key Lab, Shanghai Jiaotong University
More informationThe Benefit of Tree Sparsity in Accelerated MRI
The Benefit of Tree Sparsity in Accelerated MRI Chen Chen and Junzhou Huang Department of Computer Science and Engineering, The University of Texas at Arlington, TX, USA 76019 Abstract. The wavelet coefficients
More informationNon-Parametric Bayesian Dictionary Learning for Sparse Image Representations
Non-Parametric Bayesian Dictionary Learning for Sparse Image Representations Mingyuan Zhou, Haojun Chen, John Paisley, Lu Ren, 1 Guillermo Sapiro and Lawrence Carin Department of Electrical and Computer
More informationPatch-Based Color Image Denoising using efficient Pixel-Wise Weighting Techniques
Patch-Based Color Image Denoising using efficient Pixel-Wise Weighting Techniques Syed Gilani Pasha Assistant Professor, Dept. of ECE, School of Engineering, Central University of Karnataka, Gulbarga,
More informationBlind Compressed Sensing Using Sparsifying Transforms
Blind Compressed Sensing Using Sparsifying Transforms Saiprasad Ravishankar and Yoram Bresler Department of Electrical and Computer Engineering and Coordinated Science Laboratory University of Illinois
More informationWeighted-CS for reconstruction of highly under-sampled dynamic MRI sequences
Weighted- for reconstruction of highly under-sampled dynamic MRI sequences Dornoosh Zonoobi and Ashraf A. Kassim Dept. Electrical and Computer Engineering National University of Singapore, Singapore E-mail:
More informationCompressive Sensing MRI with Wavelet Tree Sparsity
Compressive Sensing MRI with Wavelet Tree Sparsity Chen Chen and Junzhou Huang Department of Computer Science and Engineering University of Texas at Arlington cchen@mavs.uta.edu jzhuang@uta.edu Abstract
More informationOptimal Sampling Geometries for TV-Norm Reconstruction of fmri Data
Optimal Sampling Geometries for TV-Norm Reconstruction of fmri Data Oliver M. Jeromin, Student Member, IEEE, Vince D. Calhoun, Senior Member, IEEE, and Marios S. Pattichis, Senior Member, IEEE Abstract
More informationCompressive Sensing Algorithms for Fast and Accurate Imaging
Compressive Sensing Algorithms for Fast and Accurate Imaging Wotao Yin Department of Computational and Applied Mathematics, Rice University SCIMM 10 ASU, Tempe, AZ Acknowledgements: results come in part
More informationImage Denoising via Group Sparse Eigenvectors of Graph Laplacian
Image Denoising via Group Sparse Eigenvectors of Graph Laplacian Yibin Tang, Ying Chen, Ning Xu, Aimin Jiang, Lin Zhou College of IOT Engineering, Hohai University, Changzhou, China School of Information
More informationAn Optimized Pixel-Wise Weighting Approach For Patch-Based Image Denoising
An Optimized Pixel-Wise Weighting Approach For Patch-Based Image Denoising Dr. B. R.VIKRAM M.E.,Ph.D.,MIEEE.,LMISTE, Principal of Vijay Rural Engineering College, NIZAMABAD ( Dt.) G. Chaitanya M.Tech,
More informationG Practical Magnetic Resonance Imaging II Sackler Institute of Biomedical Sciences New York University School of Medicine. Compressed Sensing
G16.4428 Practical Magnetic Resonance Imaging II Sackler Institute of Biomedical Sciences New York University School of Medicine Compressed Sensing Ricardo Otazo, PhD ricardo.otazo@nyumc.org Compressed
More informationImage Deblurring Using Adaptive Sparse Domain Selection and Adaptive Regularization
Volume 3, No. 3, May-June 2012 International Journal of Advanced Research in Computer Science RESEARCH PAPER Available Online at www.ijarcs.info ISSN No. 0976-5697 Image Deblurring Using Adaptive Sparse
