检索结果-内蒙古大学图书馆

International Conference on Manufacturing Automation 1992

作者： Poon, Ting-Chung Pieper, Ronald J. Optical Image Processing Laboratory Bradley Department of Electrical Engineering Virginia Polytechnic Institute State University BlacksburgVA24061 United States Department of Electrical and Computer Engineering Naval Postgraduate School MontereyCA93943 United States

Two commonly used optical correlation techniques, matched spatial filtering and joint-Fourier transform correlation, are briefly reviewed. A recently proposed real-time joint-Fourier transform correlation is then disc... 详细信息

关键词： Fourier transforms

来源：评论

学校读者我要写书评

暂无评论

On empirical estimation of the parameters of edge enhancement filters

On empirical estimation of the parameters of edge enhancemen...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： A.A. Farag Y. Cao D.M. Rose E.J. Delp Engineering Mathematics & Computer Science Department Speed Scientific School University of Louisville Louisville KY USA Computer Vision & Image Processing Laboratory School of Electrical Engineering Purdue University West Lafayette IN USA

The authors develop an empirical measure for the selection of the Gaussian filter that is commonly used for edge enhancement. The measure is based totally on the image at hand. Edge enhancement by a Gaussian filter has two distinct advantages: (1) the filter is fully described by a single parameter, the standard deviation sigma ; (2) the two-dimensional filter is separable and can be easily implemented. The filter's spatial support is a function of sigma . This support is normally in the range of +or-3.5 sigma . An empirical measure is described for the selection of the Gaussian filter's spatial support using the power spectrum density of the input image. Classic Fourier analysis is used to obtain a measure for the spatial support of the Gaussian filter given a particular image. Experimental results suggest that this measure can be used as an aid in deciding the Gaussian filter's spatial support needed to enhance the edges.< >

关键词： Parameter estimation Low pass filters image edge detection image segmentation Joining processes Smoothing methods Frequency estimation Density functional theory Shape mathematics

来源：评论

学校读者我要写书评

暂无评论

BRINGING THE GRANDMOTHER BACK INTO THE PICTURE: A MEMORY-BASED VIEW OF OBJECT RECOGNITION

引用

International Journal of Pattern Recognition and Artificial Intelligence 1992年第1期6卷 37-61页

作者： SHIMON EDELMAN TOMASO POGGIO Center for Biological Information Processing Department of Brain and Cognitive Sciences MIT Cambridge MA 02139 USA Present address: Department of Applied Mathematics and Computer Science The Weizmann Institute of Science Rehovot 76100 Israel.

We describe experiments with a versatile pictorial prototype-based learning scheme for 3-D object recognition. The Generalized Radial Basis Function (GRBF) scheme seems to be amenable to realization in biophysical hardware because the only kind of computation it involves can be effectively carried out by combining receptive fields. Furthermore, the scheme is computationally attractive because it brings together the old notion of a "grandmother" cell and the rigorous approximation methods of regularization and splines.

关键词： Artificial neural network object recognition vision learning radial basis functions approximation

来源：评论

学校读者我要写书评

暂无评论

image SEQUENCE CODING BY SPLIT AND MERGE

引用

IEEE TRANSACTIONS ON COMMUNICATIONS 1991年第12期39卷 1845-1855页

作者： WILLEMIN, P REED, TR KUNT, M Signal and Image Processing Laboratory Swiss Federal Institute of Technology Lausanne Switzerland Department of Electrical Engineering and Computer Science University of California Davis CA USA

This paper describes a method for reducing the information contained in an image sequence, while retaining the information necessary for the interpretation of the sequence by a human observer. The method consists of first locating the redundant information, reducing the degree of redundancy, and coding the result. The sequence is treated as a single 3-D data volume, the voxels of which are grouped into several regions, obtained by a 3-D split and merge algorithm. To find these regions, we first obtain an initial region space by splitting the image sequence until the gray-level variation over each region can be approximated by a 3-D polynomial, to a specified accuracy. This results in a set of parallelepipedic regions of various sizes. To represent the gray-level variation over these regions, the coefficients of the approximating polynomial are used as features. The most similar regions are then merged, using a region adjacency graph. The information is coded by representing the borders of the regions using a pyramidal structure in the x, y, t space. The coefficients of the approximating polynomials are coded in a straightforward manner. For 256 x 256 pixel, 25 frames/s image sequences, compressions allowing transmission rates near 64 kbit/s are obtained.

关键词： image sequences image coding Pixel Bandwidth Layout Polynomials image segmentation Humans Helium ISDN

来源：评论

学校读者我要写书评

暂无评论

A THREE-LAYER ADAPTIVE NETWORK FOR PATTERN DENSITY ESTIMATION AND CLASSIFICATION

引用

International Journal of Neural Systems 1991年第3期2卷 211-220页

作者： Jian-xiong Wu Chorkin Chan Department of Computer Science University of Hong Kong Hong Kong Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University P.R.C

Based on the assumption that most probability densities in real life can be approximated by a mixture of Gaussian densities, we propose here a three-layer adaptive network with each neuron in the lower hidden layer representing a Gaussian basis function (covariance matrix equal to where I is a unit matrix) to estimate various probability densities and serve as a Bayes classifier. The width of the basis function may be the same for all neurons in this layer or it may vary from one neuron to another. This paper investigates the effectiveness of the network for both cases and presents a localized learning algorithm to adjust the network parameters. The network was trained with artificial data derived from known mixtures of memoryless Gaussian sources as well as exponential and Gamma densities. The performance of the network as a pattern density estimator was measured in terms of the relative difference between the target probability density function (p.d.f.) which generates the training and testing data and the network output representing the estimation. Samples from two mixtures corresponding to two classes were used to test the network capability as a classifier by comparing its error rate against that of a Bayes classifier. Both one- and two-dimensional cases were explored. The successfulness of the network depended on how well the target p.d.f.’s were represented by the training samples, the number of hidden neurons employed in the network and how thoroughly the network was trained. It was also found that allowing each basis function to have an independent width had a predominant effect on the network performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automatic custom layout of analog ICs using constraint-based module generation

Automatic custom layout of analog ICs using constraint-based...

