发布求助
文献互助 智能选刊 最新文献

1996 Fourth IEEE International Workshop on Cellular Neural Networks and their Applications Proceedings (CNNA-96)最新文献

筛选
英文 中文
Adaptive histogram equalization with cellular neural networks 细胞神经网络的自适应直方图均衡化
1996 Fourth IEEE International Workshop on Cellular Neural Networks and their Applications Proceedings (CNNA-96) Pub Date : 1996-06-24 DOI: 10.1109/CNNA.1996.566497
M. Csapodi, T. Roska
{"title":"Adaptive histogram equalization with cellular neural networks","authors":"M. Csapodi, T. Roska","doi":"10.1109/CNNA.1996.566497","DOIUrl":"https://doi.org/10.1109/CNNA.1996.566497","url":null,"abstract":"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.","PeriodicalId":222524,"journal":{"name":"1996 Fourth IEEE International Workshop on Cellular Neural Networks and their Applications Proceedings (CNNA-96)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125381585","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 25
Design of monotonic binary-valued cellular neural networks 单调二值细胞神经网络的设计
1996 Fourth IEEE International Workshop on Cellular Neural Networks and their Applications Proceedings (CNNA-96) Pub Date : 1996-06-24 DOI: 10.1109/CNNA.1996.566593
I. Fajfar, F. Bratkovic
{"title":"Design of monotonic binary-valued cellular neural networks","authors":"I. Fajfar, F. Bratkovic","doi":"10.1109/CNNA.1996.566593","DOIUrl":"https://doi.org/10.1109/CNNA.1996.566593","url":null,"abstract":"In order to be able to take full advantage of the great application potential that lies in cellular neural networks (CNNs) we need to have successful design and learning techniques as well. In almost any analogic CNN algorithm that performs an image processing task, binary CNNs play an important role. We observed that all binary CNNs reported in the literature, except for a connected component detector, exhibit monotonic dynamics. In the paper we show that the local stability of a monotonic binary CNN represents sufficient condition for its functionality, i.e. convergence of all initial states to the prescribed global stable equilibria. Based on this finding, we propose a rigorous design method, which results in a set of design constraints in a form of linear equalities. These are obtained from a simple local rules similar to that in elementary cellular automata without having to worry about continuous dynamics of a CNN. In the end we utilize our method to design a new CNN template for detecting holes in a 2D object.","PeriodicalId":222524,"journal":{"name":"1996 Fourth IEEE International Workshop on Cellular Neural Networks and their Applications Proceedings (CNNA-96)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126856063","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 20
Structure verification on photolithographic masks based on tolerance criteria by cellular neural networks 基于细胞神经网络公差准则的光刻掩模结构验证
1996 Fourth IEEE International Workshop on Cellular Neural Networks and their Applications Proceedings (CNNA-96) Pub Date : 1996-06-24 DOI: 10.1109/CNNA.1996.566510
S. Schwarz, A. Pohl, W. Mathis
{"title":"Structure verification on photolithographic masks based on tolerance criteria by cellular neural networks","authors":"S. Schwarz, A. Pohl, W. Mathis","doi":"10.1109/CNNA.1996.566510","DOIUrl":"https://doi.org/10.1109/CNNA.1996.566510","url":null,"abstract":"First of all, the problem of structure verification is introduced with respect to tolerance criteria and their verifications. After that, the basic principle of a verification method for cellular neural networks is motivated by means of local restrictions. Then their solution is presented on the basis of local operators which are only designed with the help of local restrictions of the design rules of the mask structures and their tolerance zones. After that, the result of the successful use of the method is demonstrated on manufacturing and calibration masks. Finally, the debate discusses the competitive position of the method with reference to two standard methods. Last of all, the summary indicates future improvements.","PeriodicalId":222524,"journal":{"name":"1996 Fourth IEEE International Workshop on Cellular Neural Networks and their Applications Proceedings (CNNA-96)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115171405","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Simple model of equilibrium froth height for foams: an application for CNN image analysis 泡沫平衡泡沫高度的简单模型:在CNN图像分析中的应用
1996 Fourth IEEE International Workshop on Cellular Neural Networks and their Applications Proceedings (CNNA-96) Pub Date : 1996-06-24 DOI: 10.1109/CNNA.1996.566563
W. Zimmermann, L. Jeanmeure
