Filters








41,384 Hits in 2.9 sec

Elastic registration of brain images on large PC-Clusters

J. Modersitzki, G. Lustig, O. Schmitt, W. Obelöer
2001 Future generations computer systems  
Our approach of correcting these deformations is based on an elastic matching of the images.  ...  As these requirements are in the range of today's grand challenges, a large PC-Cluster was used to provide the performance demands.  ...  In this paper we describe the parallel implementation of our elastic matching algorithm and present performance measurements on a 48 node cluster system.  ... 
doi:10.1016/s0167-739x(00)00081-9 fatcat:utekyslwkrb3neeydy5ipvp5fy

Robust Registration of Multi-modal Images: Towards Real-Time Clinical Applications [chapter]

Sébastien Ourselin, Radu Stefanescu, Xavier Pennec
2002 Lecture Notes in Computer Science  
For medical applications, we show that a cheap cluster of dual-processor PCs connected by an Ethernet network is a good trade-off between the power and the cost of the parallel platform.  ...  The resulting computation times are very good on small and medium resolution images, and they are still acceptable on high resolution MR images (resp. 19, 45 and 95 seconds on 5 dual-processors Pentium  ...  Dormont from the Neurological Dpt. of La Pitié Salpêtrière Hospital (Paris) for the high resolution MR images.  ... 
doi:10.1007/3-540-45787-9_18 fatcat:icklstozkng6fkfkxc3rmzddim

Out-Of-Core Sort-First Parallel Rendering for Cluster-Based Tiled Displays [article]

Wagner T. Correa, James T. Klosowski, Claudio T. Silva
2002 Eurographics Symposium on Parallel Graphics and Visualization  
We present a sort-first parallel system for out-of-core rendering of large models on cluster-based tiled displays.  ...  Running our system in approximate mode on a cluster of 16 PCs each with 512 MB of main memory, we are able to render 12-megapixel images of a 13-million-triangle model with 99.3% of accuracy at 10.8 frames  ...  In this paper, we present a parallel rendering system that exploits the power of a cluster of inexpensive PCs to render high-resolution images of large models at interactive frame rates on a tiled display  ... 
doi:10.2312/egpgv/egpgv02/089-096 fatcat:67cakk4qazdu5klsqvitio5tqe

Out-of-core sort-first parallel rendering for cluster-based tiled displays

Wagner T Corrêa, James T Klosowski, Cláudio T Silva
2003 Parallel Computing  
Running our system in approximate mode on a cluster of 16 PCs each with 512 MB of main memory, we are able to render 12-megapixel images of a 13-million-triangle model with 99.3% of accuracy at 10.8 frames  ...  We present a sort-first parallel system for out-of-core rendering of large models on clusterbased tiled displays.  ...  In this paper, we present a parallel rendering system that exploits the power of a cluster of inexpensive PCs to render high-resolution images of large models at interactive frame rates on a tiled display  ... 
doi:10.1016/s0167-8191(02)00249-1 fatcat:wj4jo3hp4bfldi3j7demnnw3aq

Building and using a scalable display wall system

K. Li, H. Chen, Y. Chen, D.W. Clark, P. Cook, S. Damianakis, G. Essl, A. Finkelstein, T. Funkhouser, T. Housel, A. Klein, Z. Liu (+6 others)
2000 IEEE Computer Graphics and Applications  
To further improve the performance, we use parallel decoding on a PC cluster.  ...  The image viewer contains two parts: a controller program and an imageviewer program. An image viewer program runs on every PC in the display cluster.  ... 
doi:10.1109/38.851747 fatcat:56lbb7crvjgxbkmaiwj3izxxau

Development and Performance Evaluation Of A Lan-Based EDGE-Detection Tool

Ghassan F. Issa
2012 International Journal of Soft Computing  
For equivalent calculations, the computation times on a single computer and a LAN of various number of computers, are estimated, and the resulting speedup and parallelization efficiency, are computed.  ...  The estimated results demonstrated that parallelization efficiencies achieved vary between 87% to 60% when the number of computers on the LAN varies between 2 to 5 computers connected through 10/100 Mbps  ...  Qiu et. al.[27] developed fast parallel stereo matching parallel algorithm on home-based software DSM JIAJIA. A cluster of 8 P-II PCs connected by a 100 Mbps switched Ethernet was used.  ... 
doi:10.5121/ijsc.2012.3110 fatcat:577i4svyifgwrpzfevrozqv5de

Building Rome on a Cloudless Day [chapter]

Jan-Michael Frahm, Pierre Fite-Georgel, David Gallup, Tim Johnson, Rahul Raguram, Changchang Wu, Yi-Hung Jen, Enrique Dunn, Brian Clipp, Svetlana Lazebnik, Marc Pollefeys
2010 Lecture Notes in Computer Science  
This paper introduces an approach for dense 3D reconstruction from unregistered Internet-scale photo collections with about 3 million images within the span of a day on a single PC ("cloudless").  ...  Our method advances image clustering, stereo, stereo fusion and structure from motion to achieve high computational performance.  ...  [2] parallelize the matching process and use approximate nearest neighbor search and query expansion [21] on a cluster of 62 machines each one comparable to our single PC.  ... 
doi:10.1007/978-3-642-15561-1_27 fatcat:suyl53jywvgelcfnopxbqew5jy

A Parallel Implementation of Non-rigid Registration Using a Volumetric Biomechanical Model [chapter]

