检索结果-内蒙古大学图书馆

National Conference on Radio science (NSRC)

作者： H.M. El-Bakry M.A. Abo-Elsoud M.S. Kamel Faculty of Computer Science &Information System Mansoura University Egypt Systems Design Engineering Department University of Waterloo Canada

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.

关键词： Principal component analysis Neural networks Face recognition Face detection Lighting Pattern recognition Humans Computational modeling Image reconstruction Information systems

来源：评论

学校读者我要写书评

暂无评论

Modular neural networks for face detection

Modular neural networks for face detection

引用

National Conference on Radio science (NSRC)

作者： H.M. El-Bakry M.A. Abo-Elsoud M.S. Kanel Faculty of Computer Science&Information System Mansoura University Egypt Electronics & Electrical Comm.Department Faculty of Engineering Mansoura University Egypt

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 20/spl times/20 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.

关键词： Neural networks Face detection Testing Humans Wavelet transforms Neurons computer networks Fourier transforms Layout Image databases

来源：评论

学校读者我要写书评

暂无评论

The effects of MAC protocols on ad hoc network communication

The effects of MAC protocols on ad hoc network communication

引用

IEEE Conference on Wireless communications and Networking

作者： E.M. Royer Sung-Ju Lee C.E. Perkins Department of Electrical and Computer Engineering University of California Santa Barbara USA Department of Computer Science University of California Los Angeles USA Communication System Laboratory Nokia Research Center Finland

ISBN: (纸本)0780365968

As mobile computing gains popularity, the need for ad hoc routing protocols will continue to grow. There have been numerous simulations comparing the performance of these protocols under varying conditions and constraints. One question that arises is whether the choice of MAC protocol affects the relative performance of the routing protocols being studied. This paper investigates the answer to that question by simulating the performance of three ad hoc routing protocols when run over different MAC protocols. It is determined that the choice of MAC layer protocol does, in fact, affect the relative performance of the routing protocols.

关键词： Media Access Protocol Ad hoc networks Routing protocols Access protocols Mobile communication computer science Laboratories Mobile computing Computational modeling Unicast

来源：评论

学校读者我要写书评

暂无评论

Compound splitting and lexical unit recombination for improved performance of a speech recognition system for German parliamentary speeches

Compound splitting and lexical unit recombination for improv...

引用

6～(th) International Conference on Spoken Language Processing

作者： Martha Larson Daniel Willett Joachim Khler Gerhard Rigoll IMK: Institute for Media Communication GMD German National Research Institute for Information Technology Sankt Augustin Germany Department of Computer Science Faculty of Electrical Engineering Duisburg University Duisburg Germany Department of Computer Science Faculty of Electrical Engineering Duisburg University Duisburg Germany IMK: Institute for Media Communication GMD German National Research Institute for Information Technology Sankt Augustin Germany Department of Computer Science Faculty of Electrical Engineering Duisburg University Duisburg Germany

This paper proposes a novel combined compound splitting and phrase recombination method that optimizes the composition of the speech recognition lexicon for a given domain. Data-driven compound word splitting is followed by iterative recombination of high frequency combinations. Language model perplexity and size are the criteria used to identify a balance between compound decomposition, which reduces OOV, and lexical unit recombination, which packs additional context into a fixed-size vocabulary. The method provides a basis for lexicon design for a LVCSR system on the domain of German parliamentary speeches that is to be used as the foundation of a spoken document information retrieval system. The approach achieves a 35% reduction in OOV without a prohibitively large sacrifice in recognition performance.

关键词： Compound splitting and lexical unit recombination for improved performance of a speech recognition system for German parliamentary speeches

来源：评论

学校读者我要写书评

暂无评论

Data link control layer performance for variable packet size and fixed packet size (wireless ATM packet)

Data link control layer performance for variable packet size...