More informationCompressed Sensing Reconstructions for Dynamic Contrast Enhanced MRI
1 Compressed Sensing Reconstructions for Dynamic Contrast Enhanced MRI Kevin T. Looby klooby@stanford.edu ABSTRACT The temporal resolution necessary for dynamic contrast enhanced (DCE) magnetic resonance
More informationDenoising an Image by Denoising its Components in a Moving Frame
Denoising an Image by Denoising its Components in a Moving Frame Gabriela Ghimpețeanu 1, Thomas Batard 1, Marcelo Bertalmío 1, and Stacey Levine 2 1 Universitat Pompeu Fabra, Spain 2 Duquesne University,
More informationCollaborative Sparsity and Compressive MRI
Modeling and Computation Seminar February 14, 2013 Table of Contents 1 T2 Estimation 2 Undersampling in MRI 3 Compressed Sensing 4 Model-Based Approach 5 From L1 to L0 6 Spatially Adaptive Sparsity MRI
More informationStructure-adaptive Image Denoising with 3D Collaborative Filtering
, pp.42-47 http://dx.doi.org/10.14257/astl.2015.80.09 Structure-adaptive Image Denoising with 3D Collaborative Filtering Xuemei Wang 1, Dengyin Zhang 2, Min Zhu 2,3, Yingtian Ji 2, Jin Wang 4 1 College
More information29 th NATIONAL RADIO SCIENCE CONFERENCE (NRSC 2012) April 10 12, 2012, Faculty of Engineering/Cairo University, Egypt
K1. High Performance Compressed Sensing MRI Image Reconstruction Ahmed Abdel Salam, Fadwa Fawzy, Norhan Shaker, Yasser M.Kadah Biomedical Engineering, Cairo University, Cairo, Egypt, ymk@k-space.org Computer
More informationADAPTIVE LOW RANK AND SPARSE DECOMPOSITION OF VIDEO USING COMPRESSIVE SENSING
ADAPTIVE LOW RANK AND SPARSE DECOMPOSITION OF VIDEO USING COMPRESSIVE SENSING Fei Yang 1 Hong Jiang 2 Zuowei Shen 3 Wei Deng 4 Dimitris Metaxas 1 1 Rutgers University 2 Bell Labs 3 National University
More informationIMAGE DENOISING USING NL-MEANS VIA SMOOTH PATCH ORDERING
IMAGE DENOISING USING NL-MEANS VIA SMOOTH PATCH ORDERING Idan Ram, Michael Elad and Israel Cohen Department of Electrical Engineering Department of Computer Science Technion - Israel Institute of Technology
More informationRedundancy Encoding for Fast Dynamic MR Imaging using Structured Sparsity
Redundancy Encoding for Fast Dynamic MR Imaging using Structured Sparsity Vimal Singh and Ahmed H. Tewfik Electrical and Computer Engineering Dept., The University of Texas at Austin, USA Abstract. For
More informationImage Interpolation using Collaborative Filtering
Image Interpolation using Collaborative Filtering 1,2 Qiang Guo, 1,2,3 Caiming Zhang *1 School of Computer Science and Technology, Shandong Economic University, Jinan, 250014, China, qguo2010@gmail.com
More informationSynthesis and Analysis Sparse Representation Models for Image Restoration. Shuhang Gu 顾舒航. Dept. of Computing The Hong Kong Polytechnic University
Synthesis and Analysis Sparse Representation Models for Image Restoration Shuhang Gu 顾舒航 Dept. of Computing The Hong Kong Polytechnic University Outline Sparse representation models for image modeling
More informationSparsity and image processing
Sparsity and image processing Aurélie Boisbunon INRIA-SAM, AYIN March 6, Why sparsity? Main advantages Dimensionality reduction Fast computation Better interpretability Image processing pattern recognition
More informationSupplemental Material for Efficient MR Image Reconstruction for Compressed MR Imaging
Supplemental Material for Efficient MR Image Reconstruction for Compressed MR Imaging Paper ID: 1195 No Institute Given 1 More Experiment Results 1.1 Visual Comparisons We apply all methods on four 2D
