检索结果-内蒙古大学图书馆

Outlier detection by weighted mercer-kernel based fuzzy clustering algorithm

Iranian Journal of Electrical and computer Engineering 2005年第2期4卷 129-136页

作者： Shen, Hongbin Yang, Jie Dong, Yifei Wang, Shitong College of Computer and Information Engineering Hohai University Changzhou Jiangsu China Department of Image Processing and Pattern Recognition Jiaotong University Shanghai China School of Computer Science and Engineering University of New South Wales Australia School of Information Southern Yantze University Wuxi Jiangsu China Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University China IEEE Institute of National Automation Department of Information Southern Yangtse University Polytechnic University of Hongkong Advanced Computing Research Center Bristol University United Kingdom

Outliers are data values that lie away from the general cluster of other data values. Detecting the outliers of a dataset is an important research topic for data cleaning and finding new useful knowledge in many research areas, i.e. data mining, pattern recognition, etc. In the past decades, many useful algorithms were proposed in the literature. In this paper, a new fuzzy kernel-clustering algorithm with outliers (FKCO) is presented to locate critical areas that are often represented by only a few outliers. Theoretic analysis also shows that FKCO can converge to a local minimum of the objective function. Finally, based on the information theory, a new criterion for finding outliers is also proposed. Simulations of different types of datasets demonstrate the feasibility of this new method. © 2005 JD.

关键词： Fuzzy control

来源：评论

学校读者我要写书评

暂无评论

Radar backscattering model for multilayer mixed-species forests

Radar backscattering model for multilayer mixed-species fore...

引用

作者： Liang, Pan Moghaddam, Mahta Pierce, Leland E. Lucas, Richard M. IEEE Atmospheric and Environmental Research Inc. Lexington MA Department of Electrical Engineering and Computer Science Radiation Laboratpry University of Michigan Ann Arbor URSI Commission B Electromagnetics Academy Phi Kappa Phi Tau Beta Pi Eta Kappa Nu Microwave Image Processing Facility Within the Radiation Laboratory Electrical Engineering and Computer Science Department University of Michigan University of Wales Aberystwyth Aberystwyth United Kingdom Radiation Laboratory Department of Electrical Engineering and Computer Science University of Michigan Ann Arbor MI 48109-2122 United States Institute of Geography and Earth Sciences University of Wales Aberystwyth SY23 3DB United Kingdom

A multilayer canopy scattering model is developed for mixed-species forests. The multilayer model provides a significantly enhanced representation of actual complex forest structures compared to the conventional canopy-trunk layer models. Multilayer Michigan Microwave Canopy Scattering model (Multi-MIMICS) allows overlapping layer configuration and a tapered trunk model applicable to forests of mixed species and/or mixed growth stages. The model is the first-order solution to a set of radiative transfer equations and includes layer interactions between overlapping layers. It simulates SAR backscattering coefficients based on input dimensional, geometrical, and dielectric variables of forest canopies. The Multi-MIMICS is an efficient realization of actual forest structures and can be shaped for specific interest of forest parameters. We present the model's application and validation in the paper. The model is parameterized using data collected from a 220 000-ha area of forests in central Queensland, Australia. Fifteen 50 × 50 m test sites representing the general forest diversity and growth stages are chosen as ground truth. Polarimetric backscattering Airborne SAR (AIRSAR) data of the same area are acquired to validate the model simulations. The model predicts SAR backscattering coefficients of the test areas. Simulation results show a good agreement with AIRSAR data at most frequencies and polarizations. The simulated backscattering coefficient from the multilayer model and the standard MIMICS are also compared and significant improvements are observed. © 2005 IEEE.

关键词： Mathematical models

来源：评论

学校读者我要写书评

暂无评论

Lossy-to-lossless block-based compression of hyperspectral volumetric data

Lossy-to-lossless block-based compression of hyperspectral v...

引用

2004 International Conference on image processing, ICIP 2004

作者： Tang, Xiaoli Pearlman, William A. Center for Image Processing Research Electrical Computer and Systems Engineering Department Rensselaer Polytechnic Institute Troy NY 12180-3590

An embedded, block-based, wavelet transform coding algorithm of low complexity is proposed. Three-Dimensional Set Partitioned Embedded bloCK(3D-SPECK) efficiently encodes hyperspectral volumetric image data by exploiting the dependencies in all dimensions. Integer wavelet transform is applied to enable lossy and lossless decompression from the same bit stream. We demonstrate that 3D-SPECK, a wavelet domain algorithm, like other time domain algorithms, can preserve spectral profiles well. Airborne Visible Infrared Imaging Spectrometer (AVIRIS) imagery is used to test the proposed algorithm. Results show that 3D-SPECK, in addition to being very flexible, retains all the desirable features of compared state-of-the-art algorithms and is highly competitive to 3D-SPIHT and better than JPEG2000 multi-component in compression efficiency. © 2004 IEEE.

