GPU Profiling of Singular Value Decomposition in OLPCA Method for Image Denoising

We focus on the Graphic Processor Unit (GPU) profiling of the Singular Value Decomposition (SVD) that is a basic task of the Overcomplete Local Principal Component Analysis (OLPCA) method. More in detail, we investigate the impact of the SVD on the OLPCA algorithm for the Magnetic Resonance Imaging (MRI) denoising application. We have resorted several parallel approaches based on scientific libraries in order to investigate the heavy computational complexity of the algorithm. The GPU implementation is based on two specific libraries: NVIDIA cuBLAS and CULA, in order to compare them. Our results show how the GPU library based solution could be adopted for improving the performance of same tasks in a denoising algorithm.

[1]  Salvatore Cuomo,et al.  A GPU parallel implementation of the Local Principal Component Analysis overcomplete method for DW image denoising , 2016, 2016 IEEE Symposium on Computers and Communication (ISCC).

[2]  Flora Amato,et al.  An integrated framework for securing semi-structured health records , 2015, Knowl. Based Syst..

[3]  Salvatore Cuomo,et al.  Surface reconstruction from scattered point via RBF interpolation on GPU , 2013, 2013 Federated Conference on Computer Science and Information Systems.

[4]  Jean-Michel Morel,et al.  A Review of Image Denoising Algorithms, with a New One , 2005, Multiscale Model. Simul..

[5]  Thomas W. Parks,et al.  Orthogonal, exactly periodic subspace decomposition , 2003, IEEE Trans. Signal Process..

[6]  Salvatore Cuomo,et al.  A Regularized MRI Image Reconstruction based on Hessian Penalty Term on CPU/GPU Systems , 2013, ICCS.

[7]  Flora Amato,et al.  A model driven approach to data privacy verification in E-Health systems , 2015, Trans. Data Priv..

[8]  Flora Amato,et al.  An FPGA-Based Smart Classifier for Decision Support Systems , 2013, IDC.

[9]  Salvatore Cuomo,et al.  Toward a Multi-level Parallel Framework on GPU Cluster with PetSC-CUDA for PDE-based Optical Flow Computation , 2015, ICCS.

[10]  Konstantinos Konstantinides,et al.  Noise estimation and filtering using block-based singular value decomposition , 1997, IEEE Trans. Image Process..

[11]  Jar-Ferr Yang,et al.  Combined techniques of singular value decomposition and vector quantization for image coding , 1995, IEEE Trans. Image Process..

[12]  Salvatore Cuomo,et al.  3D Non-Local Means denoising via multi-GPU , 2013, 2013 Federated Conference on Computer Science and Information Systems.

[13]  H. Andrews,et al.  Singular value decompositions and digital image processing , 1976 .

[14]  D. Louis Collins,et al.  Diffusion Weighted Image Denoising Using Overcomplete Local PCA , 2013, PloS one.

[15]  Salvatore Cuomo,et al.  3D Data Denoising via Nonlocal Means Filter by Using Parallel GPU Strategies , 2014, Comput. Math. Methods Medicine.

[16]  Pierrick Coupé,et al.  Author manuscript, published in "Journal of Magnetic Resonance Imaging 2010;31(1):192-203" DOI: 10.1002/jmri.22003 Adaptive Non-Local Means Denoising of MR Images with Spatially Varying Noise Levels , 2010 .

[17]  Jiang Du,et al.  Noise reduction in multiple-echo data sets using singular value decomposition. , 2006, Magnetic resonance imaging.