检索结果-内蒙古大学图书馆

Proceedings of the 5th IEEE Symposium on parallel and distributed processing

作者： Lam, K.P. Horne, E. Univ of Kent Canterbury United Kingdom

ISBN: (纸本)081864222X

Non-linear filters have been used in many signal processing applications, for example, to obtain optimum signal extraction or detection in the presence of random noise. The weighted median filter (WMF), of which the standard median is a special case, is a novel non-linear technique designed for 2D image processing. A major advantage of the WMF is its flexibility in design to deal with a wide variety of properties. This paper describes a commonly used class W(4,4,1) of the WMF. As with most non-linear methods, the computational demands of this technique are high and require a non-trivial number of `expensive' operations. A data parallel approach for efficient implementation of the WMF is described and implemented on two architecturally dissimilar supercomputers, the Convex C3840 and the Connection Machine CM-200. An analysis of the performance obtained from these two high performance parallel platforms is presented.

关键词： parallel processing systems

来源：评论

学校读者我要写书评

暂无评论

Neural and Stochastic methods in image and Signal processing ii

Neural and Stochastic Methods in Image and Signal Processing...

引用

Neural and Stochastic methods in image and Signal processing ii 1993

The proceedings contain 29 papers. The topic discussed include: algorithm for classification of multispectral data and its implementation on a massively parallel computer;convergence measure and some parallel aspects of Markov-chain Monte Carlo algorithms;evidential reasoning based on Dempster-Shafer theory and its application to medical image analysis;cluster approximations for statistical image processing;image recovery and segmentation using competitive learning in a layered network;feature competition and domain of attraction in artificial-perceptron pattern recognizer;and probabilistic spectral feature extraction technique for neural networks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The fast discrete radon transform - I: Theory

引用

IEEE TRANSACTIONS ON image processing 1993年第3期2卷 382-400页

作者： Kelley, Brian T. Madisetti, Vijay K. Georgia Inst Technol Sch Elect Engn Natl Ctr Excellence DSP Atlanta GA 30332 USA

A new inversion scheme for reconstruction of images from projections based upon the slope-intercept form of the discrete Radon transform is presented. A seminal algorithm for the forward and the inverse transforms was proposed by Beylkin in 1987. However, as proposed, the original algorithm demonstrated poor dispersion characteristics for steep slopes and could not invert transforms based upon nonlinear slope variations. By formulating the computation as a discrete computation of the continuous Radon transform formula, we explicitly derive fast new generalized inversion methods that overcome the original shortcomings. The generalized forward (FRT) and inverse algorithm (IFRT) proposed are fast, eliminate interpolation calculations, and convert directly between a raster scan grid and a rectangular/polar grid in one step. Part ii of this paper describes the implementation of the algorithm on a massively parallel computer, and a new time-domain formulation.

关键词： Discrete transforms image reconstruction Grid computing Geophysics computing Concurrent computing Time domain analysis Application software Tomography Ultrasonic imaging

来源：评论

学校读者我要写书评

暂无评论

ON THE parallel-processing OF RUNLENGTH-ENCODED (RLE) BOOLEAN imageRY .1. RLE TRANSFORMATION, ARITHMETIC, AND GLOBAL-REDUCE OPERATIONS 2

ON THE PARALLEL-PROCESSING OF RUNLENGTH-ENCODED (RLE) BOOLEA...

引用

CONF ON SIGNAL processing, SENSOR FUSION, AND TARGET RECOGNITION 2

作者： SCHMALZ, MS Department of Computer and Information Sciences University of Florida Gainesville 32611 FL United States

