检索结果-内蒙古大学图书馆

IEEE/INNS/ENNS International Joint conference on neural networks (IJCNN 2000)

作者： Kamio, T Tanaka, S Morisue, M Hiroshima City Univ Fac Informat Sci Dept Informat Machines & Interfaces Asaminami Ku Hiroshima 7313194 Japan

Mulilayer feedforward neural network (MFNN) trained by the backpropagation (BP) algorithm is one of the most significant models in artificial neural networks. MFNNs have been used in many areas of signal and image processing due to high applicability. Although they have been implemented as analog, mixed analog-digital and fully digital VLSI circuits, it is still difficult to realize their hardware implementation with BP teaming function. This paper describes the BP algorithm for the logic oriented neural network (LOGO-NN) which we have proposed as a sort of MFNN with quantized weights and multilevel threshold neurons. As both weights and neuron outputs are quantized to integer values in LOGO-NNs, it is expected that LOGO-NNs with BP learning can be more effectively implemented than the common MFNNs. Finally, it is shown by simulations that the proposed BP algorithm has good performance for LOGO-NNs.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Fuzzy logic model-based technique with application to Urdu characters recognition

Fuzzy logic model-based technique with application to Urdu c...

引用

conference on applications of artificial neural networks in image processing V

作者： Megherbi, D Lodhi, SM Boulenouar, JA Univ Denver Dept Engn Denver CO 80208 USA

ISBN: (纸本)0819435805

This work is in the field of automated document processing. This work addresses the problem of representation and recognition of Urdu characters based on concepts from Fuzzy logic. In particular, we show that Fuzzy logic is used here to make a classification of 36 Urdu characters into seven sub-classes namely sub-classes characterized by seven proposed and defined fuzzy features specifically related to Urdu characters. We show that here Fuzzy logic provides a remarkably simple way to draw definite conclusions from vague, ambiguous, noisy or imprecise information. In particular, we illustrate the concept of "interest regions" and describe a framing method that provides a way to make the proposed technique for Urdu characters recognition robust and invariant to scaling and translation. We also show that a given character rotation is dealt with by using the Hotelling transform. This transform is based upon the eigenvalue decomposition of the covariance matrix of an image, providing a method of determining the orientation of the major axis of an object within an image. Finally experimental results are presented to show the power and robustness of the proposed Fuzzy logic based technique for Urdu character recognition, its fault tolerance, and high recognition accuracy.

关键词： fuzzy systems signals & low level image processing character recognition document decoding filtering image enhancement segmentation coding

来源：评论

学校读者我要写书评

暂无评论

Experimental demonstration of real-time image-processing using a VLSI analog programmable array processor

Experimental demonstration of real-time image-processing usi...

引用

conference on applications of artificial neural networks in image processing V

作者： Liñán, G Domínguez-Castro, R Espejo, S Roca, E Foldesy, P Rodríguez-Vázquez, A Ctr Nacl Microelect Inst Microelect Sevilla E-41012 Seville Spain

ISBN: (纸本)0819435805

This paper describes a full-custom mixed-signal chip which embeds distributed optical signal acquisition, digitally-programmable analog parallel processing, and distributed image memory - cache - on a common silicon substrate. This chip, designed in a 0.5 mu m CMOS standard technology contains around 1, 000, 000 transistors, 80% of which operate in analog mode;it is hence one the most complex mixed-signal chip reported to now. Chip functional features are in accordance to the CNN Universal Machine (1) paradigm: cellular, spatial-invariant array architecture;programmable local interactions among cells;randomly-selectable memory of instructions (elementary instructions are defined by specific values of the cell local interactions);random storage/retrieval of intermediate images;capability to complete algorithmic image processing tasks controlled by the user-selected stored instructions and interacting with the cache memory, etc. Thus, as illustrated in this paper, the chip is capable to complete complex spatio-temporal image processing tasks within short computation time ( similar to 200ns for linear convolutions) and using a low power budget (<1.2W for the complete chip). The internal circuitry of the chip has been designed to operate in robust manner with >7-bit equivalent accuracy in the internal analog operations, which has been confirmed by experimental measurements. Hence, to all practical purposes, processing tasks completed by the chip have the same accuracy than those completed by digital processors preceded by 7-bit digital-to-analog converters for image digitalization. Such 7-bit accuracy is enough for most image processing applications. The paper briefly describes the chip architecture and focus mostly on presenting experimental evidences of the chip functionality. Multiscale low-pass and high-pass filtering of gray-scale images, analog edges extraction, image segmentation, thresholded gradient detection, mathematical morphology operations, shortest path d

关键词： image processing Analog electronics Logic Binary data Signal processing Digital image processing Prototyping Digital signal processing image filtering Digital electronics

来源：评论

学校读者我要写书评

暂无评论

Target tracking in a multisensor environment using neural networks

Target tracking in a multisensor environment using neural ne...

