检索结果-内蒙古大学图书馆

IEEE International Workshop on Cellular Nanoscale Networks and their Applications, (CNNA)

作者： K.R. Crounse T. Roska L.O. Chua Nonlinear Electronics Laboratory University of California Berkeley CA USA Analogic and Neural Computing Laboratory Hungarian Academy of Sciences Computer and Automation Institute Budapest Hungary

This paper explores two issues which are relevant in practical halftoning situations on the CNN universal machine: block processing of large images with small CNN arrays, and the use of no larger than 3/spl times/3 templates. It is shown that block processing can be performed without noticeable boundary artifacts by careful selection of boundary cell values. In this example, a standard 3/spl times/3 halftoning template is used; higher quality halftones can be obtained only by using larger templates. A CNNUM algorithm is introduced which uses only a 3/spl times/3 template but emulates a much larger effective template through an iterative procedure. The method is to discretize the CNN transient in time and then implement the spatial correlations at each time step with a CNN transient. An A-B-template pair was designed for a single CNN transient to approximate a very simple linear filter model of the human visual system. The resulting discrete-time system was analyzed. The iterative procedure is demonstrated to produce a visually pleasing halftone.

关键词： Cellular neural networks Turing machines Laboratories Iterative algorithms Humans Visual system Image processing Gray-scale automation Nonlinear filters

来源：评论

学校读者我要写书评

暂无评论

An adaptive resonance theory-based neural network capable of learning via representational redescription

An adaptive resonance theory-based neural network capable of...

引用

International Joint Conference on neural Networks (IJCNN)

作者： G. Bartfai Analogical and Neural Computing Systems Laboratory Computer and Automation Research Institute Hungarian Academy of Sciences (ATOMKI) Budapest Hungary

This paper introduces a neural network architecture called R2MAP, which is based on the representational redescription hypothesis in cognitive science and adaptive resonance theory (ART) neural networks. The R2MAP network learns to classify arbitrary sequences of input patterns using a re-iterative process whereby knowledge that gets embedded in the network via ARTMAP-style error-driven learning is redescribed and becomes available to it for further learning. The knowledge redescription phase is triggered when the perceived level of difficulty of the given task exceeds a certain threshold, and is achieved through the dynamic creation of new features that better distinguish between output classes. This way the R2MAP network is capable of learning complex, relational input-output dependencies that cannot be represented efficiently using solely the features extracted through ordinary learning of statistical relationships. A simple proof-of-concept example is presented to illustrate the main ideas. Some related work is also discussed.

关键词： Resonance neural networks Biological neural networks Subspace constraints Cognitive science Artificial neural networks Humans Laboratories automation computer science

来源：评论

学校读者我要写书评

暂无评论

On the chip implementation of analogic algorithms for optical detection of some layout errors of printed circuit boards

On the chip implementation of analogic algorithms for optica...

引用

IEEE International Workshop on Cellular Nanoscale Networks and their Applications, (CNNA)

作者： K. Tomordi P. Foldesy P. Szolgay Analogic and Neural Computing Systems Laboratory Computer and Automation Research Institute Hungarian Academy of Sciences (ATOMKI) Budapest Hungary Image Processing and Neurocomputing Department Faculty of Engineering University of Veszprém Veszprem Hungary

Printed circuit board layout inspection methods are mostly based on local geometric information, therefore they are well suited to the cellular neural networks (CNN) paradigm. The wire break, the wire and isolation width violation and an "H" type short circuits detector analogic algorithms were tested on a 20*22 CNN Universal Machine (CNNUM) chip working in the CNN Chip Prototyping System (CCPS) and on the CNN Engine Board (CNNEB), and the results were compared to the commercially available inspection systems.

关键词： Cellular neural networks Inspection Wire Circuit testing Geometrical optics Optical computing Printed circuits Detectors System testing Turing machines

来源：评论

学校读者我要写书评

暂无评论

A fast fixed point learning method to implement associative memory on CNN's

引用

IEEE TRANSACTIONS ON CIRCUITS AND systems I-FUNDAMENTAL THEORY AND APPLICATIONS 1997年第4期44卷 362-366页

作者： Szolgay, P Szatmari, I Laszlo, K Analogic and Neural Computing Systems Laboratory Computer and Automation Institute Hungarian Academy of Sciences (ATOMKI) Budapest Hungary

Cellular neural Networks (CNN's) with space-varying interconnections are considered here to implement associative memories, A fast learning method is presented to compute the interconnection weights. The algorithm was carefully tested and compared to other methods. Storage capacity, noise immunity, and spurious state avoidance capability of the proposed system are discussed.