M. Sermesant, O. Clatz, Z. Li, S. Lantéri, H. Delingette, N. Ayache
2003 Lecture Notes in Computer Science  
In this paper, we propose a patient-specific biomechanical model based on block-matching in order to register two MR images of the same patient with a parallel implementation.  ...  Then we describe in more details the parallel implementation of the algorithm. Finally we present a retrospective registration study made of four pre/post operative MRI pairs.  ...  PC cluster, the communication time is very reduced, as the network is not slowed down by other tasks.  ... 
doi:10.1007/978-3-540-39701-4_42 fatcat:xth2hvcic5gp7ppe67tr6jjwpa

Tile-based level of detail for the parallel age

Krzysztof Niski, Jonathan D. Cohen
2007 IEEE Transactions on Visualization and Computer Graphics  
We demonstrate our approach on parallel configurations consisting of both single PCs and a cluster of PCs.  ...  Today's PCs incorporate multiple CPUs and GPUs and are easily arranged in clusters for high-performance, interactive graphics.  ...  Much of the recent work in the area of parallel rendering has focused on using networked clusters of commodity PCs.  ... 
doi:10.1109/tvcg.2007.70587 pmid:17968084 fatcat:cxsobo3oxbepfbxcfwwg6mxz64

The Optimal High Performance Computing Infrastructure for Solving High Complexity Problem

Yuliant Sibaroni, Fitriyani Fitriyani, Fhira Nhita
2016 TELKOMNIKA (Telecommunication Computing Electronics and Control)  
Based on the experiments results, we conclude that the use of GA is very effective to solve TSP. the use of multi-core single-node in parallel for solving high complexity problems as far as this is still  ...  The current development trend leads to the development of PCs with higher specifications like this.  ...  In this study, individual evaluation process is conducted as a parallel process. This process is implemented in parallel on GPU and computer clusters.  ... 
doi:10.12928/telkomnika.v14i4.3586 fatcat:qbopvgplzfaprkkkpl34zyhhiq

Linked exploratory visualizations for uncertain MR spectroscopy data

David Feng, Lester Kwock, Yueh Lee, Russell M. Taylor II, Chaomei Chen, Jinah Park, Ming C. Hao, Pak C. Wong
2010 Visualization and Data Analysis 2010  
Using MRS, radiologists generate multiple 3D scalar fields of metabolite concentrations within the brain and compare them to anatomical magnetic resonance imaging.  ...  We describe two novel contributions to parallel coordinates visualizations: linear function brushing and new axis construction.  ...  CISMM is supported by the NIH National Institute of Biomedical Imaging and Bioengineering (NIH P41-EB002025).  ... 
doi:10.1117/12.839818 pmid:21152337 pmcid:PMC2997734 dblp:conf/vda/FengKLT10 fatcat:2drqp2i6irbstol7zf7pjr7xk4

FILAMENTARY STRUCTURE OF STAR-FORMING COMPLEXES

Philip C. Myers
2009 Astrophysical Journal  
Such "hub-filament structure" is associated with all of the nine young stellar groups within 300 pc, forming low-mass stars.  ...  Systems with many filaments tend to have parallel filaments with similar spacing.  ...  In the 0.85 mm image, the hub resolves into four bright peaks, two lying within nearly parallel filaments having length and separation~0.4 pc.  ... 
doi:10.1088/0004-637x/700/2/1609 fatcat:xblmohfrujbv3nuze4dd76qocm

Fast direct image retrieval for mechanical drawings management by using parallel processing
機械設計図における図面要素の高速検索システムに関する研究(第二報 高精度化と並列処理による高速化)

Itaru NAGAYAMA
2016 Transactions of the JSME (in Japanese)  
The system is designed with PC-cluster that consistes of one master node and eight slave nodes.  ...  The parallel processing uses many rotated templates of a target symbol to perform pattern matching by each slave node.  ...  Fig. 2 2 Interlaced matching. Fig. 3 Increasing of local similarity. Fig. 4 4 Fig. 4 Precise searching process. Fig. 9 9 Parallel processing with rotation templates.  ... 
doi:10.1299/transjsme.15-00278 fatcat:k44jhjpnabg7darshpdbywp6he

Towards highly parallel event processing through reconfigurable hardware

Mohammad Sadoghi, Harsh Singh, Hans-Arno Jacobsen
2011 Proceedings of the Seventh International Workshop on Data Management on New Hardware - DaMoN '11  
achieve line-rate processing by exploring various degrees of parallelism.  ...  Therefore, each solution is formulated as a design trade-off between the degree of parallelism versus the desired application requirement.  ...  Since all BMUs are ran in parallel and in sync with each other, the DISPATCHER must dispense the next cluster address only when all BMUs have completed matching all subscriptions in the current cluster  ... 
doi:10.1145/1995441.1995445 dblp:conf/damon/SadoghiSJ11 fatcat:pllgpwvx7zbc3hw2g2ja4tzcgi

Multilevel SIFT Matching for Large-Size VHR Image Registration

Chunlei Huo, Chunhong Pan, Leigang Huo, Zhixin Zhou
2012 IEEE Geoscience and Remote Sensing Letters  
Index Terms-Coarse-to-fine strategy, geometric constraint, large-size image registration, parallel-based architecture.  ...  Refined registration is achieved by blockwise SIFT matching and global optimization on the whole matched keypoints based on iterative reweighted least squares.  ...  page_id=36) for providing the QuickBird images and the anonymous reviewers for their suggestions to improve this letter.  ... 
doi:10.1109/lgrs.2011.2163491 fatcat:lj2qxco3uzcq5dgrr5lkikzz7u
« Previous Showing results 1 — 15 out of 41,384 results