引用

作者： Wong, Yee Chin The University of Arizona

学位级别：Ph.D.

The advent of technology has brought to the field of engineering many tools that were once considered impractical. For example, the increased processing speed of microprocessors now allows measurements from image sensors to be used for target tracking or target identification in real time—a task once thought unachievable. Of late the advances made in artificial intelligence (AI), specifically the artificial neural network, have sprung many different applications among which the implementation of AI controllers being the most popular. However, these advances have been slow in their implementation in the field of target tracking for several reasons. First, there seems to be a lack of sound tracking architectures that can exploit the use of artificial intelligent agents. Second, there is some difficulty in fusing the different forms of information that can be measured from the various available sensors such as the image sensor, millimeter wave radar, Doppler radar, etc. Third, the increased computational complexity due to the employment of the various sensors could limit the practical usefulness of such a tracking system. This dissertation presents a novel framework in which various dissimilar sensors can be used simultaneously to track a highly agile and non-cooperative target. The proposed framework not only allows the usage of multiple sensors to yield a robust and accurate tracker but also maintain a reasonable computational requirement. Unlike the methods proposed in the literature for the design of multi-sensor tracking systems, this dissertation presents an AI-based system that can accept, process, and fuse measurements from any number of sensors of dissimilar forms. The principal contributions of this dissertation are the following: (i) a novel architecture of a three-layer feedforward neural-network-based tracking system with the ability to fuse measurements from dissimilar sensors; (ii) a powerful optimization algorithm for training the neural network; (iii)

关键词：

来源：评论

学校读者我要写书评

暂无评论

A novel suite of tests for evaluating one-way hash functions for electronic commerce applications

A novel suite of tests for evaluating one-way hash functions...

引用

26th Euromicro conference

作者： Karras, DA Zorkadis, V Hellen Aerosp Inc Athens 16342 Greece

ISBN: (纸本)0769507816

The quality of one-way functions determines, among other parameters, in great extent the security grant provided by cryptographic protocols, which rely an them. In this paper, we propose a novel evaluation methodology of one-way hash functions for security mechanisms of electronic commerce systems as, for instance, digital signatures. The methodology consists of three parts, the bit-variance test, the entropy assessment of the digests produced and the hash-function non modeling rest. The bit-variance test shows the impact of small changes of the input message in the digest output The entropy assessment of the hash function values is its information measure and, therefore, a measure of the difficulty to find two or more messages that lead to a given digest. On the other hand, the nan modeling test (based on neural networks) should show the impossibility To model the one-way hash function by neural network architectures having the ability to approximate arbitrary real functions. Otherwise, it would indicate feasibility in modeling the hash functions by artificial intelligence techniques and consequently, in reducing the processing effort required to break them. The application of the suggested methodology to the well known MD5 one-way function reveals its potential to hash function quality characteristics evaluation. The proposed methodology may be applied in conjunction with other methods described in the technical literature.

关键词： security protocols cryptographic mechanisms authentication data integrity digital signature electronic commerce neural networks multilayer perceptrons one-way hash function quality

来源：评论

学校读者我要写书评

暂无评论

CGH-ANN based system in interference pattern recognition

CGH-ANN based system in interference pattern recognition

引用

2nd International conference on Subsurface Sensing Technologies and applications

作者： Jaroszewicz, LR Cyran, RA Mil Univ Technol Inst Appl Phys PL-00908 Warsaw 49 Poland

ISBN: (纸本)0819437743

Interference figures are often subject of interest in subsurface sensing technologies. Proper further processing of them is essential for interpretation of data covered in such images. This interpretation is often possible after recognition of the interference patterns. The article presents pattern recognition system suitable for dealing with interference figures. The system consists of optimized computer-generated hologram used for feature extraction and artificial neural network used as classifrer of features. This pattern recognizer was tested with images of intermodal interference occurring in the optical fiber. If this fiber is embedded in the polymer composite material then such subsurface sensor together with mentioned pattern recognition system can be used for determining stress and distortion of that material. Since polymers are wide utilized for different constructions, including airplane wings, presented hybrid system can be used for real time, nondestructive monitoring of working stresses occurring in these constructions. The recognition of critical compressive stress can be therefore an early alarm signal of possible forthcoming danger.

