检索结果-内蒙古大学图书馆

36th IEEE computer Society International Conference - COMPCON Sping '91

作者： Jackel, L.D. Stenard, C.E. Baird, H.S. Boser, B. Bromley, J. Burges, C.J.C. Denker, J.S. Graf, H.P. Henderson, D. Howard, R.E. Hubbard, W. leCun, Y. Matan, O. Pednault, E. Satterfield, W. Sackinger, E. Thompson, T. AT&T Bell Lab Holmdel NJ USA

ISBN: (纸本)0818621346

The authors outline OCR (optical character recognition) technology developed at AT&T Bell Laboratories, including a recognition network that learns feature extraction kernels and a custom VLSI chip that is designed for neural-net image processing. It is concluded that both high speed and high accuracy can be obtained using neural-net methods for character recognition. Networks can be designed that learn their own feature extraction kernels. Special-purpose neural-net chips combined with digital signal processors can quickly evaluate character-recognition neural nets. This high speed is particularly useful for recognition-based segmentation of character strings.

关键词： Character Recognition, Optical

来源：评论

学校读者我要写书评

暂无评论

Discontinuity detection and thresholding-a stochastic approach

Discontinuity detection and thresholding-a stochastic approa...

引用

Conference on computer vision and Pattern Recognition (CVPR)

作者： D. Lee G.W. Wasilkowski AT and T Bell Laboratories Inc. Murray Hill NJ USA Department of Computer Science University of Kentucky Lexington KY USA

Detection and thresholding using a stochastic approach is discussed. A general form of detectors which includes a number of well-known detectors as special cases is discussed. Thresholding is indispensable to eliminate spurious responses from the detection process. The authors propose a weighted thresholding, which is designed to cope with a variety of anomalies. The analysis and experimental results on real images show that intelligent thresholding methods can make a significant difference for discontinuity detection.< >

关键词： stochastic processes Detectors Nonlinear filters image edge detection signal processing computer science image analysis Application software computer vision Markov random fields

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

neural networks for signal/image processing using the Princeton Engine multi-processor

Neural networks for signal/image processing using the Prince...

引用

IEEE Workshop on neural Networks for signal processing

作者： N. Binenbaum L. Dias P. Hsieh C.H. Ju S. Markel J.C. Pearson H. Taylor The National Information Display Laboratory David Samoff Research Center Inc. Princeton NJ USA

The authors describe a modular neural network system for the removal of impulse noise from the composite video signal of television receivers, and the use of the Princeton Engine multi-processor for real-time performance assessment. This system out-performs alternative methods, such as median filters and matched filters. The system uses only eight neurons, and can be economically implemented in VLSI.< >

关键词： neural networks signal processing image processing Engines Matched filters TV receivers Real time systems Very large scale integration computer aided manufacturing computer networks

来源：评论

学校读者我要写书评

暂无评论

Improved neural structures for image compression

Improved neural structures for image compression

引用

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

作者： S. Marsi G. Ramponi G.L. Sicuranza Telettra S.p.A. Vimercate (Milano) Italy DEEI-Università di Trieste Italy

The problem considered is the effective compression of image data. Compared to the many methods which allow for high compression factors (mainly based on the DCT), the proposed neural approaches offer, after a suitable training, comparable performance both in terms of perceived image quality and measured SNR. Moreover, they are able to perform in the same step the two main required operations of transformation and selection of the most significant terms, with a correspondingly smaller computational effort.< >

关键词： image coding neural networks computer networks Concurrent computing Databases Discrete cosine transforms Performance evaluation signal processing Parallel processing image processing

来源：评论

学校读者我要写书评

暂无评论

stochastic neural direct adaptive control

Stochastic neural direct adaptive control

引用

IEEE International Symposium on Intelligent Control (ISIC)

作者： T.T. Ho H.T. Ho J.T. Bialasiewicz E.T. Wall Electrical Engineering and Computer Science Department University of Colorado Denver Denver CO USA

A stochastic neural direct adaptive control algorithm for partially known state-space nonlinear time-varying plants is presented. A neural network is used to generate the control signal, which optimizes a quadratic (one-step-ahead prediction) performance index. In comparison to conventional stochastic state-space adaptive control, this neural control algorithm offers higher computation speed due to the parallel processing structure of the neural network. The algorithm is limited to known system matrices B(k) and C(k). For applications where B(k) and C(k) are unknown to the controller, an indirect neural adaptive control scheme may be used.< >

关键词： stochastic processes Adaptive control Nonlinear control systems Size control State-space methods Predictive models Equations neural networks Joining processes stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Mri Segmentation Using Supervised And Unsupervised methods

Mri Segmentation Using Supervised And Unsupervised Methods

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： A.M. Bensaid L.O. Hall L.P. Clarke R.P. Velthuizen Department of Computer Science & Engineering University of South Florida Tampa FL USA

来源：评论

学校读者我要写书评

暂无评论

A neural network based on differential Gabor filters for computing image flow from two successive images

A neural network based on differential Gabor filters for com...

