检索结果-内蒙古大学图书馆

17th National Radio science Conference, NRSC 2000

作者： El-Bakry, H.M. Abo-Elsoud, M.A. Kanel, M.S. Faculty of Computer Science and Information System Mansoura University Egypt Electronics and Elec. Comm. Dept. Faculty of Engineering Mansoura University Egypt Systems Design Eng. Dept. University of Waterloo Canada

ISBN: (纸本)9775031648

A new concept for detection of human faces is presented. An efficient approach to reduce the computation time taken by neural networks for the searching process is introduced. We combine both Fourier and wavelet transforms with cooperative modular neural networks (MNNs) to enhance the performance of the detection process. Such an approach is applied to identify human faces automatically in cluttered scenes. Here, neural networks are used to test whether a window of 20x20 pixels contains a face or not. The major difficulty in the learning process comes from the large database required for face/nonface images. A simple design for cooperative MNNs is presented to solve this problem by dividing these data into some groups. Such division results in reduction of computational complexity and thus decreasing the time and memory needed during the test of an image. In order to have a faster detection algorithm, a combination of the FFT and the wavelet transform is made in order to reduce the elapsed time during the test phase and enhance the detection performance. Feature measurements of the input faces are made through Fourier descriptors which are insensitive to rotation, translation and scaling. Such a feature is modified to reduce the number of neurons in the hidden layer. The second stage extracts wavelet coefficients that have been shown to provide advantages in terms of better representation for a given data to be compressed. Finally, the resulting vector is fed to one of five neural networks for face detection. Compared to previous work in face detection, the use of this combination reduces the number of neurons required for neural networks. Simulation results for the proposed algorithm show good performance on detecting faces with rotation, occlusion, noise, or change in illumination. © 2000 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Integrating Fourier descriptors and PCA with neural networks for face recognition 17

Integrating Fourier descriptors and PCA with neural networks...

引用

17th National Radio science Conference, NRSC 2000

作者： El-Bakry, H.M. Abo-Elsoud, M.A. Kamel, M.S. Faculty of Computer Science and Information System Mansoura University Egypt Electronics and Elec. Comm. Dept. Faculty of Engineering Mansoura University Egypt Systems Design Eng. Dept. University of Waterloo Canada

ISBN: (纸本)9775031648

A new approach to the face recognition problem is presented through combining Fourier descriptors with principal component analysis (PCA) and neural networks. Here the faces are vertically oriented frontal view with scaling, orientation, expression, and illumination changes. There are many research activities on face recognition using the face space which is described by a set of eigenfaces. Each face is efficiently represented by its projection onto the space expanded by the eigenfaces and has a new descriptor. Previous work on eigenface has shown that it performs well only with changes in expression, but results are poor in the case of rotating, or scaling the input face. In order to enhance the performance of the eigenfaces technique to accommodate other variations of the input face, the Fourier vector of each face is projected in the eigenspace. Neural networks are used to recognize the face through learning the correct classification of these new descriptors. A real-time system has been created which combines the face detection and recognition techniques. A recognition rate of 91% has been achieved over real tests. It is also shown that our proposed system behaves accurately in the case of rotated or scaled faces as well as for changes in expression. © 2000 IEEE.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Configuring Role-Based Access Control to Enforce Mandatory and Discretionary Access Control Policies

引用

ACM Transactions on information and System Security 2000年第2期3卷 85-106页

作者： Osborn, Sylvia Sandhu, Ravi Munawer, Qamar Dept. of Computer Science The University of Western Ontario London ON N6A 5B7 Canada Laboratory for Information Security Technology MS4A4 Information and Software Engineering Department George Mason University Fairfax VA 22030 United States

Access control models have traditionally included mandatory access control (or lattice-based access control) and discretionary access control. Subsequently, role-based access control has been introduced, along with claims that its mechanisms are general enough to simulate the traditional methods. In this paper we provide systematic constructions for various common forms of both of the traditional access control paradigms using the role-based access control (RBAC) models of Sandhu et al., commonly called RBAC96. We see that all of the features of the RBAC96 model are required, and that although for the mandatory access control simulation, only one administrative role needs to be assumed, for the discretionary access control simulations, a complex set of administrative roles is required. © 2000, ACM. All rights reserved.

关键词： discretionary access control lattice-based access control Management mandatory access control Role-based access control Security

来源：评论

学校读者我要写书评

暂无评论

Efficient specialisation in prolog using the hand-written compiler generator LOGEN

Efficient specialisation in prolog using the hand-written co...