{"title":"Simple model of equilibrium froth height for foams: an application for CNN image analysis","authors":"W. Zimmermann, L. Jeanmeure","doi":"10.1109/CNNA.1996.566563","DOIUrl":"https://doi.org/10.1109/CNNA.1996.566563","url":null,"abstract":"The design of a control system to monitor the washing of coal by a froth flotation mechanism is considered. The froth in a batch cell, due to steady sparging by air, reaches an equilibrium height h. This height is determined by the cumulative effects of several resistance mechanisms dissipating the air pressure gradient: viscous fiction of the rising air and of the falling liquid, the surface tension of bubbles, and the buoyancy forces. This control system is based upon a hydrodynamic model for the resistance and a feedback loop consisting of an image processing system that computes bubble density and size distribution needed by the model. The model hypothesis is that bubble flow is an air flow through a porous medium with an effective resistance coefficient K which depends on the dissipative mechanisms given above. The pressure gradient needed to estimate the froth height is found from Darcy's law when the froth is idealized as a set of vertical tubes, with radius R chosen to be the average bubble size, which varies with vertical position, allowing the air to flow through with an average velocity V/sub m/. The model equation is grad p=K V/sub m//R/sub 0//sup 2/. The cellular neural network (CNN) paradigm was chosen for its ability to process images quickly for use as control system element to compute k and thus infer changes to h by changing the set point for air flow rate or by addition of more liquid or surfactant, which would change the drainage rate or the surface tension.","PeriodicalId":222524,"journal":{"name":"1996 Fourth IEEE International Workshop on Cellular Neural Networks and their Applications Proceedings (CNNA-96)","volume":"6 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113979349","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 6
6/spl times/6 DPCNN: a programmable mixed analogue-digital chip for cellular neural networks DPCNN:用于细胞神经网络的可编程混合模拟-数字芯片
1996 Fourth IEEE International Workshop on Cellular Neural Networks and their Applications Proceedings (CNNA-96) Pub Date : 1996-06-24 DOI: 10.1109/CNNA.1996.566616
M. Salerno, F. Sargeni, V. Bonaiuto
{"title":"6/spl times/6 DPCNN: a programmable mixed analogue-digital chip for cellular neural networks","authors":"M. Salerno, F. Sargeni, V. Bonaiuto","doi":"10.1109/CNNA.1996.566616","DOIUrl":"https://doi.org/10.1109/CNNA.1996.566616","url":null,"abstract":"The implementation of a versatile VLSI chip represents an important step to develop cellular neural networks (CNN). In this paper a VLSI realization of the multi-chip oriented, 6/spl times/6 digitally programmable cellular neural network (6/spl times/6 DPCNN) chip, is presented. This chip covers most of the available one-neighbourhood templates for image processing applications. Moreover, it can be easily interconnected to others to form very large CNN arrays.","PeriodicalId":222524,"journal":{"name":"1996 Fourth IEEE International Workshop on Cellular Neural Networks and their Applications Proceedings (CNNA-96)","volume":"146 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122641197","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 29
Hysteresis cellular neural networks 滞后细胞神经网络
1996 Fourth IEEE International Workshop on Cellular Neural Networks and their Applications Proceedings (CNNA-96) Pub Date : 1996-06-24 DOI: 10.1109/CNNA.1996.566491
K. Jin'no, M. Tanaka
{"title":"Hysteresis cellular neural networks","authors":"K. Jin'no, M. Tanaka","doi":"10.1109/CNNA.1996.566491","DOIUrl":"https://doi.org/10.1109/CNNA.1996.566491","url":null,"abstract":"This article proposes a hysteresis cellular neural network (HCNN). First, we define an energy function for the HCNN, and analyze it. Next, we analyze the stable equilibria of HCNN.","PeriodicalId":222524,"journal":{"name":"1996 Fourth IEEE International Workshop on Cellular Neural Networks and their Applications Proceedings (CNNA-96)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131642683","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Three versions of a digital hardware implementation of a multi-layer perceptron in 0.7 /spl mu/ CMOS-design 三个版本的数字硬件实现了一个多层感知器在0.7 /spl mu/ cmos的设计
1996 Fourth IEEE International Workshop on Cellular Neural Networks and their Applications Proceedings (CNNA-96) Pub Date : 1996-06-24 DOI: 10.1109/CNNA.1996.566607
V. Tryba, B. Kiziloglu
{"title":"Three versions of a digital hardware implementation of a multi-layer perceptron in 0.7 /spl mu/ CMOS-design","authors":"V. Tryba, B. Kiziloglu","doi":"10.1109/CNNA.1996.566607","DOIUrl":"https://doi.org/10.1109/CNNA.1996.566607","url":null,"abstract":"In this paper, three versions of an implementation of a multi-layer perceptron as a neural ASIC are presented. A fully parallel version with 9 neurons as a fast version, a version with sequential processing inside the neurons, and a version with one fast neuron which is multiplexed. The three versions are compared in size and speed.","PeriodicalId":222524,"journal":{"name":"1996 Fourth IEEE International Workshop on Cellular Neural Networks and their Applications Proceedings (CNNA-96)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131842265","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