More informationInverse Problems and Machine Learning
Inverse Problems and Machine Learning Julian Wörmann Research Group for Geometric Optimization and Machine Learning (GOL) 1 What are inverse problems? 2 Inverse Problems cause/ excitation 3 Inverse Problems
More informationPATCH-DISAGREEMENT AS A WAY TO IMPROVE K-SVD DENOISING
PATCH-DISAGREEMENT AS A WAY TO IMPROVE K-SVD DENOISING Yaniv Romano Department of Electrical Engineering Technion, Haifa 32000, Israel yromano@tx.technion.ac.il Michael Elad Department of Computer Science
More informationDepartment of Electronics and Communication KMP College of Engineering, Perumbavoor, Kerala, India 1 2
Vol.3, Issue 3, 2015, Page.1115-1021 Effect of Anti-Forensics and Dic.TV Method for Reducing Artifact in JPEG Decompression 1 Deepthy Mohan, 2 Sreejith.H 1 PG Scholar, 2 Assistant Professor Department
More informationDetecting Burnscar from Hyperspectral Imagery via Sparse Representation with Low-Rank Interference
Detecting Burnscar from Hyperspectral Imagery via Sparse Representation with Low-Rank Interference Minh Dao 1, Xiang Xiang 1, Bulent Ayhan 2, Chiman Kwan 2, Trac D. Tran 1 Johns Hopkins Univeristy, 3400
More information2D and 3D Far-Field Radiation Patterns Reconstruction Based on Compressive Sensing
Progress In Electromagnetics Research M, Vol. 46, 47 56, 206 2D and 3D Far-Field Radiation Patterns Reconstruction Based on Compressive Sensing Berenice Verdin * and Patrick Debroux Abstract The measurement
More informationLEARNING FLIPPING AND ROTATION INVARIANT SPARSIFYING TRANSFORMS
LEARNING FLIPPING AND ROTATION INVARIANT SPARSIFYING TRANSFORMS Bihan Wen 1, Saiprasad Ravishankar, and Yoram Bresler 1 1 Department of Electrical and Computer Engineering and the Coordinated Science Laboratory
More informationClustered Compressive Sensing: Application on Medical Imaging
Clustered Compressive Sensing: Application on Medical Imaging Solomon A. Tesfamicael, IACSIT Member and Faraz Barzideh Abstract This paper provides clustered compressive sensing (CCS) based image processing
More informationImage reconstruction based on back propagation learning in Compressed Sensing theory
Image reconstruction based on back propagation learning in Compressed Sensing theory Gaoang Wang Project for ECE 539 Fall 2013 Abstract Over the past few years, a new framework known as compressive sampling
More informationLearning Splines for Sparse Tomographic Reconstruction. Elham Sakhaee and Alireza Entezari University of Florida
Learning Splines for Sparse Tomographic Reconstruction Elham Sakhaee and Alireza Entezari University of Florida esakhaee@cise.ufl.edu 2 Tomographic Reconstruction Recover the image given X-ray measurements
More informationIterative CT Reconstruction Using Curvelet-Based Regularization
Iterative CT Reconstruction Using Curvelet-Based Regularization Haibo Wu 1,2, Andreas Maier 1, Joachim Hornegger 1,2 1 Pattern Recognition Lab (LME), Department of Computer Science, 2 Graduate School in
More informationREGULARIZATION PARAMETER TRIMMING FOR ITERATIVE IMAGE RECONSTRUCTION
REGULARIZATION PARAMETER TRIMMING FOR ITERATIVE IMAGE RECONSTRUCTION Haoyi Liang and Daniel S. Weller University of Virginia, Department of ECE, Charlottesville, VA, 2294, USA ABSTRACT Conventional automatic
More informationELEG Compressive Sensing and Sparse Signal Representations
ELEG 867 - Compressive Sensing and Sparse Signal Representations Gonzalo R. Arce Depart. of Electrical and Computer Engineering University of Delaware Fall 211 Compressive Sensing G. Arce Fall, 211 1 /