关键词： associative memory fixed point

来源：评论

学校读者我要写书评

暂无评论

Markov random field image segmentation using cellular neural network

引用

IEEE TRANSACTIONS ON CIRCUITS AND systems I-FUNDAMENTAL THEORY AND APPLICATIONS 1997年第1期44卷 86-89页

作者： Sziranyi, T Zerubia, J Analogical and Neural Computing Systems Research Laboratory Computer and Automation Institute Hungarian Academy of Sciences (MTA-SZTAKI) Budapest Hungary I.N.R.I.A. Sophia Antipolis Sophia-Antipolis France

Markovian approaches to early vision processes need a huge amount of computing power. These algorithms can usually be implemented on parallel computing structures. with the Cellular neural Networks (CNN), a new image processing toot is coming into consideration, Its VLSI implementation takes place on a single analog chip containing several thousands of cells. Herein se use the CNN UM architecture for statistical image segmentation. The Modified Metropolis Dynamics (MMD) method can be implemented into the raw analog architecture of the CNN, We are able to implement a (pseudo) random held generator using one layer (one memory/cell) of the CNN. We can introduce the whole pseudostochastic segmentation process in the CNN architecture using 8 memories/cell, We use simple arithmetic functions (addition, multiplication), equality-test between neighboring pixels and very simple nonlinear output functions (step, jigsaw, With this architecture, a real VLSI CNN chip can execute a pseudostochastic relaxation algorithm of about 100 iterations in about 1 ms, In the proposed solution the segmentation is unsupervised. We have developed a pixel-level statistical estimation model. The CNN turns the original image into a smooth one. Then we have two gray-level values for every pixel: the original and the smoothed one. These two values are used for estimating the probability distribution of region label at a given pixel. Using the conventional first-order Markov Random Field (MRF) model, some misclassification errors remained at the region boundaries, because of the estimation difficulties in case of low SNR. By using a greater neighborhood, this problem has been avoided. In our CNN experiments, we used a simulation system with a fixed-point integer precision of 16 bits, Our results show that even in the case of the very constrained conditions of value-representations (the interval is (-64, +64), the accuracy is 0.002) can result in an effective and acceptable segmentation.

关键词： Markov processes VLSI analogue integrated circuits analogue processing circuits cellular neural nets estimation theory image segmentation neural chips neural net architecture parallel algorithms probability CNN UM architecture Markov random field image s Parallel algorithms Cellular neural networks neural network hardware Probability estimation theory image segmentation neural net architecture Analog integrated circuits analogue processing circuits Very large scale integration Markov random fields Markov chain

来源：评论

学校读者我要写书评

暂无评论

Spatial depth extraction using random stereograms in analogic CNN framework

引用

INTERNATIONAL JOURNAL OF CIRCUIT THEORY AND APPLICATIONS 1996年第1期24卷 69-92页

作者： Radvanyi, AG Analogical and Neural Computing Systems Laboratory Computer and Automation Institute Hungarian Academy of Sciences POB 63 H-1518 Budapest Hungary

Demonstrated and motivated on human stereo vision analogic CNN algorithms are proposed to extract 3D spatial information from computer-generated random-dot stereograms as well as real scene random-dot like ones produced with simple optical devices, projector and camera. Several aspects of making real scene stereograms are considered to minimize perspective distortion and enable local CNN processing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Robustness of cellular neural networks in image deblurring and texture segmentation

引用

INTERNATIONAL JOURNAL OF CIRCUIT THEORY AND APPLICATIONS 1996年第3期24卷 381-396页

作者： Sziranyi, T Analogical and Neural Computing Systems Research Laboratory Computer and Automation Institute Hungarian Academy of Sciences (MTA SZTAKI) pf. 63 H-1518 Budapest Hungary

