检索结果-内蒙古大学图书馆

Reducing memory bottlenecks in embedded, parallel image processors

ELECTRONICS LETTERS 2003年第1期39卷 33-35页

作者： McBader, S Lee, P NeuriCam SpA Res & Dev I-38100 Trent Italy Univ Kent Elect Engn Lab Canterbury CT2 7NT Kent England

Owing to the sequential nature of memory interfaces, as well as the growing processor-memory performance gap, the design of parallel image processors is often faced with a challenge in deciding memory organisation and distribution. This work addresses the problem of memory access bottlenecks in parallel digital image processors and presents one solution which demonstrates up to 93.4% reduction over standard sequential methods.

关键词： image processing parallel memories DMA channel distributed memory systems Computer vision and image processing techniques parallel image processor design Xilinx XCV200E FPGA embedded systems memory distribution Storage system design memory organisation parallel architecture embedded parallel image processors Multiprocessing systems sequential memory interfaces memory access bottleneck reduction processor-memory performance gap

来源：评论

学校读者我要写书评

暂无评论

parallel deconvolution methods for three dimensional image restoration

Parallel deconvolution methods for three dimensional image r...

引用

Conference on Advanced Signal processing Algorithms Architectures and Implementations XiiI

作者： Lewis, B Reichel, L LLC Rocketcalc Richfield OH 44286 USA

Restoration by deconvolution of three-dimensional images that have been contaminated by noise and spatially invariant blur is computationally demanding. We describe efficient parallel implementations of iterative meth... 详细信息

ISBN: (纸本)0819450782

关键词： image restoration ill-posed problem Krylov iterative methods parallel computation

来源：评论

学校读者我要写书评

暂无评论

MedIGrid: A medical imaging application for computational Grids

MedIGrid: A medical imaging application for computational Gr...

引用

International parallel and distributed processing Symposium, IPDPS 2003

作者： Bertero, M. Bonetto, P. Carracciuolo, L. D'Amore, L. Formiconi, A. Guarracino, M.R. Laccetti, G. Murli, A. Oliva, G. Department of Computer and Information Science University of Genoa Italy Institute for High Performance Computing and Networking CNR Naples Italy Department of Clinical Phisiopatology University of Florence Italy Department of Mathematics and Applications University of Naples Federico II Italy

ISBN: (纸本)0769519261

In the last decades, diagnosing medical images has heavily relied on digital imaging. As a consequence, huge amounts of data produced by modern medical instruments need to be processed, organized, and visualized in a suitable response time. Many efforts have been devoted to the development of digital Picture Archiving and Communications Systems (PACS) which archive and distribute image information across a hospital and provide Web access to avoid the expensive deployment of a large number of such systems. On the other hand, this approach does not solve problems related to the increasing demand of high performance computing and storage facilities, which cannot be placed within a hospital. In this work we describe MedIGrid, an application that enables nuclear doctors to transparently use high performance computers and storage systems for the PET/SPECT (Positron Emission Tomography/Single Photon Emission Computed Tomography) image processing, management, visualization and analysis. MedIGrid is the result of the joint efforts of a group of researchers committed to the development of a distributed application to test and deploy new reconstruction methods in clinical environments. The outcomes of this work include a set of platform independent software tools to read medical images, control the execution of computing intensive tomographic algorithms, and explore the reconstructed tomographic volumes. In the paper we describe how the collaboration among different research groups has contributed to the integration of the application into a single framework. The results of our work are discussed. © 2003 IEEE.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

A divided-screenwise hierarchical compositing for sort-last parallel volume rendering

A divided-screenwise hierarchical compositing for sort-last ...