ISBN: (纸本)0819411914

The processing of Boolean imagery compressed by runlength encoding (RLE) frequently exhibits greater computational efficiency than the processing of uncompressed imagery, due to the data reduction inherent in RLE. In a previous publication [1], we outlined general methods for developing operators that compute over RLE Boolean imagery. In this paper, we present sequential and parallel algorithms for a variety of operations over RLE imagery, including the customary arithmetic and logical Hadamard operations, as well as the global reduce functions of image sum and maximum. RLE neighborhood-based operations, as well as the more advanced RLE operations of linear transforms, connected component labelling, and pattern recognition are presented in the companion paper [2]. For example, given the uncompressed image domain X and the compressed domain Y, we show that RLE encoding and decoding can be computed in 0(log(|Y|)) time, using only addition, comparison, and tuple construction. Similarly, the unary arithmetic operations can be computed in 0(|Y|) time sequentially, and in unitary time with 0(|Y|) parallelism. We further show that the binary arithmetic operations, which were previously thought to be inherently sequential, are amenable to k-fold decimation, and thus yield a parallel time complexity of 0(log(|Y|)-log(k)) operations over the compressed image. Likewise, the global reduce operations can be computed in parallel in 0(log(|Y|)) time, with sufficient processors. Since |Y| > |X| is usual, significant computational speedup can be achieved in practice. © 1993 SPIE. All rights reserved.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

AN ALGORITHM FOR CLASSIFICATION OF MULTISPECTRAL DATA AND ITS IMPLEMENTATION ON A MASSIVELY-parallel COMPUTER 2

AN ALGORITHM FOR CLASSIFICATION OF MULTISPECTRAL DATA AND IT...

引用

CONF ON NEURAL AND STOCHASTIC methods IN image AND SIGNAL processing 2

作者： SHAHSHAHANI, BM LANDGREBE, DA School Of Electrical Engineering Purdue University West Lafayette 47906 IN United States

ISBN: (纸本)0819412813

A new method for classification of multi-spectral data is proposed. This method is based on fitting mixtures of multivariate Gaussian components to training and unlabeled samples by using the EM algorithm. Through a backtracking search strategy with appropriate depth bounds, a series of mixture models are compared. The validity of the candidate models are evaluated by considering their description lengths and allocation rates. The most suitable model is selected and the multi-spectral data are classified accordingly. The EM algorithm is mapped onto a massively parallel computer system to reduce the computational cost. Experimental results show that the proposed algorithm is more robust against variations in training samples than the conventional supervised Gaussian maximum likelihood classifier. © 1993 SPIE. All rights reserved.

关键词： Mixtures

来源：评论

学校读者我要写书评

暂无评论

SQUARE-ROOT FILTERING IN TIME-SEQUENTIAL ESTIMATION OF RANDOM-FIELDS

SQUARE-ROOT FILTERING IN TIME-SEQUENTIAL ESTIMATION OF RANDO...

引用

CONF ON VIDEO AND image processing

作者： CHIN, TM KARL, WC MARIANO, AJ WILLSKY, AS Univ. of Miami (United States) Massachusetts Institute of Technology (United States)

ISBN: (纸本)0819411361

As a time-sequential and Bayesian front-end for image sequence processing, we consider the square root information (SRI) realization of Kalman filter. The computational complexity of the filter due to the dimension of the problem -- the size of the state vector is on the order of the number of pixels in the image frame -- is decreased drastically using a reduced-order approximation exploiting the natural spatial locality in the random field specifications. The actual computation for the reduced-order SRI filter is performed by an iterative and distributed algorithm for the unitary transformation steps, providing a potentially faster alternative to the common QR factorization-based methods. For the space-time estimation problems, near- optimal solutions can be obtained in a small number of iterations (e.g., less than 10), and each iteration can be performed in a finely parallel manner over the image frame, an attractive feature for a dedicated hardware implementation.

关键词： Filtering (signal processing) image processing Electronic filtering Matrices image filtering Video processing Chemical elements Digital filtering Optimal filtering Information operations

来源：评论

学校读者我要写书评

暂无评论

Convergence measure and some parallel aspects of Markov-chain Monte Carlo algorithms

Convergence measure and some parallel aspects of Markov-chai...