引用

IEEE Region 10 International Conference TENCON

作者： S.K.A. Yaklaf B.M. Ali V. Prakash S. Khatun A. Gasim Department of Computer & Communication System Eng Faculty of Engineering Universiti Putra Malaysia Serdang Selangor Darul Ehsan Malaysia Universiti Putra Malaysia Serdang Selangor MY

This paper deals with the transmission of digital data in ATM like format over a noisy wireless channel affected by burst of errors. It evaluates and compares go-back-N (GBN) and selective repeat (SR) for non-real time traffic over the wireless portion of the network for variable packet size and fixed packet size, and the effect of packet loss and check-sum error percentages on the throughput. Results show that SR-ARQ achieves better throughput under a wide variety of error rate conditions than GBN-ARQ.

关键词： Size control Asynchronous transfer mode Automatic repeat request Forward error correction Error correction Wireless application protocol Strontium Radio link Telecommunication traffic Throughput

来源：评论

学校读者我要写书评

暂无评论

Robust global terminal sliding mode control of SISO nonlinear uncertain systems

Robust global terminal sliding mode control of SISO nonlinea...

引用

IEEE Conference on Decision and Control

作者： Shuanghe Yu Xinghuo Yu Man Zhihong Faculty of Informatics and Communication Central Queensland University Rockhampton QLD Australia Department of Electrical Engineering and Computer Science University of Tasmania Hobart Australia

ISBN: (纸本)0780366387

A global terminal sliding mode controller is proposed for higher order SISO nonlinear dynamic systems by employing the fast terminal sliding mode concept in both the reaching phase and the sliding phase. The inherent dynamical properties of the fast terminal sliding modes and the recursive mechanism for application in higher order systems are explored. A control design procedure is developed. It is shown that, by suitably choosing the parameters of the fast terminal sliding modes, the system state variables will reach the fast terminal sliding manifolds within a desired finite time, and stay in the sliding modes thereafter, resulting in the convergence to the equilibrium in a finite time which can also be prespecified. The control law designed, which is called "the global terminal sliding mode control", is nonlinear and continuous. It does not cause chattering in the reaching phase and sliding phase. The robustness analysis shows that the proposed global terminal sliding mode controller has superior robustness in system uncertainties and external disturbances. Simulation studies are presented to validate the proposed scheme.

关键词： Robust control Sliding mode control Uncertain systems Control systems Nonlinear control systems Convergence Uncertainty Robustness Force control Informatics

来源：评论

学校读者我要写书评

暂无评论

The removal of secondaries of Jawi characters

The removal of secondaries of Jawi characters

引用

IEEE Region 10 International Conference TENCON

作者： K. bin Omar R. bin Mahmoud M.N. bin Sulaiman A.R. bin Ramli Department of Communication and Computer SystemFaculty of Engineering Universiti Putra Malaysia Serdang Selangor Darul Ehsan Malaysia Department of Computer ScienceFaculty of Computer Science and Information Technology Universiti Putra Malaysia Serdang Selangor Darul Ehsan Malaysia Department of System Science & ManagementFaculty of Information Science and Technology Universiti Kebangsaan Malaysia Malaysia

This paper is presented to explain the steps in removing the secondary part of Jawi characters (such as dots, hamzah, and madda). The method used is based on the connected component labelling algorithm or CCLA and is added with the secondary type detection algorithm (STDA) by Bushofa and Spann (see Image and Vision Computing, vol.15, p.167-79, 1997). Several steps in the algorithm however, have been modified in order for it to be matched with the handwritten Jawi characters. Several samples of the result from the suggested algorithm are also presented. The result promises a good outcome.

关键词： computer science Character recognition Iterative algorithms Information technology Optical character recognition software Pixel Information management Technology management Information science Labeling

来源：评论

学校读者我要写书评

暂无评论

All-zero-AC block detection using energy preservation theorem for H.263 video coding

All-zero-AC block detection using energy preservation theore...