引用

International Joint Conference on neural Networks (IJCNN)

作者： T.-R. Tsao V.C. Chen Vitro Corporation Silver Spring MD USA Naval Research Laboratory Inc. Washington D.C. DC USA

Proposes a neural network based on differential Gabor filters for computing the image flow. The approach attempts to overcome the limitation of the spatio-temporal frequency models by taking time derivatives of the Gabor responses as the carrier of visual motion information. A differential Gabor filter is a linear filter with the spatial derivative of a Gabo elemental function as its impulse response function. The authors derive a rigorous scheme for computing image motion. Based on this computational scheme, they present the architecture of a neural network system for visual motion. The computational model effectively bypasses the certainty constraint that severely limits the accuracy of the spatio-temporal frequency models, and avoids the time dimension integration required by the spatio-temporal frequency models. Experimental results show that the differential Gabor filter model performs better than the existing models.< >

关键词： neural networks Gabor filters computer networks Biology computing Biological system modeling Smoothing methods Filtering Power harmonic filters Frequency Optical signal processing

来源：评论

学校读者我要写书评

暂无评论

stochastic AND DETERMINISTIC NETWORKS FOR TEXTURE SEGMENTATION

引用

IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND signal processing 1990年第6期38卷 1039-1049页

作者： MANJUNATH, BS SIMCHONY, T CHELLAPPA, R UNIV SO CALIF INST SIGNAL & IMAGELOS ANGELESCA 90089

Several texture segmentation algorithms based on deterministic and stochastic relaxation principles, and their implementation on parallel networks, are described. The segmentation process is posed as an optimization problem and two different optimality criteria are considered. The first criterion involves maximizing the posterior distribution of the intensity field given the label field (maximum a posteriori estimate). The posterior distribution of the texture labels is derived by modeling the textures as Gauss Markov random fields (GMRFs) and characterizing the distribution of different texture labels by a discrete multilevel Markov model. A stochastic learning algorithm is proposed. This iterated hill-climbing algorithm combines fast convergence of deterministic relaxation with the sustained exploration of the stochastic algorithms, but is guaranteed to find only a local minimum. The second optimality criterion requires minimizing the expected percentage of misclassification per pixel by maximizing the posterior marginal distribution, and the maximum posterior marginal algorithm is used to obtain the corresponding solution. All these methods implemented on parallel networks can be easily extended for hierarchical segmentation; results of the various schemes in classifying some real textured images are presented.< >

关键词： stochastic processes image segmentation neural networks Markov random fields Simulated annealing computer vision Optical computing Gaussian distribution Hopfield neural networks Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Contour extraction of images on parallel computer - Local, parallel and stochastic algorithm which learns energy parameters

Contour extraction of images on parallel computer - Local, p...

引用

IJCNN International Joint Conference on neural Networks

作者： Hongo, Sadayuki Kawato, Mitsuo Inui, Toshio Miyake, Sei ATR Kyoto Jpn

The stochastic relaxation algorithm of S. Geman and D. Geman (IEEE Trans. Pattern Anal. Mach. Intell., vol. PAMI-6, pp. 721-741, 1984), which is based on the Markov random-field (MRF) model of images, was implemented on a hypercube parallel computer for contour extraction of human face images. The local energy parameters that define the MRF model were estimated by the learning algorithm recently proposed by the authors, while supervised by a desirable object contour as a teaching signal. The constrained optimization method recently developed by D. Geman (image vision Comput., vol. 5, no. 2, pp. 61-65, 1987) was utilized to avoid flaws in a fast simulated annealing. The contours extracted by the learning stochastic relaxation method were systematically compared with those obtained by several conventional edge detection methods. The contours extracted by the authors' method include few discontinuity points and small amounts of noise, and faithfully represent the contours of the original image. The authors propose a new algorithm, multiple-level, multiple-resolution MRF, which is an extension of the original MRF. This model can incorporate a priori knowledge about the global structures in images and still be implemented in a local and parallel mode.

关键词： image processing

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：