引用

International parallel and distributed processing Symposium, IPDPS 2003

作者： Ino, Fumihiko Sasaki, Tomomitsu Takeuchi, Akira Hagihara, Kenichi Graduate School of Information Science and Technology Osaka University 1-3 Machikaneyama Toyonaka Osaka560-8531 Japan Graduate School of Engineering Science Osaka University 1-3 Machikaneyama Toyonaka Osaka560-8531 Japan Toyota Motor Corporation Japan

ISBN: (纸本)0769519261

In this work, to render at least 5123 voxel volumes in real-time, we have developed a sort-last parallel volume rendering method for distributed memory multiprocessors. Our sort-last method consists of two methods, Hsu's (1993) segmented ray casting and our divided-screenwise hierarchical (DSH) compositing, in which each processor produces a subimage and merges all the produced subimages into the final image. This paper describes the DSH method, which aims at achieving high performance compositing on a large number of processors. Our implementation on a 64-node PC cluster can composite a 5122 pixel image about twice as fast as an existing method, the binary-swap method, so that can render a 512×512×224 voxel volume at approximately eight frames per second (fps). © 2003 IEEE.

关键词： Volume rendering

来源：评论

学校读者我要写书评

暂无评论

Utilizing support vector machines for the characterization of digital dermatological images

Utilizing support vector machines for the characterization o...

引用

Proceedings of the International Conference on parallel and distributed processing Techniques and Applications

作者： Maglogiannis, Ilias Zafiropoulos, Elias P. University of the Aegean Dept. of Infor. and Comm. Syst. Eng. 83200 Karlovasi Greece Sch. of Electrical and Comp. Eng. National Technical Univ. of Athens 9 Iroon Polytecnheiou St. GR15773 Athens Greece

ISBN: (纸本)1892512416

In this paper we discuss an efficient methodology for the image analysis and characterization of digital images containing skin lesions. The methodology is based on the support vector machines algorithm for data classification and it has been applied to the problem of the recognition of malignant melanoma versus dysplastic nevus. Border and color based features were extracted from digital images of skin lesions acquired under reproducible conditions, using basic image processing techniques. Although larger sample sizes are necessary to resolve these issues fully, the support vector machines algorithm performed excellently achieving a high percentage of correct classification (approximately 100%). Two other classification methods, the statistical discriminant analysis and the application of neural networks were applied also to the same problem and their efficiency was compared with the support vector machines algorithm performance.

关键词： image processing

来源：评论

学校读者我要写书评

暂无评论

Several parallel algorithms for solving nonlinear systems with symmetric and positive definite Jacobians

Several parallel algorithms for solving nonlinear systems wi...

引用

International parallel and distributed processing Symposium, IPDPS 2003

作者： Peinado, Jesús Vidal, Antonio M. Departamento de Sistemas Informáticos y Computación Universidad Politécnica de Valencia Apartado 22012 Valencia46071 Spain

ISBN: (纸本)0769519261

In this work we describe two sequential algorithms and their parallel counterparts for solving nonlinear systems, when the Jacobian matrix is symmetric and positive definite. This case appears frequently in unconstrained optimization problems. Both algorithms are based on Newton's method. The first solves the inner iteration with Cholesky decomposition while the second is based on the inexact Newton methods family, where a preconditioned CG method has been used for solving the linear inner iteration. In this latter case and to control the inner iteration as far as possible and avoid the oversolving problem, we also parallelized several forcing term criteria and used parallel preconditioning techniques. We implemented the parallel algorithms using the SCALAPACK library. Experimental results have been obtained using a cluster of Pentium ii PC connected through a Myrinet network. To test our algorithms we used four different problems. The algorithms show good scalability in most cases. © 2003 IEEE.

关键词： parallel algorithms

来源：评论

学校读者我要写书评

暂无评论

International Symposium on parallel and distributed processing and Applications, ISPA 2003

International Symposium on Parallel and Distributed Processi...

