检索结果-内蒙古大学图书馆

Markov random field image segmentation using cellular neural network

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

Face and Eye Detection by CNN Algorithms

引用

Journal of VLSI signal processing systems for signal, image and video technology 1999年第2期23卷 497-511页

作者： Balya, David Roska, Tamás Analogical and Neural Computing Laboratory Computer and Automation Research Institute Budapest Hungary

A novel approach to critical parts of face detection problems is given, based on analogic cellular neural network (CNN) algorithms. The proposed CNN algorithms find and help to normalize human faces effectively while their time requirement is a fraction of the previously used methods. The algorithm starts with the detection of heads on color pictures using deviations in color and structure of the human face and that of the background. By normalizing the distance and position of the reference points, all faces should be transformed into the same size and position. For normalization, eyes serve as points of reference. Other CNN algorithm finds the eyes on any grayscale image by searching characteristic features of the eyes and eye sockets. Tests made on a standard database show that the algorithm works very fast and it is reliable.

关键词：

来源：评论

学校读者我要写书评

暂无评论

3D integrated scalable focal-plane processor array

3D integrated scalable focal-plane processor array

引用

European Conference on Circuit Theory and Design, ECCTD

作者： Peter Foldesy Akos Zarandy Csaba Rekeczky Tamas Roska Analogic and Neural Computing Laboratory Computer and Automation Research Institute Hungarian Academy of Sciences (ATOMKI) Budapest Hungary

The ASIC implementation of a 64times64 sized mixed-signal cellular visual microprocessor architecture with digital processors is described. Measurement results are shown. The architecture is composed of a regular photosensor readout circuit array, prepared for 3D sensor integration, an array of identical SIMD processing elements, and central program scheduler. The processing architecture supports cluster formation of differently parameterized arrays.

关键词： Sensor arrays Xenon computer architecture Application specific integrated circuits Processor scheduling computer interfaces Sensor phenomena and characterization Space technology Silicon Integrated circuit interconnections

来源：评论

学校读者我要写书评

暂无评论

Trends in design of massively parallel coprocessors implemented in digital ASICs

Trends in design of massively parallel coprocessors implemen...

引用

International Joint Conference on neural Networks (IJCNN)

作者： P. Foldesy Analogic and Neural Computing Laboratory Computer and Automation Research Institute Hungarian Academy of Sciences (ATOMKI) Budapest Hungary

This paper collects the most recent parallel coprocessors and highlights the recent trends. It is shown that the single chip massively parallel processor implementations seem to disappear from the scientific investigations (with the exception of low-level near-sensor image processing). Meanwhile, the formerly developed architectures have moved inside complex system-on-chips/microprocessors. The common aspect of the recent architectures is the advanced processing element and internal interconnection solutions, and the dominant mid-grain parallelism (i.e. up to a hundred processing element per chip).

关键词： Coprocessors Application specific integrated circuits Concurrent computing Parallel processing Systolic arrays Radar signal processing Signal processing algorithms Laboratories automation Image processing

来源：评论

学校读者我要写书评

暂无评论

High-speed label inspection system for textile industry

High-speed label inspection system for textile industry

引用

10th IMEKO TC10 International Conference on Technical Diagnostics

作者： Szatmári, István Zarándy, Ákos Analogical and Neural Computing Laboratory Computer and Automation Research Institute Hungarian Academy of Sciences 13-17 Kende Street Budapest H-1111 Hungary AnaLogic Computers Ltd. 13-17 Kende Street Budapest H-1111 Hungary

ISBN: (纸本)9789638658647

In this paper, the current development of a high-speed, visual inspection unit for use in the quality assurance of narrow fabric and label weaving will be presented. The aim of the project is to provide full visual defect recognition for the textile industry. Dirt spots and patches, weaving faults, missing or torn fibers, and certain errors of the label patterns are detected. A special experimental setup was prepared for evaluating the algorithm performance. Current phase achieves a very high quality level with low false alarm rate at inspection speed of 4 m/s.

关键词： Textile industry

来源：评论

学校读者我要写书评

暂无评论

Efficient off-line feature selection strategies for on-line classifier systems

Efficient off-line feature selection strategies for on-line ...

引用

International Joint Conference on neural Networks (IJCNN)

作者： D. Balya G. Timar I. Szatmari Cs. Rekeczky AnaLogic and Neural Computing Systems Laboratory Computer and Automation Research Institute Hungarian Academy of Sciences (ATOMKI) Budapest Hungary

In this work we discuss feature/signature selection strategies for on-line classifier systems, implemented on a common stand-alone HW/SW vision system. In the chosen computational environment topographic and non-topographic computing can be combined for the targeted task of terrain feature analysis. The topographic front-end of the system is capable of deriving more than thousand different visual signatures per second from a few dozen visual feature channels. These signatures are statistically correlated and might also be computationally inter-dependent. To develop an efficient real-time classification algorithm the dimensionality of the extracted features has to be significantly reduced, i.e. only a few signatures can be selected. In this paper we analyze different signature selection strategies for various classifiers with given performance criteria and system-level time performance constraints. Two blind signature selection techniques are described: variance maximization and a factor-based analysis. We also discuss supervised selection mechanisms: class-based statistical and decision-tree-based approaches.