关键词： image compression

来源：评论

学校读者我要写书评

暂无评论

On Estimation Of 3D Hand Position Using Stereo Vision 19

On Estimation Of 3D Hand Position Using Stereo Vision

引用

19th International Conference on computers and Their Applications, CATA 2004

作者： Teruel, M.B. Kubushyna, O. El-Khater, R. Yfantis, E.A. Boyle, R. Computer Graphics and Image Processing Laboratory School of Computer Science University of Nevada Las Vegas Las VegasNV89154-4019 United States NASA Ames Research Center Moffett FieldCA94035-1000 United States

ISBN: (纸本)9781618395511

In this paper an approach for reconstructing the position of an object from a pair of stereo images that allows for a fast and effective hand tracking and 3D gesture reconstruction is presented. The algorithm will serve as a building block for more advanced tasks such as the reconstructing a complete 3D hand model from multiple views using feature extraction based on color and shape. Copyright © (2004) by the International Society for computers and Their Applications. All rights reserved.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

Object recognition using local information content

Object recognition using local information content

引用

International Conference on Pattern Recognition

作者： G. Fritz L. Paletta H. Bischof Joanneum Research Institute of Digital Image Processing Graz Austria Institute of Computer Graphics and Vision Graz University of Technology Graz Austria

Object identification from local information has recently been investigated with respect to its potential for robust recognition, e.g., in case of partial object occlusions, scale variation, noise, and background clutter in detection tasks. This work contributes to this research by a thorough analysis of the discriminative power of local appearance patterns and by proposing to exploit local information content for object representation and recognition. In a first processing stage, we localize discriminative regions in the object views from a posterior entropy measure, and then derive object models from selected discriminative local patterns. Object recognition is then applied to test patterns with associated low entropy using an efficient voting process. The method is evaluated by various degrees of partial occlusion and Gaussian image noise, resulting in highly robust recognition even in the presence of severe occlusion effects.

关键词： Object recognition Noise robustness Entropy Background noise Object detection Information analysis Pattern analysis Pattern recognition Testing Voting

来源：评论

学校读者我要写书评

暂无评论

High-level design environment for massive parallel VLSI-implementations of statistical signal- and image processing models

High-level design environment for massive parallel VLSI-impl...

引用

2004 IEEE International Symposium on Circuits and Systems - Proceedings

作者： Stilkerich, Stephan Anlauf, Joachim K. EADS Corporate Research Center Image and Signal Processing Groupe 81663 Munich Germany University of Bonn Institute of Computer Science II 53117 Bonn Germany

In this paper we introduce and describe a novel generic and semiconductor-technology independent hardware development environment for a class of statistical signal- and image processing models. The statistical signal- and image processing approach under consideration formally adopts the Bayesian paradigm and uses discrete Markov Random Field (MRF) methods for the processing models to derive the joint distribution of signal- and image-processing problems by means of mathematically and computationally tractable conditional distributions. We experimentally demonstrate and prove the capabilities respectively the concepts of the proposed novel high-level design environment by detailed chip-layouts of different neighbourhood topologies and a single processing element of a MRF- architecture, which solves the image processing problem of noise removing, restoration and intensity-level preserving.

关键词： VLSI circuits

来源：评论

学校读者我要写书评

暂无评论

Lossy-to-lossless block-based compression of hyperspectral volumetric data

Lossy-to-lossless block-based compression of hyperspectral v...

引用

IEEE International Conference on image processing

作者： Xiaoli Tang W.A. Pearlman Center for Image Processing Research Electrical Computer and Systems Engineering Department Rensselaer Polytechnic Institute Troy NY USA

An embedded, block-based, wavelet transform coding algorithm of low complexity is proposed. Three-dimensional set partitioned embedded block (3D-SPECK) efficiently encodes, hyperspectral volumetric image data by exploiting the dependencies in all dimensions. Integer wavelet transform is applied to enable lossy and lossless decompression from the same bit stream. We demonstrate that 3D-SPECK, a wavelet domain algorithm, like other time domain algorithms, can preserve spectral profiles well. Airborne visible infrared imaging spectrometer (AVIRIS) imagery is used to test the proposed algorithm. Results show that 3D-SPECK, in addition to being very flexible, retains all the desirable features of compared state-of-the-art algorithms and is highly competitive to 3D-SPIHT and better than JPEG2000 multi-component in compression efficiency.