引用

WOID'99, Workshop on Optimization and Implementation of Declarative Programs (in Connetion with ICLP'99, International Conference on Logic)

作者： Leuschel, Michael Jørgensen, Jesper Declarative Systems and Software Engineering Dept. of Electronics and Computer Science University of Southampton Southampton SO17 1BJ United Kingdom Dept. of Mathematics and Physics Royal Veterinary and Agricultural University Thorvaldsensvej 40 DK-1871 Frederiksberg C Denmark

The so called "cogen approach" to program specialisation, writing a compiler generator instead of a specialiser, has been used with considerable success in partial evaluation of both functional and imperative languages. In earlier work we have shown that this approach is also applicable to partial evaluation of logic programming languages, also called partial deduction. In this paper we extend upon this by allowing partially instantiated datastructures (via binding types), which are especially important in the context of logic programming. We also extend cogen to directly support a large part of Prolog's declarative and non-declarative features and how semi-online specialisation can be efficiently integrated. Benchmarks show that the resulting cogen is very efficient, generates very efficient generating extensions (executing up to several orders of magnitude faster than current online systems) which in turn perform very good and non-trivial specialisation, even rivalling existing online systems. © 2000 Published by Elsevier science B.V.

关键词： Program compilers

来源：评论

学校读者我要写书评

暂无评论

Performance evaluation of line drawing recognition systems

Performance evaluation of line drawing recognition systems

引用

15th International Conference on Pattern Recognition, ICPR 2000

作者： Chhabra, Atul K. Phillips, Ihsin T. Bell Atlantic Network Systems Advanced Technology White PlainsNY10604 United States Computer Science/Software Engineering Dept. Seattle University SeattleWA98122 United States

ISBN: (纸本)0769507506

Presents the results of the third international graphics recognition contest. We evaluated the performance of four different vectorization systems on scanned images of CAD drawings. The EditCost Index was used for comparative evaluation of the systems. The performance curves of the systems on the test images are presented in this paper. © 2000 IEEE.

关键词： Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

A design of an associative memory array processor for ultrasonograph image acquisition and processing

A design of an associative memory array processor for ultras...

引用

作者： Aly, Gamal M. El-Nadi, Nabeel M. Fayed, Zaki T. Faheem, Hossam M. Dept. of Comp. and Control Systems Ain Shams University Faculty of Engineering Cairo Egypt Information Technology Institute Cairo Egypt Department of Computer Science Ain Shams University Fac. of Comp. and Info. Science Cairo Egypt

This paper describes a design of an associative memory array processor that can be used in the acquisition and processing of ultrasonograph images. The major concept is to design a parallel architecture that reduces task's execution time by analyzing multiple parts of the image concurrently. The architecture constitutes a distinctive type of single-instruction stream, multiple-data stream machine that is built around content-addressable associative memory slabs, that allow parallel access of multiple memory words. The basic building block of this architecture is a one-pixel processing element, which can perform the standard load (data acquisition) function and also contains some special comparison logic to enable its content to be compared with an external data. Several image processing operations are implemented in parallel, among them: component labeling, size filtering, pattern centralization, and pattern recognition. The proposed novel architecture can label specific regions into the image and isolate them intelligently. It is also capable of storing templates that may be considered as references for similar cases. The system is able to perform learning process and extract features from several input patterns and store the reference pattern in a slice. Moreover, the system is capable of comparing an input image with a pre-stored template during recognition process. The proposed architecture is of interest because it speeds up the recognition process and helps radiology specialists to write their reports confidently.

关键词： Ultrasonic imaging

来源：评论

学校读者我要写书评

暂无评论

Efficient Specialisation in Prolog Using the Hand-Written Compiler Generator LOGEN

引用

Electronic Notes in Theoretical computer science 2000年第2期30卷 157-162页

作者： Michael Leuschel Jesper Jørgensen Declarative Systems and Software Engineering Dept. of Electronics and Computer Science University of Southampton Southampton SO17 1BJ UK Dept. of Mathematics and Physics Royal Veterinary and Agricultural University Thorvaldsensvej 40 DK-1871 Frederiksberg C Denmark

The so called “ cogen approach” to program specialisation, writing a compiler generator instead of a specialiser, has been used with considerable success in partial evaluation of both functional and imperative languages. In earlier work we have shown that this approach is also applicable to partial evaluation of logic programming languages, also called partial deduction. In this paper we extend upon this by allowing partially instantiated datastructures (via binding types), which are especially important in the context of logic programming. We also extend cogen to directly support a large part of Prolog's declarative and non-declarative features and how semi-online specialisation can be efficiently integrated. Benchmarks show that the resulting cogen is very efficient, generates very efficient generating extensions (executing up to several orders of magnitude faster than current online systems) which in turn perform very good and non-trivial specialisation, even rivalling existing online systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Tightly coupling authoring and evaluation in an integrated tool to support iterative design of interactive hypermedia educational manuals 00

Tightly coupling authoring and evaluation in an integrated t...