引用

Custom Integrated Circuits Conference (CICC)

作者： D.J. Chen B.J. Sheu Department of Electrical Engineering and Computer Science and Signal and Image Processing Institute University of Southern California Los Angeles CA USA

A systematic method for automatic custom layout of analog integrated circuits is presented. This method uses analog circuit recognition and critical net analysis techniques to derive proper layout constraints for analog circuit performance optimization. Constraint-driven analog floorplanning and routing techniques are developed to generate custom layouts which incorporate the layout constraints. This method can be applied to handle a wide variety of analog circuit modules as well as analog subsystems. Experimental results on CMOS operational amplifiers and a comparator are presented.< >

关键词： Analog circuits Circuit synthesis Routing Automation Degradation Circuit noise Coupling circuits Circuit analysis Signal generators Signal processing

来源：评论

学校读者我要写书评

暂无评论

A path metric for sequential search and its application in edge linking

A path metric for sequential search and its application in e...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： A.A. Farag E.J. Delp Engineering Mathematics & Computer Science Department Speed Scientific School University of Louisville Louisville KY USA Computer Vision & Image Processing Laboratory School of Electrical Engineering Purdue University West Lafayette IN USA

The authors develop a path metric for sequential search based on the linear model. The metric forms the heart of an edge-linking algorithm that combines edge elements enhanced by an optimal filter. From a starting node, transitions are made to the goal nodes by a maximum likelihood metric. This metric requires only local calculations on the search space and its use in edge linking provides more accurate results than other linking techniques.< >

关键词： Joining processes image edge detection Filters Application software Heart Layout Decoding mathematics computer science computer vision

来源：评论

学校读者我要写书评

暂无评论

A VLSI neuroprocessor for real-time image flow computing

A VLSI neuroprocessor for real-time image flow computing

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Wai-Chi Fang B.J. Sheu Ji-Chien Lee Advanced Computer Systems and Technology Section California Institute of Technology Pasadena CA USA Department of Electrical Engineering Signal and Image Processing Institute University of Southern California Los Angeles CA USA

A locally connected multi-layer stochastic neural network and its associated VLSI array neuroprocessors have been developed for high-performance image flow computing systems. An extendable VLSI neural chip has been designed with a silicon area of 4.6*6.8 mm/sup 2/ in a MOSIS 2 mu m scalable CMOS process. The mixed analog-digital design techniques are utilized to achieve compact and programmable synapses with gain-adjustable neurons and winner-take-all cells for massively parallel neural computation. Hardware annealing through the control of the neurons' gain helps to efficiently search the optimal solutions. Computing of image flow using one 2 mu m 72-neuron neural chip can be accelerated by a factor of 187 more than a Sun-4/260 workstation. Real-time image flow processing on industrial images is practical using an extended array of VLSI neural chips. Actual examples on moving trucks are presented.< >

关键词： Very large scale integration Neural network hardware Neurons Stochastic systems Neural networks Multi-layer neural network computer networks Silicon CMOS process Analog-digital conversion

来源：评论

学校读者我要写书评

暂无评论

NC algorithms for finding depth-first-search trees in interval graphs and circular-arc graphs

NC algorithms for finding depth-first-search trees in interv...

引用

IEEE Southeastcon

作者： Y. Liang C. Rhee S.K. Dhall S. Lakshmivarahan School of Electrical Engineering and Computer Science Parallel Processing Institute University of Oklahama Norman OK USA Department of Mathematics Statistics and Computer Science Eastern Kentucky University Richmond KY USA

Finding depth-first-search (DFS) trees of graphs is one of the fundamental problems in graph theory which has many practical applications. However, there exists no NC parallel algorithm for this problem in general graphs. NC parallel algorithms for finding DFS trees for the interval graphs and circular-arcs graphs are presented. These algorithms take O(log n) time using kappa n processors on the EREW model, where kappa is the number of cliques in a graph of n nodes.< >

关键词： Tree graphs Parallel algorithms computer science Read-write memory Parallel processing mathematics Statistics Graph theory Application software Spine

来源：评论

学校读者我要写书评

暂无评论

Real-time high-ratio image compression using adaptive VLSI neuroprocessors

Real-time high-ratio image compression using adaptive VLSI n...

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： B.J. Sheu W.-C. Fang Department of Electrical Engineering Signal and Image Processing Institute University of Southern California Los Angeles CA USA Jet Propulsion Laboratory Advanced Computer Systems and Technology Section California Institute of Technology Pasadena CA USA

An adaptive VLSI neuroprocessor based on vector quantization algorithm has been developed for real-time high-ratio image compression applications. This VLSI neural-network-based vector quantization (NNVQ) module combines a fully parallel vector quantizer with a pipelined codebook generator for a broad area of data compression applications. The NNVQ module is capable of producing good-quality reconstructed data at high compression ratios more than 20. The vector quantizer chip has been designed, fabricated, and tested. It contains 64 inner-product neural units and a high-speed extendable winner-take-all block. This mixed-signal chip occupies a compact silicon area of 4.6*6.8 mm/sup 2/ in a 2.0- mu m scalable CMOS technology. The throughput rate of the 2- mu m NNVQ module is 2 million vectors per second and its equivalent computation power is 3.33 billion connections per second.< >

关键词： image coding Very large scale integration Vector quantization Neural networks Data compression High performance computing Clustering algorithms Application software image reconstruction CMOS technology

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：