关键词： Hyperspectral imaging Partitioning algorithms image coding Transform coding Wavelet transforms Streaming media Wavelet domain Infrared imaging Infrared spectra Spectroscopy

来源：评论

学校读者我要写书评

暂无评论

High-level design environment for massive parallel VLSI-implementations of statistical signal- and image processing models

High-level design environment for massive parallel VLSI-impl...

引用

IEEE International Symposium on Circuits and Systems (ISCAS)

作者： S. Stilkerich J.K. Anlauf Image and Signal Processing Groupe EADS Corporate Research Center Munich Germany Institute of Computer Science II University of Bonn Bonn Germany

In this paper we introduce and describe a generic and semiconductor-technology independent hardware development environment for a class of statistical signal- and image processing models. The statistical signal- and image processing approach under consideration formally adopts the Bayesian paradigm and uses discrete Markov random field (MRF) models for the processing models to derive the joint distribution of signal- and image processing problems by means of mathematically and computationally tractable conditional distributions. We experimentally demonstrate and prove the capabilities respectively the concepts of the proposed high-level design environment by detailed chip layouts of different neighbourhood topologies and a single processing element of a MRF-architecture, which solves the image processing problem of noise removing, restoration and intensity-level preserving.

关键词： Signal design Signal processing image processing Mathematical model Hardware Bayesian methods Markov random fields Distributed computing Topology Working environment noise

来源：评论

学校读者我要写书评

暂无评论

Enhancement of stents using interference of low-frequency ultrasonic echo signals

引用

Journal of Medical Ultrasonics 2004年第2期31卷 67-73页

作者： Ohashi, Gosuke Ohya, Akihisa Tobise, Kazimobu Akiyama, Iwaki Faculty of Engineering Shizuoka University Hamamatsu Japan Institute of Information Sciences and Electronics University of Tsukuba Tsukuba Japan Shoryo Electronic Corporation Kamakura Japan Faculty of Engineering Shonan Institute of Technology Fujisawa Japan Image Processing and Vision Research Laboratory Department of Electrical and Computer Engineering University of California at Santa Barbara Santa Barbara CA 93106-9560 United States

Purpose. We set out to enhance the imaging of stents used for coronary coarctation surgery without imaging the reticulation of the stent. Because the stent is a reticulated structure, there is a relation between ultrasound wavelength and the interstice reticulation that produces the echo. Methods. First we performed computer simulation by ultrasound frequency of transmitted signals to analyze this relation. Then, instead of controlling the transmitted wave, we processed the returned signals through a band-pass filter because of the difficulty of controlling the transmitted waves of diagnostic ultrasound equipment. Following this, we conducted experiments on an agar gel phantom containing a stent to verify the effectiveness of this method. Results. The simulation confirmed that the stent was apparent when the ultrasonic wavelength equaled the product of an integer and twice the interval of the reticulation of the stent. Application of a band-pass filter of 0.8 to 1.5MHz to the waveform returned from the agar gel phantom containing the stent. Conclusions. The effectiveness of this method in depicting the stent was confirmed. © The Japan Society of Ultrasonics in Medicine 2004.

关键词： Interference Received waveform Signal processing Stent Ultrasonic echography

来源：评论

学校读者我要写书评

暂无评论

Collaborative interactions on 3D display for multi-user game environments

引用

6th Asia Pacific Conference on computer Human Interaction, APCHI 2004

作者： Choi, Jeong-Dan Jang, Byung-Tae Hwang, Chi-Jeong Telematics Solution Research Team Telematics Research Department Electronic and Telecommunications Research Institute 161 Gajeong-dong Yuseong-gu Dajeon305-350 Korea Republic of Image Processing Laboratory Computer Engineering Department Chungnam National University 220 Gung-dong Yuseong-gu Daejeon305-764 Korea Republic of

ISBN: (纸本)3540223126

This paper describes a method to integrate VR interfaces on 3D display for multiuser game environments, which addresses the problem of synchronization and calibration multiple devices together to treat game events. The challenge we interest in is how to build and use a low cost 3D display that collaborative interact for multi-user immersive game requirements. In the multi-user VR game, 3D display is an important component that supports immersion to gamer. So our display system is supported by following two methods. Projection-based screen system makes it possible to display on large-sized surface. Stereo sea-through HMD is to produce private area as well as public area: a viewer-oriented and private information display. To accomplish this system, we concrete a multi-projector system for creating a seamless wide-area view, head mounted device to play game, and gesture recognition system for collaborative interactions. Our preliminary system is well suited for jungle hunting as game contents with surround displays running on a PC clusters. © Springer-Verlag Berlin Heidelberg 2004.

关键词： Three dimensional displays

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：