关键词： signal processing classification pattern recognition computer generated holograms neural networks

来源：评论

学校读者我要写书评

暂无评论

neural net computing for biomedical image processing

引用

Proceedings of SPIE - The International Society for Optical Engineering 1999年 3722卷 414-423页

作者： Meyer-Base, A. Univ of Florida Gainesville United States

In this paper we describe some of the most important types of neural networks applied in biomedical image processing. The networks described are variations of well-known architectures but are including image-relevant features in their structure. Convolutional neural networks, modified Hopfield networks, regularization networks and nonlinear principal component analysis neural networks are successfully applied in biomedical image classification, restoration and compression.

关键词： Multilayer neural networks

来源：评论

学校读者我要写书评

暂无评论

An investigation into Cellular neural networks internal dynamics applied to image processing 5th

引用

5th International Work-conference on artificial and Natural neural networks (IWANN 99)

作者： Monnin, D Merlat, L Köneke, A Hérault, J French German Res Inst St Louis F-68301 St Louis France Inst Natl Polytech Grenoble LIS Lab F-38031 Grenoble France

ISBN: (纸本)3540660682

Interesting perspectives in image processing with cellular neural networks can be emphasized from an investigation into the internal states dynamics of the model. Most of the cellular neural networks design methods intend to control internal states dynamics in order to pet a straight processing result. The present one involves some kind of internal states preprocessing so as to finally achieve processing otherwise unrealizable. applications of this principle to the building of complex processing schemes, gray level preserving segmentation and selective brightness variation are presented.

关键词： Cellular neural networks

来源：评论

学校读者我要写书评

暂无评论

Application of neural networks for automated x-ray image inspection in electronics manufacturing 5th

引用

5th International Work-conference on artificial and Natural neural networks (IWANN 99)

作者： König, A Herenz, A Wolter, K Tech Univ Dresden Chair Elect Devices & Integrated Circuits D-01062 Dresden Germany Tech Univ Dresden Ctr Microtech Mfg ZuP D-01062 Dresden Germany Tech Univ Dresden Chair Procedure Technol Elect D-01062 Dresden Germany

ISBN: (纸本)3540660682

artificial neural networks have proven to be valuable tools in industrial problems, e.g. for image processing, and classification in visual inspection tasks. Typically, todays successful systems have a heterogeneous structure, applying small and specialised neural networks together with classical and heuristic methods in a hybrid framework. This paper reports on the practical application of such a system, developed in prior work: which efficiently employs selected neural networks in an innovative Framework. In particular, the application in electronics manufacturing with advanced sensor technology was subject of investigation.

关键词： neural networks

来源：评论

学校读者我要写书评

暂无评论

A neural network approach for micro-PIXE data

引用

NUCLEAR INSTRUMENTS & METHODS IN PHYSICS RESEARCH SECTION B-BEAM INTERACTIONS WITH MATERIALS AND ATOMS 1999年第1-4期158卷 159-164页

作者： Rokita, E Mutsaers, PHA Quaedackers, JA Tabor, Z de Voigt, MJA Jagiellonian Univ Inst Phys PL-30059 Krakow Poland Eindhoven Univ Technol Cyclotron Lab NL-5600 MB Eindhoven Netherlands

The application of the artificial neural network for the processing of one-dimensional micro-PIXE data is described. The network architecture, selection of the transfer function as well as the training and verification operations are described in detail. The performed reconstructions confirm that the neural network may be used for improvement of the resolution and for processing of low statistics data. The limitations of the neural network application for two-dimensional images are discussed. (C) 1999 Elsevier Science B.V. All rights reserved.

关键词： micro-PIXE image processing artificial neural networks

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：