CNNs with radial basis input function 具有径向基输入函数的cnn
1996 Fourth IEEE International Workshop on Cellular Neural Networks and their Applications Proceedings (CNNA-96) Pub Date : 1996-06-24 DOI: 10.1109/CNNA.1996.566562
M. Yalçin, C. Guzelis
{"title":"CNNs with radial basis input function","authors":"M. Yalçin, C. Guzelis","doi":"10.1109/CNNA.1996.566562","DOIUrl":"https://doi.org/10.1109/CNNA.1996.566562","url":null,"abstract":"This paper proposes a cellular neural network (CNN) model with radial basis input function (radial basis input CNN) for improving function approximation ability of CNNs. The model can be viewed as a cascade of two units: the first unit is a multi-input, multi-output radial basis function network (RBFN), the second unit is the original CNN model. The weights and centers of the RBFN unit are chosen identical for all RBFN outputs yielding a space-invariant connection weight pattern over the network. With such a weight sharing property, the proposed model becomes a special kind of nonlinear B-template CNN. The ability of the radial basis input CNN model in approximation to functions as its input-(steady state) output mapping is examined on an edge detection task for noisy images. A modified version of the recurrent perceptron learning algorithm (RPLA) is used for the training radial basis input CNN.","PeriodicalId":222524,"journal":{"name":"1996 Fourth IEEE International Workshop on Cellular Neural Networks and their Applications Proceedings (CNNA-96)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114798225","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
The edge regularization of noised image method 噪声图像的边缘正则化方法
1996 Fourth IEEE International Workshop on Cellular Neural Networks and their Applications Proceedings (CNNA-96) Pub Date : 1996-06-24 DOI: 10.1109/CNNA.1996.566554
A. Stankiewicz, I. Merta, L. Jaroszewicz
{"title":"The edge regularization of noised image method","authors":"A. Stankiewicz, I. Merta, L. Jaroszewicz","doi":"10.1109/CNNA.1996.566554","DOIUrl":"https://doi.org/10.1109/CNNA.1996.566554","url":null,"abstract":"A model of extraction and regularization of edges of noisy images is presented. Edge is defined as a local maximum of the image gradient. The model is based on a formation of local dependences between pixels of the image, so called pattern and step dynamic approximation of the value of the brightness of individual pixels. The dynamics of the model are defined by an adequately constructed function of cost (further on called energy, due to an analogy with potential energy). Energy is specified from the use of the sum of adversities of scalar products of the neighboring vectors of the gradient. This process can be easily implemented in a cellular neuron network of a suitable design. Regularization of the image is an important phase of image processing among others image recognition.","PeriodicalId":222524,"journal":{"name":"1996 Fourth IEEE International Workshop on Cellular Neural Networks and their Applications Proceedings (CNNA-96)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123018777","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Pulse stream current mode CMOS CNN chip 脉冲流电流模式CMOS CNN芯片
1996 Fourth IEEE International Workshop on Cellular Neural Networks and their Applications Proceedings (CNNA-96) Pub Date : 1996-06-24 DOI: 10.1109/CNNA.1996.566617
A. Paasio, A. Dawidziuk, V. Porra
{"title":"Pulse stream current mode CMOS CNN chip","authors":"A. Paasio, A. Dawidziuk, V. Porra","doi":"10.1109/CNNA.1996.566617","DOIUrl":"https://doi.org/10.1109/CNNA.1996.566617","url":null,"abstract":"A new idea of analog cellular neural network (CNN) VLSI implementation is described. The main problem in neural networks realization is the size of adjustable connections between neurons in the net. The weight circuits may occupy more than 90% of the single neuron space. The main advantage of current mode pulse stream neurons is small size of the weight circuit. The simplicity of the building blocks used allows one to operate them with relatively high speed. As compared with the other pulse stream circuits, this approach is based on current pulses. Therefore, for both basic neural operations, summation and multiplication are easy to implement, if only the phase is irrelevant.","PeriodicalId":222524,"journal":{"name":"1996 Fourth IEEE International Workshop on Cellular Neural Networks and their Applications Proceedings (CNNA-96)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121516835","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 4
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术官方微信