More informationSingle Image Interpolation via Adaptive Non-Local Sparsity-Based Modeling
Single Image Interpolation via Adaptive Non-Local Sparsity-Based Modeling Yaniv Romano The Electrical Engineering Department Matan Protter The Computer Science Department Michael Elad The Computer Science
More informationDCT image denoising: a simple and effective image denoising algorithm
IPOL Journal Image Processing On Line DCT image denoising: a simple and effective image denoising algorithm Guoshen Yu, Guillermo Sapiro article demo archive published reference 2011-10-24 GUOSHEN YU,
More informationI. INTRODUCTION. B. Exploiting Structure and Compressive Measurements
130 IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 21, NO. 1, JANUARY 2012 Nonparametric Bayesian Dictionary Learning for Analysis of Noisy and Incomplete Images Mingyuan Zhou, Haojun Chen, John Paisley,
More informationSparse sampling in MRI: From basic theory to clinical application. R. Marc Lebel, PhD Department of Electrical Engineering Department of Radiology
Sparse sampling in MRI: From basic theory to clinical application R. Marc Lebel, PhD Department of Electrical Engineering Department of Radiology Objective Provide an intuitive overview of compressed sensing
More informationCompressive Sensing for Multimedia. Communications in Wireless Sensor Networks
Compressive Sensing for Multimedia 1 Communications in Wireless Sensor Networks Wael Barakat & Rabih Saliba MDDSP Project Final Report Prof. Brian L. Evans May 9, 2008 Abstract Compressive Sensing is an
More informationCHAPTER 9 INPAINTING USING SPARSE REPRESENTATION AND INVERSE DCT
CHAPTER 9 INPAINTING USING SPARSE REPRESENTATION AND INVERSE DCT 9.1 Introduction In the previous chapters the inpainting was considered as an iterative algorithm. PDE based method uses iterations to converge
More informationIntroduction. Wavelets, Curvelets [4], Surfacelets [5].
Introduction Signal reconstruction from the smallest possible Fourier measurements has been a key motivation in the compressed sensing (CS) research [1]. Accurate reconstruction from partial Fourier data
More informationBlind Compressed Sensing Using Sparsifying Transforms
Blind Compressed Sensing Using Sparsifying Transforms Saiprasad Ravishankar and Yoram Bresler Department of Electrical and Computer Engineering and the Coordinated Science Laboratory University of Illinois
More informationSUPPLEMENTARY MATERIAL
SUPPLEMENTARY MATERIAL Zhiyuan Zha 1,3, Xin Liu 2, Ziheng Zhou 2, Xiaohua Huang 2, Jingang Shi 2, Zhenhong Shang 3, Lan Tang 1, Yechao Bai 1, Qiong Wang 1, Xinggan Zhang 1 1 School of Electronic Science
More informationOff-the-Grid Compressive Imaging: Recovery of Piecewise Constant Images from Few Fourier Samples
Off-the-Grid Compressive Imaging: Recovery of Piecewise Constant Images from Few Fourier Samples Greg Ongie PhD Candidate Department of Applied Math and Computational Sciences University of Iowa April
More informationImage Inpainting Using Sparsity of the Transform Domain
Image Inpainting Using Sparsity of the Transform Domain H. Hosseini*, N.B. Marvasti, Student Member, IEEE, F. Marvasti, Senior Member, IEEE Advanced Communication Research Institute (ACRI) Department of
More informationRecovery of Piecewise Smooth Images from Few Fourier Samples
Recovery of Piecewise Smooth Images from Few Fourier Samples Greg Ongie*, Mathews Jacob Computational Biomedical Imaging Group (CBIG) University of Iowa SampTA 2015 Washington, D.C. 1. Introduction 2.