引用

International Symposium on parallel and distributed processing and Applications, ISPA 2003

ISBN: (纸本)9783540376194

The proceedings contain 43 papers. The special focus in this conference is on Applications on Web-Based, Intranet Systems, Optimization Techniques, Performance Evaluation of parallel Systems and Wireless Communication. The topics include: Localized algorithms and their applications in ad hoc wireless networks;towards a single system image for high-performance java;reliability of a distributed search engine for fresh information retrieval in large-scale intranet;a web-based graphical interface for general-purpose high-performance computing clusters;a compressed diagonals remapping technique for dynamic data redistribution on banded sparse matrix;scheduling parallel tasks onto NUMA multiprocessors with inter-processor communication overhead;an efficient algorithm for irregular redistributions in parallelizing compilers;balancing traffic in meshes by dynamic channel selection;an ad hoc on-demand routing protocol with alternate routes;design of a viable fault-tolerant routing strategy for optical-based grids;direct execution simulation of mobile agent algorithms;mpi-2 support in heterogeneous computing environment using an score cluster system;internet traffic congestion modelling and parallel distributed analysis;a comparative investigation into optimum-time synchronization protocols for a large scale of one-dimensional cellular automata;impact from mobile spam mail on mobile internet services;solving the set-splitting problem in sticker-based model and the Adleman-Lipton model;parallel MCGLS and ICGLS methods for least squares problems on distributed memory architectures;effective admission control for real-time anycast flow;a comprehensive software distributed shared memory system and a scheme of interactive data mining support system in parallel and distributed environment.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Block-level discrete cosine transform coefficients for autonomic face recognition

Block-level discrete cosine transform coefficients for auton...

引用

作者： Scott, Willie L., ii Louisiana State University and Agricultural & Mechanical College

学位级别：Ph.D.

This dissertation presents a novel method of autonomic face recognition based on the recently proposed biologically plausible network of networks (NoN) model of information processing. The NoN model is based on locally parallel and globally coordinated transformations. In the NoN architecture, the neurons or computational units form distributed networks, which themselves link to form larger networks. In the general case, an n-level hierarchy of nested distributed networks is constructed. This models the structures in the cerebral cortex described by Mountcastle and the architecture based on that proposed for information processing by Sutton. In the implementation proposed in the dissertation, the image is processed by a nested family of locally operating networks along with a hierarchically superior network that classifies the information from each of the local networks. The implementation of this approach helps obtain sensitivity to the contrast sensitivity function (CSF) in the middle of the spectrum, as is true for the human vision system. The input images are divided into N x N blocks to define the local regions of processing. The N x N two-dimensional Discrete Cosine Transform (DCT), a spatial frequency transform, is used to transform the data into the frequency domain. Thereafter, statistical operators that calculate various functions of spatial frequency in the block are used to produce a block-level DCT coefficient. The image is now transformed into a variable length vector that is trained with respect to the data set. The classification was done by the use of a backpropagation neural network. The proposed method yields excellent results on a benchmark database. The results of the experiments yielded a maximum of 98.5% recognition accuracy and an average of 97.4% recognition accuracy. An advanced version of the method where the local processing is done on offset blocks has also been developed. This has validated the NoN approach and further research using lo

关键词：

来源：评论

学校读者我要写书评

暂无评论

Block-LevelDiscrete Cosine Transform Coefficients for Autonomic Face Recognition

Block-LevelDiscrete Cosine Transform Coefficients for Autono...

引用

作者： Willie L. Scott, ii Louisiana State University and Agricultural and Mechanical College

学位级别：博士

关键词：

来源：评论

学校读者我要写书评

暂无评论

Education of photonic methods of information processing

Education of photonic methods of information processing

引用

4th International Conference on Photonics, Devices and Systems

作者： Klíma, M Páta, P Kaiser, J Czech Tech Univ Dept Radioelectr Fac Elect Engn Prague 16627 6 Czech Republic

ISBN: (纸本)0819448370

The submitted paper is describes a relevant experience in an introduction of photonic information processing techniques into the curricula of MSc course subject image processing and Photonics and PhD course subject Selected Parts from Photonics. The photonic information processing systems offer extensive computational power because of several advantages: the information carrier - photon - is the fastest one, massively parallel access and computation, some mathematical operations performed by physical effects (2D convolution, 2D Fourier transform).

关键词： Optical processors Photonics education optical 2D correlation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：