引用

IEEE Region 10 International Conference TENCON

作者： Soong Der Chen A.R. Ramli M.R. Mukerjee Fac. of Eng. Univ. Putra Malaysia Selangor Malaysia Department of Computer and Communication System Faculty of Engineering Universiti Putra Malaysia Serdang Malaysia Universiti Putra Malaysia Serdang Selangor MY

This paper present a technique used in H.263 video coding to detect all-zero-AC occurrence without performing the transformation and quantization process. It is developed based on the energy preservation theorem. When the total AC energy in the pre-transform domain is known, the occurrence of all-zero-AC is predictable by comparing the total AC energy with the quantization threshold Q/sup 2/. The evaluations indicate that its prediction efficiency and speed gain depends on motion activities, level of Q and also the relative overhead imposed by the shortcut itself. In conclusion, the proposed new algorithm is expected to be practical in all common environments (low bit rate) targeted by H.263 standards as no negative speed gain is observed during the evaluation for all range of QP (Q=2.5QP).

关键词： Video coding Discrete cosine transforms Motion estimation Quantization Video compression Videoconference Transform coding communication systems Power engineering and energy systems engineering and theory

来源：评论

学校读者我要写书评

暂无评论

Information presentation by inferring user's interests based on individual conceptual spaces

引用

systems and computers in Japan 2000年第10期31卷 41-55页

作者： Sumi, Kaoru Sumi, Yasuyuki Mase, Kenji Nakasuka, Shin-Ichi Hori, Koichi Breakthrough21 Nishida Project Communication Research Laboratory Hyogo 651-2401 Japan ATR Media Intgn. Commun. Res. Labs. Kyoto 619-0288 Japan Faculty of Engineering University of Tokyo 153-8904 Japan Science University of Tokyo University of Tsukuba University of Tokyo ATR Media Intgn. Commun. Res. Labs. Breakthrough21 Nishida Project Communications Research Laboratory Min. of Posts and Telecommunications Japan. Soc. for Artif. Intelligence Info. Processing Society of Japan Waseda University IEICE IPSJ Amer. Assoc. for Artif. Intelligence Nagoya University Department 2 Nippon Telegraph and Tel. Corp. NTT Human Interface Laboratories MIT's Media Laboratory IPSJ IEICE IEEE Computer Society

We present the system called Takealook, which personalizes information presentation according to the user's interests and knowledge. The system infers the user's interests from her/his question-and-answer interactions and the information presenters' conceptual spaces by using the related method of collaborative filtering. It then provides additional information about current contents and also recommends other related contents. The user's interests are represented by her/his own individual conceptual space (i.e., a set of related keywords) which is adapted to her/his preferences. In this paper we describe a method for personalizing the information presentation, implementating the system at reviewing an exhibition, and experimental results.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Visual, tactile and gazing line - action linkage system for 3D shape evaluation in virtual space

Visual, tactile and gazing line - action linkage system for ...

引用

IEEE International Workshop on Robot and Human communication (ROMAN)

作者： M. Okubo T. Watanabe Department of System Engineering Faculty of Computer Science and System Engineering Okayama Prefectural University Soja Okayama Japan

ISBN: (纸本)0780358414

A new virtual system for shape evaluation is proposed, which integrates the visual information in virtual space and the tactile and gazing line-action information in real space. The preference of 3D shape images in the proposed virtual space is compared with that of the real photoforming products made from the same data in 28 subjects by the sensory evaluation of paired comparison and the questionnaire analysis. It was found that the preference for shapes was consistent in both spaces in the relation of preference among shapes based on the Bradley-Terry model in sensory evaluation. This indicates that the proposed system provides almost the same environment as the real space for shape evaluation. The results of questionnaire also indicate that the proposed system is adequate to evaluate the 3D shapes in virtual space. The system enables one to investigate the human's sense for shape evaluation by handling the visual, tactile and gazing fine-action information.

关键词： Couplings computer displays Three dimensional displays Magnetic heads Graphics systems engineering and theory Magnetic sensors Watches Shape measurement Workstations

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：