More informationGRID WARPING IN TOTAL VARIATION IMAGE ENHANCEMENT METHODS. Andrey Nasonov, and Andrey Krylov
GRID WARPING IN TOTAL VARIATION IMAGE ENHANCEMENT METHODS Andrey Nasonov, and Andrey Krylov Lomonosov Moscow State University, Moscow, Department of Computational Mathematics and Cybernetics, e-mail: nasonov@cs.msu.ru,
More informationA Compressed Sensing Approach for Biological Microscopy Image Denoising
A Compressed Sensing Approach for Biological Microscopy Image Denoising Marcio M. Marim, Elsa D. Angelini, Jean-Christophe Olivo-Marin To cite this version: Marcio M. Marim, Elsa D. Angelini, Jean-Christophe
More informationImage Restoration and Background Separation Using Sparse Representation Framework
Image Restoration and Background Separation Using Sparse Representation Framework Liu, Shikun Abstract In this paper, we introduce patch-based PCA denoising and k-svd dictionary learning method for the
More informationImage denoising in the wavelet domain using Improved Neigh-shrink
Image denoising in the wavelet domain using Improved Neigh-shrink Rahim Kamran 1, Mehdi Nasri, Hossein Nezamabadi-pour 3, Saeid Saryazdi 4 1 Rahimkamran008@gmail.com nasri_me@yahoo.com 3 nezam@uk.ac.ir
More informationModified Iterative Method for Recovery of Sparse Multiple Measurement Problems
Journal of Electrical Engineering 6 (2018) 124-128 doi: 10.17265/2328-2223/2018.02.009 D DAVID PUBLISHING Modified Iterative Method for Recovery of Sparse Multiple Measurement Problems Sina Mortazavi and
More informationImage Restoration Using DNN
Image Restoration Using DNN Hila Levi & Eran Amar Images were taken from: http://people.tuebingen.mpg.de/burger/neural_denoising/ Agenda Domain Expertise vs. End-to-End optimization Image Denoising and
More informationTotal Variation Denoising with Overlapping Group Sparsity
1 Total Variation Denoising with Overlapping Group Sparsity Ivan W. Selesnick and Po-Yu Chen Polytechnic Institute of New York University Brooklyn, New York selesi@poly.edu 2 Abstract This paper describes
More informationImage Denoising Using Sparse Representations
Image Denoising Using Sparse Representations SeyyedMajid Valiollahzadeh 1,,HamedFirouzi 1, Massoud Babaie-Zadeh 1, and Christian Jutten 2 1 Department of Electrical Engineering, Sharif University of Technology,
More informationAdvanced phase retrieval: maximum likelihood technique with sparse regularization of phase and amplitude
Advanced phase retrieval: maximum likelihood technique with sparse regularization of phase and amplitude A. Migukin *, V. atkovnik and J. Astola Department of Signal Processing, Tampere University of Technology,
More informationImage Super-Resolution Reconstruction Based On L 1/2 Sparsity
Buletin Teknik Elektro dan Informatika (Bulletin of Electrical Engineering and Informatics) Vol. 3, No. 3, September 4, pp. 55~6 ISSN: 89-39 55 Image Super-Resolution Reconstruction Based On L / Sparsity
More informationRECOVERY OF PARTIALLY OBSERVED DATA APPEARING IN CLUSTERS. Sunrita Poddar, Mathews Jacob
RECOVERY OF PARTIALLY OBSERVED DATA APPEARING IN CLUSTERS Sunrita Poddar, Mathews Jacob Department of Electrical and Computer Engineering The University of Iowa, IA, USA ABSTRACT We propose a matrix completion
More informationExpected Patch Log Likelihood with a Sparse Prior
Expected Patch Log Likelihood with a Sparse Prior Jeremias Sulam and Michael Elad Computer Science Department, Technion, Israel {jsulam,elad}@cs.technion.ac.il Abstract. Image priors are of great importance