引用

Proceedings of the 3rd conference on Designing interactive systems: processes, practices, methods, and techniques

作者： Selma Holmquist N. Hari Narayanan Departamento de Cálculo Facultad de Ingeniería Universidad de Los Andes Mérida Venezuela Intelligent & Interactive Systems Laboratory Dept. of Computer Science & Software Engineering Auburn University Auburn AL

ISBN: (纸本)9781581132199

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a *** this paper we present a framework for the iterative design of interactive Hypermedia Educational Manuals, implemented in a software tool that integrates authoring and evaluation support in order to speed up iterative design cycles. Two unique features of our approach are the automatic generation of a structural description of the manual being designed and the automatic incorporation of interaction data logging elements in the manual during the authoring phase. These are then used by an evaluation tool to generate statistical analyses and graphical presentations of user interactions with the manual and redesign recommendations. Thus, the architecture of this tool embodies a tight coupling between the design of Hypermedia Educational Manuals and the evaluation of their instructional effectiveness. An experiment was carried out in which a prototype manual was created, tested with a group of students, redesigned based on analyses and recommendations provided by the evaluation tool, and then re-evaluated using data from a second group of students. This experiment showed that the integrated tool does help simplify the evaluation process and improve the efficiency of iterative design cycles.

关键词： empirical study interaction data analysis and visualization iterative design tool evaluation hypermedia authoring

来源：评论

学校读者我要写书评

暂无评论

Cost model and copyright management for 3D digital contents using multilevel complex objects

引用

systems and computers in Japan 2000年第12期31卷 73-82页

作者： Kidawara, Yutaka Sugiyama, Yuichi Tanaka, Katsumi Telecom. Adv. Organization of Japan Kobe 650-0046 Japan Div. of Media and Computer Sciences Grad. Sch. of Science and Technology Kobe University Kobe 657-0013 Japan Dept. of Comp. and Syst. Engineering Grad. Sch. of Science and Technology Kobe University Kobe 657-0013 Japan Instrumentation Department School of Engineering Kobe University Kobe Steel Ltd. Telecom. Adv. Organization of Japan Dept. of Comp. and Syst. Engineering Grad. Sch. of Sci. and Engineering Kobe University Information Processing Council Syst. Contr. and Info. Association Eng. and Information Department Kyoto University Education Department Kobe University Engineering School Engineering Department Div. of Media and Computer Sciences Grad. Sch. of Science and Technology Database Systems Research Group Information Processing Council Next Generation Digit. Image C. Res. Distributed Devmt.-type D. Min. of Educ.'s Focal Topic Research Kobe Multimedia Internet Cooperative Information Processing Council Artif. Intelligence Association IEEE Computer Society

The authors discuss multimedia data communications using the Internet from the standpoint of providing services, and propose a cost model based on multilevel complex objects for the purpose of responding to the various needs of users. The proposed cost model creates multiple levels of the service which provide each element of the complex object, and then introduces the concept of `service ranges' that can dynamically vary the service which can be received within the scope of the price paid. Conventional multimedia data can only provide one service. However, the authors' service can be selected dynamically from within a range based on the price paid by the user. In order to evaluate these methods, the authors created a framework which can be applied to 3DCG content using VRML by using Java and OODBMS. In addition, rights such as copyrights that are frequently a part of 3DCG content must be protected. The proposed multilevel complex object can confirm a user's rights by using a built-in user authentication function. Thus, copyright management features that provide services within a service range available to valid users and block out illegal users can be realized.

关键词： Multimedia systems

来源：评论

学校读者我要写书评

暂无评论

On Built-in Test Reuse in Object-Oriented Framework Design

引用

ACM Computing Surveys 2000年第1期32卷 7-7页

作者： Wang, Yingxu Patel, Dilip King, Graham Court, Ian Staples, Geoff Ross, Margaret Fayad, Mohamed School of Computing Information Systems and Mathematics South Bank University London SE1 0AA London 103 Borough Road United Kingdom Research Centre for Systems Engineering Southampton Institute Southampton SO14 0YN United Kingdom Dept. of Computer Science University of Nevada Reno Nevada 89557 United States

Object-oriented frameworks have extended reusability of software from code modules to architectural and domain information. This paper further extends software reusability from code and architecture to built-in tests (BITs) in object-oriented framework development. Methods for embedding BITs at object and object-oriented framework levels are addressed. Behaviours of objects and object-oriented frameworks with BITs in the normal and test modes are analyzed. Systematic reuse methods of BITs in object-oriented framework development are provided. The most interesting development in the paper is that the BITs in object-oriented frameworks can be inherited and reused as that of code. Therefore testability and maintainability of the test-built-in object-oriented frameworks can be improved by the BIT approach. The BIT method can be used in analysis, design and coding of object-oriented frameworks. © 2000, ACM. All rights reserved.

关键词： built-in test code reuse framework framework reuse object-oriented technology pattern software engineering test reuse testable software

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：