关键词： Feature extraction computer vision Classification algorithms Performance analysis Hardware Microprocessors Laboratories automation Machine vision Time factors

来源：评论

学校读者我要写书评

暂无评论

Topographic and non-topographic neural network based computational platform for UAV applications

Topographic and non-topographic neural network based computa...

引用

International Joint Conference on neural Networks (IJCNN)

作者： Cs. Rekeczky G. Timar D. Balya I. Szatmari A. Zarandy AnaLogic and Neural Computing Systems Laboratory Computer Automation Research Institute Hungarian Academy of Sciences (ATOMKI) Budapest Hungary

In this work, we present an architecture and algorithmic framework where topographic and non-topographic computation is combined on the basis of several artificial neural network models. The algorithm cores utilize an analogic (analog and logical) architecture consisting of a high resolution optical sensor, a low resolution cellular sensor-processor (cellular nonlinear network-CNN-based chip) and a digital signal processor. The proposed framework makes the acquisition of a spatially and temporally consistent image flow possible even in case of extreme variations in the environment. It ideally supports the handling of difficult problems on a moving platform such as terrain identification, navigation parameter estimation and multi-target tracking. The proposed spatio-temporal adaptation relies on a feature based optical flow estimation that can be efficiently calculated on available CNN chips. The paper illustrate how multi-channel visual flow analysis and classifier (ART, KN) driven visual attention-selection mechanisms can be efficiently supported by an analogic architecture. The experiments performed on an analogic CNN hardware prototype highlights some of the application potentials for unmanned air vehicle (UAV) applications.

关键词： neural networks computer networks Unmanned aerial vehicles Artificial neural networks computer architecture Signal processing algorithms Spatial resolution Signal resolution Optical sensors Cellular networks

来源：评论

学校读者我要写书评

暂无评论

Solution of stereo correspondence in real scene: an analogic CNN algorithm

Solution of stereo correspondence in real scene: an analogic...

引用

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

作者： A.G. Radvanyi Analogic & Neural Computing Systems Laboratory Computer and Automation Institute Hungarian Academy of Sciences Budapest Hungary

A multilayer analogic CNN (cellular neural network) algorithm is proposed to reconstruct surfaces from real scene stereo-pairs consisting of two images shot from one and the same camera position. The whole scene is illuminated by randomly structured light to provide texture on otherwise "empty" surfaces. One image is that of the illuminated background, the other one is the image of illuminated objects in front of the same background.< >

关键词： Layout Cellular neural networks Image reconstruction Surface reconstruction Stereo vision Surface texture Matched filters Laboratories automation Nonhomogeneous media

来源：评论

学校读者我要写书评

暂无评论

Adaptive image sensing and enhancement using the adaptive cellular neural network Universal Machine

Adaptive image sensing and enhancement using the adaptive ce...

引用

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

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

A simple but powerful active image equalization method is introduced via adaptive CNN-UM sensor-computers. The method can be used for the adaptive control of image sensing and for subsequent image enhancement. The algorithm uses intensity and contrast content as well. The method is completely executable on the adaptive cellular neural network Universal Machine (ACNN-UM) architecture. The adaptive extended cell is presented.

关键词： Adaptive systems Cellular neural networks Turing machines Image enhancement computer networks computer architecture Histograms Adaptive equalizers Adaptive control Concurrent computing

来源：评论

学校读者我要写书评

暂无评论

CASTLE: an emulated digital CNN architecture design issues, new results

CASTLE: an emulated digital CNN architecture design issues, ...

引用

IEEE International Conference on Electronics, Circuits and Systems (ICECS)

作者： A. Zarandy P. Keresztes T. Roska P. Szolgay Analogic and Neural Computing Systems Laboratory Computer and Automation Institute Hungarian Academy of Sciences (ATOMKI) Budapest Hungary

A new emulated digital CNN universal machine chip architecture is introduced in this paper. The chip contains 24 CNN core processors using 70 mm/sup 2/ silicon area with a 0.35 /spl mu/m technology. Its speed is 1 ns/virtual cells/CNN iterations with 12 bit precision. This enables one to execute over five hundred 3/spl times/3 convolutions on each frame of a 240/spl times/320 sized 25 fps (standard NTSC) digital image flow. Another new feature of the design is the different precision capability. This allows the user to convert precision to speed.

关键词： Cellular neural networks computer architecture Optical feedback Equations Turing machines Silicon Convolution Image processing Very large scale integration Biomedical optical 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：