More informationSignal Reconstruction from Sparse Representations: An Introdu. Sensing
Signal Reconstruction from Sparse Representations: An Introduction to Compressed Sensing December 18, 2009 Digital Data Acquisition Suppose we want to acquire some real world signal digitally. Applications
More informationIncoherent noise suppression with curvelet-domain sparsity Vishal Kumar, EOS-UBC and Felix J. Herrmann, EOS-UBC
Incoherent noise suppression with curvelet-domain sparsity Vishal Kumar, EOS-UBC and Felix J. Herrmann, EOS-UBC SUMMARY The separation of signal and noise is a key issue in seismic data processing. By
More informationLearning best wavelet packet bases for compressed sensing of classes of images: application to brain MR imaging
Learning best wavelet packet bases for compressed sensing of classes of images: application to brain MR imaging Michal P. Romaniuk, 1 Anil W. Rao, 1 Robin Wolz, 1 Joseph V. Hajnal 2 and Daniel Rueckert
More informationarxiv: v1 [cs.cv] 23 Sep 2017
Adaptive Measurement Network for CS Image Reconstruction Xuemei Xie, Yuxiang Wang, Guangming Shi, Chenye Wang, Jiang Du, and Zhifu Zhao Xidian University, Xi an, China xmxie@mail.xidian.edu.cn arxiv:1710.01244v1
More informationSHIP WAKE DETECTION FOR SAR IMAGES WITH COMPLEX BACKGROUNDS BASED ON MORPHOLOGICAL DICTIONARY LEARNING
SHIP WAKE DETECTION FOR SAR IMAGES WITH COMPLEX BACKGROUNDS BASED ON MORPHOLOGICAL DICTIONARY LEARNING Guozheng Yang 1, 2, Jing Yu 3, Chuangbai Xiao 3, Weidong Sun 1 1 State Key Laboratory of Intelligent
More informationMAGNETIC resonance imaging (MRI) is an important
1 A Deep Error orrection Network for ompressed Sensing MRI Liyan Sun, Zhiwen Fan, Yue Huang, Xinghao Ding, John Paisley Fujian Key Laboratory of Sensing and omputing for Smart ity, Xiamen University, Fujian,
More informationResearch Article Parallel Computing of Patch-Based Nonlocal Operator and Its Application in Compressed Sensing MRI
Hindawi Publishing Corporation Computational and Mathematical Methods in Medicine Volume 2014, Article ID 257435, 6 pages http://dx.doi.org/10.1155/2014/257435 Research Article Parallel Computing of Patch-Based
More informationRecent Advances inelectrical & Electronic Engineering
4 Send Orders for Reprints to reprints@benthamscience.ae Recent Advances in Electrical & Electronic Engineering, 017, 10, 4-47 RESEARCH ARTICLE ISSN: 35-0965 eissn: 35-0973 Image Inpainting Method Based
More informationNon-Local Compressive Sampling Recovery
Non-Local Compressive Sampling Recovery Xianbiao Shu 1, Jianchao Yang 2 and Narendra Ahuja 1 1 University of Illinois at Urbana-Champaign, 2 Adobe Research 1 {xshu2, n-ahuja}@illinois.edu, 2 jiayang@adobe.com
More informationAdaptive Reconstruction Methods for Low-Dose Computed Tomography
Adaptive Reconstruction Methods for Low-Dose Computed Tomography Joseph Shtok Ph.D. supervisors: Prof. Michael Elad, Dr. Michael Zibulevsky. Technion IIT, Israel, 011 Ph.D. Talk, Apr. 01 Contents of this
More informationThe Alternating Direction Method of Multipliers
The Alternating Direction Method of Multipliers With Adaptive Step Size Selection Peter Sutor, Jr. Project Advisor: Professor Tom Goldstein October 8, 2015 1 / 30 Introduction Presentation Outline 1 Convex
More informationInverse problem regularization using adaptive signal models
Inverse problem regularization using adaptive signal models Jeffrey A. Fessler William L. Root Professor of EECS EECS Dept., BME Dept., Dept. of Radiology University of Michigan http://web.eecs.umich.edu/