引用

Neural and Stochastic methods in image and Signal processing ii

作者： Malfait, Maurits J. Roose, Dirk Vandermeulen, Dirk

ISBN: (纸本)0819412813

We examine methods to assess the convergence of Markov chain Monte Carlo (MCMC) algorithms and to accelerate their execution via parallel computing. We propose a convergence measure based on the deviations between simultaneously running MCMC algorithms. We also examine the acceleration of MCMC algorithms when independent parallel sampler are used and report on some experiments with coupled samplers. As applications we use small Ising model simulations and a larger medical image processing algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

QUANTITATIVE-ANALYSIS OF GEL ELECTROPHORETOGRAMS BY image-ANALYSIS AND LEAST-SQUARES MODELING

引用

ELECTROPHORESIS 1993年第7期14卷 601-612页

作者： VOHRADSKY, J PANEK, J CZECHOSLOVAK ACAD SCI INST MICROBIOL CS-11142 PRAGUE 1 CZECHOSLOVAKIA

A computer-aided quantitative method for a complex analysis of gel electrophoretograms is presented. The analysis consists of several steps: (i) determination of the background image by methods of mathematical morphology and its subtraction from the gel image, (ii) selection of an appropriate part of the gel lane including curved lanes and lanes with a nonuniform width, (iii) computation of the lane densitogram by averaging several lane-parallel scans, (iv) decomposition of the lane densitogram into component bands using a data selecting algorithm and Marquardt's minimizer. Several different functions for component bands are utilized. It is shown that the densitogram can be decomposed into component bands with reasonable accuracy only if an appropriate model function is chosen. The algorithms are tested on several different gel electrophoretograms which show typical features as a nonuniform background, curved lanes, an asymmetrical band shape and a superposition of small bands on the shoulders of big ones. It is shown that overlapped bands are best approximated by an asymmetrical Gaussian curve and an asymmetrical Gauss-Cauchy function. Linear response to the serial dilution of the protein sample is tested.

关键词： Densitometry DNA, Bacterial/analysis Electrophoresis, Agar Gel/methods Electrophoresis, Polyacrylamide Gel/methods Escherichia coli/genetics image processing, Computer-Assisted Least-Squares Analysis Mathematics Molecular Weight Plasmids Proteins/chemistry Ribosomal Proteins/analysis Streptomyces aureofaciens/chemistry

来源：评论

学校读者我要写书评

暂无评论

Edge detection on massively parallel machines: a local threshold approach

Edge detection on massively parallel machines: a local thres...

引用

Euromicro Workshop on parallel and distributed processing

作者： N. Scarabottolo D. Sorrenti M. Spertini Dipartimento di Elettronica e Informazione Politecnico di Milano Milano Italy

Describes an approach to edge detection particularly suited for implementation on distributed-memory massively parallel MIMD machines. One of the main tasks of this work is the identification of an optimal edge threshold, i.e. the value of the luminance gradient allowing one to identify actual edge pixels. Such identification has been done by adopting a local approach, where the image is a-priori partitioned into small square windows, and the optimal threshold is selected by ranking the outputs produced by several thresholds inside each window. The innovative contributions of this work lie in the fact that, by partitioning the image in suitably small windows, the probability of having only one edge chain in each window is maximized (thus enhancing the effectiveness of the optimal threshold selection criterion), and the scalability of the application is ensured (due to the high number of simple processing tasks into which the algorithm is subdivided).< >

关键词： image edge detection parallel machines Smoothing methods Partitioning algorithms Low pass filters Scalability Concurrent computing Pixel Algorithm design and analysis

来源：评论

学校读者我要写书评

暂无评论

A data-parallel approach to the implementation of weighted medians technique on parallel/super-computers

A data-parallel approach to the implementation of weighted m...

引用

International Symposium on parallel and distributed processing (IPDPS)

作者： K.P. Lam E. Horne Computing Laboratory University of Kent Canterbury UK University of Kent Canterbury Kent GB Kent Univ. Canterbury UK

Nonlinear filters have been used in many signal processing applications, for example, to obtain optimum signal extraction or detection in the presence of random noise. The weighted median filter (WMF), of which the standard median is a special case, is a novel nonlinear technique designed for 2D image processing. A major advantage of the WMF is its flexibility in design to deal with a wide variety of properties. This paper describes a commonly used class W(4,4,1) of the WMF. AS with most nonlinear methods, the computational demands of this technique are high and require a non-trivial number of "expensive" operations. A data parallel approach for efficient implementation of the WMF is described and implemented on two architecturally dissimilar supercomputers, the Convex C3840 and the Connection Machine CM-200. An analysis of the performance obtained from these two high performance parallel platforms is presented.< >

关键词： Filters Concurrent computing Laboratories image processing image converters Performance analysis Control systems parallel algorithms parallel processing parallel architectures

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：