Template parameters of cellular neural networks (CNNs) should be robust enough to random variability of VLSI tolerances and noise. Using the CNN for image processing, one of the main problems is the robustness of a given task in a real VLSI chip. It will be shown that very different tasks such as 2D or 3D deconvolution and texture segmentation can be solved in a real VLSI CNN environment without significant loss of efficiency and accuracy under low precision (about 6-8 bits) and random variability of the VLSI parameters. The CNN turns out to be very robust against template noise, image noise, imperfect estimation of templates and parameter accuracy. The parameters of a template are tuned using genetic learning. These optimized parameters depend on the precision of the architecture. It was found that about 6-8 bits of precision is enough for a complicated multilayer deconvolution, while only 4 bits of precision is enough for difficult texture segmentation in the presence of noise and parameter variances, The tolerance sensitivity of template parameters is considered for VLSI implementation. Theory and examples are demonstrated by many results using real-life microscopic images and natural textures.

关键词： Cellular neural networks

来源：评论

学校读者我要写书评

暂无评论

Feature extraction of postage stamps using an iterative approach of CNN

引用

IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND computer SCIENCES 1996年第10期E79A卷 1741-1746页

作者： Kishida, J Rekeczky, C Nishio, Y Ushida, A Faculty of Engineering Tokushima University Tokushima-shi 770 Japan Analogical and Neural Computing Systems Laboratory Computer and Automation Institute Hungarian Academy of Sciences 27 H-1111 Budapest Kende-u. 13-17 Hungary

In this article, a new analogic CNN algorithm to extract features of postage stamps in fray-scale images is introduced. The Gradient Controlled Diffusion method plays an important role in the approach. In our algorithm, it is used for smoothing and separating Arabic figures drawn with a color which is similar to the background color. We extract Arabic figures in postage stamps by combining Gradient Controlled Diffusion with nearest neighbor linear CNN template and logic operations. Applying the feature extraction algorithm to different test images it has been verified that it is also effective in complete segmentation problems.

关键词： cellular neural networks analogic algorithm image processing feature extraction gradient controlled diffusion

来源：评论

学校读者我要写书评

暂无评论

Distance preserving 1D Turing-wave models via CNN, implementation of complex-valued CNN and solving a simple inverse pattern problem (detection)

Distance preserving 1D Turing-wave models via CNN, implement...

引用

IEEE International Workshop on Cellular Nanoscale Networks and their Applications, (CNNA)

作者： G. Toth P. Foldesy T. Roska Analogic and Neural Computing Systems Laboratory Computer and Automation Institute Hungarian Academy of Sciences (ATOMKI) Budapest Hungary

In this paper a cellular neural network (CNN) implementation of a reaction-diffusion system is described, which produces distance preserving periodic Turing patterns. The CNN with complex-valued templates are introduced, presenting an application for pattern generation. Finally a method for black-and-white pattern detection is described.

关键词： Cellular neural networks Equations Skin Marine animals Laboratories automation Physics Chemistry Biological system modeling Inhibitors

来源：评论

学校读者我要写书评

暂无评论

Adaptive histogram equalization with cellular neural networks

Adaptive histogram equalization with cellular neural network...

引用

IEEE International Workshop on Cellular Nanoscale Networks and their Applications, (CNNA)

作者： M. Csapodi T. Roska Analogic and Neural Computing Systems Laboratory Computer and Automation Institute Hungarian Academy of Sciences (ATOMKI) Budapest Hungary

Adaptive histogram equalization (AHE), a method of contrast enhancement which is sensitive to local spatial information in image, has demonstrated its effectiveness in many applications. However, this technique is computationally intensive. In this paper we present two computational methods designed to fit well onto the locally interconnected array computer architecture of cellular neural networks (CNNs). CNNs are well known for their image processing capabilities, specially for grey-scale medical images and images of a natural scene. In many applications it would be very useful if the operation of a template or a complex analogic algorithm were highly illumination independent. Our results suggest that we can achieve this goal by using the AHE method in a pre-processing step.

关键词： Histograms Adaptive equalizers Cellular neural networks Application software Adaptive systems computer networks Design methodology computer architecture Image processing Biomedical imaging

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：