More informationA Patch Prior for Dense 3D Reconstruction in Man-Made Environments
A Patch Prior for Dense 3D Reconstruction in Man-Made Environments Christian Häne 1, Christopher Zach 2, Bernhard Zeisl 1, Marc Pollefeys 1 1 ETH Zürich 2 MSR Cambridge October 14, 2012 A Patch Prior for
More informationK11. Modified Hybrid Median Filter for Image Denoising
April 10 12, 2012, Faculty of Engineering/Cairo University, Egypt K11. Modified Hybrid Median Filter for Image Denoising Zeinab A.Mustafa, Banazier A. Abrahim and Yasser M. Kadah Biomedical Engineering
More informationVARIABLE DENSITY COMPRESSED IMAGE SAMPLING
VARIABLE DENSITY COMPRESSED IMAGE SAMPLING Zhongmin Wang, Gonzalo R. Arce and Jose L. Paredes Dep. of Electrical and Computer Engineering, University of Delaware, Newark, DE, 19716 USA. e-mail:{zhongmin,arce}@ee.udel.edu
More informationDeconvolution with curvelet-domain sparsity Vishal Kumar, EOS-UBC and Felix J. Herrmann, EOS-UBC
Deconvolution with curvelet-domain sparsity Vishal Kumar, EOS-UBC and Felix J. Herrmann, EOS-UBC SUMMARY We use the recently introduced multiscale and multidirectional curvelet transform to exploit the
More informationCompressed Sensing and L 1 -Related Minimization
Compressed Sensing and L 1 -Related Minimization Yin Wotao Computational and Applied Mathematics Rice University Jan 4, 2008 Chinese Academy of Sciences Inst. Comp. Math The Problems of Interest Unconstrained
More informationThe flare Package for High Dimensional Linear Regression and Precision Matrix Estimation in R
Journal of Machine Learning Research 6 (205) 553-557 Submitted /2; Revised 3/4; Published 3/5 The flare Package for High Dimensional Linear Regression and Precision Matrix Estimation in R Xingguo Li Department
More informationCompressed Sensing for Rapid MR Imaging
Compressed Sensing for Rapid Imaging Michael Lustig1, Juan Santos1, David Donoho2 and John Pauly1 1 Electrical Engineering Department, Stanford University 2 Statistics Department, Stanford University rapid
More informationWhen Sparsity Meets Low-Rankness: Transform Learning With Non-Local Low-Rank Constraint For Image Restoration
When Sparsity Meets Low-Rankness: Transform Learning With Non-Local Low-Rank Constraint For Image Restoration Bihan Wen, Yanjun Li and Yoram Bresler Department of Electrical and Computer Engineering Coordinated
More informationINCOHERENT DICTIONARY LEARNING FOR SPARSE REPRESENTATION BASED IMAGE DENOISING
INCOHERENT DICTIONARY LEARNING FOR SPARSE REPRESENTATION BASED IMAGE DENOISING Jin Wang 1, Jian-Feng Cai 2, Yunhui Shi 1 and Baocai Yin 1 1 Beijing Key Laboratory of Multimedia and Intelligent Software
More informationAn R Package flare for High Dimensional Linear Regression and Precision Matrix Estimation
An R Package flare for High Dimensional Linear Regression and Precision Matrix Estimation Xingguo Li Tuo Zhao Xiaoming Yuan Han Liu Abstract This paper describes an R package named flare, which implements
More informationCompressed Sensing and Applications by using Dictionaries in Image Processing
Advances in Computational Sciences and Technology ISSN 0973-6107 Volume 10, Number 2 (2017) pp. 165-170 Research India Publications http://www.ripublication.com Compressed Sensing and Applications by using
More informationBSIK-SVD: A DICTIONARY-LEARNING ALGORITHM FOR BLOCK-SPARSE REPRESENTATIONS. Yongqin Zhang, Jiaying Liu, Mading Li, Zongming Guo
2014 IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP) BSIK-SVD: A DICTIONARY-LEARNING ALGORITHM FOR BLOCK-SPARSE REPRESENTATIONS Yongqin Zhang, Jiaying Liu, Mading Li, Zongming
More informationCardiac diffusion tensor imaging based on compressed sensing using joint sparsity and low-rank approximation
Technology and Health Care 24 2016) S593 S599 DOI 10.3233/THC-161186 IOS Press S593 Cardiac diffusion tensor imaging based on compressed sensing using joint sparsity and low-rank approximation Jianping
More informationThe Alternating Direction Method of Multipliers
The Alternating Direction Method of Multipliers Customizable software solver package Peter Sutor, Jr. Project Advisor: Professor Tom Goldstein April 27, 2016 1 / 28 Background The Dual Problem Consider
More informationP257 Transform-domain Sparsity Regularization in Reconstruction of Channelized Facies
P257 Transform-domain Sparsity Regularization in Reconstruction of Channelized Facies. azemi* (University of Alberta) & H.R. Siahkoohi (University of Tehran) SUMMARY Petrophysical reservoir properties,
More informationA Novel Iterative Thresholding Algorithm for Compressed Sensing Reconstruction of Quantitative MRI Parameters from Insufficient Data
A Novel Iterative Thresholding Algorithm for Compressed Sensing Reconstruction of Quantitative MRI Parameters from Insufficient Data Alexey Samsonov, Julia Velikina Departments of Radiology and Medical
More informationCOMPRESSIVE VIDEO SAMPLING
COMPRESSIVE VIDEO SAMPLING Vladimir Stanković and Lina Stanković Dept of Electronic and Electrical Engineering University of Strathclyde, Glasgow, UK phone: +44-141-548-2679 email: {vladimir,lina}.stankovic@eee.strath.ac.uk
More informationCompressive Sensing Based Image Reconstruction using Wavelet Transform
Compressive Sensing Based Image Reconstruction using Wavelet Transform Sherin C Abraham #1, Ketki Pathak *2, Jigna J Patel #3 # Electronics & Communication department, Gujarat Technological University
More informationOne Network to Solve Them All Solving Linear Inverse Problems using Deep Projection Models
One Network to Solve Them All Solving Linear Inverse Problems using Deep Projection Models [Supplemental Materials] 1. Network Architecture b ref b ref +1 We now describe the architecture of the networks
More informationCompressed Sensing Algorithm for Real-Time Doppler Ultrasound Image Reconstruction
Mathematical Modelling and Applications 2017; 2(6): 75-80 http://www.sciencepublishinggroup.com/j/mma doi: 10.11648/j.mma.20170206.14 ISSN: 2575-1786 (Print); ISSN: 2575-1794 (Online) Compressed Sensing
More informationEfficient Imaging Algorithms on Many-Core Platforms
Efficient Imaging Algorithms on Many-Core Platforms H. Köstler Dagstuhl, 22.11.2011 Contents Imaging Applications HDR Compression performance of PDE-based models Image Denoising performance of patch-based
More informationImage Restoration with Compound Regularization Using a Bregman Iterative Algorithm
Image Restoration with Compound Regularization Using a Bregman Iterative Algorithm Manya V. Afonso, José M. Bioucas-Dias, Mario A. T. Figueiredo To cite this version: Manya V. Afonso, José M. Bioucas-Dias,
More informationVirtual Training Samples and CRC based Test Sample Reconstruction and Face Recognition Experiments Wei HUANG and Li-ming MIAO
7 nd International Conference on Computational Modeling, Simulation and Applied Mathematics (CMSAM 7) ISBN: 978--6595-499-8 Virtual raining Samples and CRC based est Sample Reconstruction and Face Recognition
More information