检索结果-内蒙古大学图书馆

International Conference on Pattern Recognition

作者： Guoying Zhao Li Cui Hua Li M. Pietikainen Machine Vision Group Infotech Oulu and Department of Electrical and Information Engineering University of Oulu Finland Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy and Sciences Beijing China School of Mathematics Science Beijing Normal University Beijing China

Video-based gait recognition is a challenging problem in computer vision. In this paper, fractal scale wavelet analysis is applied to describe and automatically recognize gait. Fractal scale based on wavelet analysis represents the self-similarity of signals, and improves the flexibility of wavelet moments. Optimal wavelets based on generalized multi-resolution analysis are used to improve the recognition rate. Descriptors of fractal scale are translation, scale and rotation invariant. Moreover, a combination of fractal scale and wavelet moments improves the recognition rate. Experiments show that the proposed descriptor is efficient for gait recognition

关键词： Fractals Wavelet analysis Image recognition Signal resolution Image sequences Continuous wavelet transforms Discrete wavelet transforms Wavelet coefficients Machine vision Laboratories

来源：评论

学校读者我要写书评

暂无评论

Method of color transfer between images

引用

Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics 2006年第10期18卷 1513-1518页

作者： Wang, Shaorong Li, Hua Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100080 China National Research Center for Intelligent Computing Systems Institute of Computing Technology Chinese Academy of Sciences Beijing 100080 China Graduate University of Chinese Academy of Sciences Beijing 100049 China

The current color transfer methods always use statistics as transfer function and can not deal with images with lower similarity. In this paper, a section by section color transfer method is presented, in which all the source images and reference images are segmented into a series of homogeneous regions, in which variations between classes are big and variations within classes are small, and then the color between the corresponding regions are transferred. The experiments show that the algorithm is efficient, the results are satisfactory, and it can be applied to complicated images with lower similarity.

关键词： Color transfer Linear transform OTSU's method

来源：评论

学校读者我要写书评

暂无评论

Fusing color and gradient features approach to real-time background subtraction using graph cuts

引用

Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics 2006年第11期18卷 1741-1747页

作者： Deng, Yu Li, Zhenbo Li, Hua Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Acad. of Sciences Beijing 100080 China National Research Center for Intelligent Computing Systems Beijing 100080 China Graduate University Chinese Acad. of Sciences Beijing 100049 China

Based on the fusion of color and gradient features, this paper implements a novel approach to real-time background subtraction. Firstly, an energy function is defined based on the fusion of color and gradient features. Secondly, the graph cuts based algorithm is employed to minimize energy function and segment the foreground. Finally, average optical flow is used to make inference about the validity of foreground regions, background models are then updated. The experimental results of different real scenes show that the proposed approach can produce real-time detection and promising results.

关键词： Background subtraction Color and gradient feature Energy function Graph cuts Real-time detection

来源：评论

学校读者我要写书评

暂无评论

Novel linear edge detector derived from Fresnel diffraction mode

引用

Jisuanji Xuebao/Chinese Journal of Computers 2006年第12期29卷 2138-2142页

作者： Diao, Lu-Hong Yu, Bin Li, Hua National Center of Computing Technology Institute of Computing Technology Chinese Academy of Sciences Beijing 100080 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100080 China Graduate University Chinese Academy of Sciences Beijing 100049 China Institute of Optoelectronics Shenzhen University Shenzhen 518600 China

This paper proposes an edge detection scheme based on Fresnel diffraction mode. Since Fresnel diffraction is mathematically complex, it is simplified into a linear convolution filter. Experiments on images are compared with the Laplacian of Gaussian, Sobel and Canny edge detection algorithms. The experimental results indicate that the new detector's result is comparable to Canny detector and agree more with human's recognition. And it also can get an even better edge map on some regions which contain abundant local details or some tiny changes.

关键词： Edge detection

来源：评论

学校读者我要写书评

暂无评论

Understanding the Dynamical Characteristics of Neural Networks by Universal Fuzzy Logical Framework

Understanding the Dynamical Characteristics of Neural Networ...

引用

2005 International Conference on Neural Networks and Brain(ICNN&B’05)

作者： Hong Hu Zhongzhi Shi Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Science

ISBN: (纸本)0780394224

The analytical study of a large scale nonlinear neural network is an uneasy *** try to analyze the function of neural systems by probing into the fuzzy logical framework of the neural ceUs'dynamical *** papers investigate the relation between fuzzy logic and neural *** most investigations focus on finding new function of neural system by combining fuzzy logical and neural system. In this paper,a novel approach is used to understand the nonlinear dynamic characteristics of neural system by analyzing the fuzzy logic framework of neural *** is the only way to understand the behavior of a large scale nonlinear neural *** abstracting the fuzzy logical framework of a neural cell,our analysis enables the delicate design of network *** an example,a difficulty task to build a recurrent network model of primary visual cortex by common dynamical analysis can be easily completed by this kind approach.

关键词： Understanding the Dynamical Characteristics of Neural Networks by Universal Fuzzy Logical Framework Fuzzy

来源：评论

学校读者我要写书评

暂无评论

A kind of dimension reduction method for classification based on hyper surface

A kind of dimension reduction method for classification base...

引用

International Conference on Machine Learning and Cybernetics, ICMLC 2005

作者： He, Qing Zhao, Xiu-Rong Shi, Zhong-Zhi Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100080 China

ISBN: (纸本)078039092X

Based on Jordan curve theorem, a universal classification method based on hyper surface is recently put forward. The experiments show that the new method can efficiently and accurately classify large data size up to 107 in three-dimensional space. However, the number of training samples needed to design a classifier grows with the dimension of the features. So a way to reduce the dimension of the features without losing any essential information is needed. We put forward a kind of simple and efficient dimension reduction method without losing any essential information to improve the performance of classification based on hyper surface for high dimension data. ©2005 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

An ontology-driven multi-agent architecture for knowledge acquisition from text in NKI

An ontology-driven multi-agent architecture for knowledge ac...

引用

International Conference on Computational Intelligence for Modelling, Control and Automation, CIMCA 2005 and International Conference on intelligent Agents, Web Technologies and Internet Commerce, IAWTIC 2005

作者： Guogang, Tian Cungen, Cao Key Laboratory of Intelligent Information Processing Graduate University of the Chinese Academy of Sciences Chinese Academy of Sciences Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences

ISBN: (纸本)0769525040

NKI contains a multi-domain oriented and large scale knowledge base. Text corpus is an important knowledge source of it. This paper presents an ontology-driven and integrated multi-agent architecture (MAKAT) for achieving sharing and reuse among different kinds of knowledge acquisition in NKI. MAKAT is a three-tier model which involves KATO, KARO, KATA, among which the description and execution layer are discussed in detail. Finally, we utilize the MAKAT model to acquire two different relations: part-of relation and hyponymy. It is observed that the MAKAT model can provide sharing and reuse in these two different cases. © 2005 IEEE.

关键词： Computer architecture

来源：评论

学校读者我要写书评

暂无评论

A fast nondominated sorting algorithm

A fast nondominated sorting algorithm

引用

2005 International Conference on Neural Networks and Brain Proceedings, ICNNB'05

作者： Chuan, Shi Ming, Chen Zhongzhi, Shi Key Laboratory of Intelligent Information Process Institute of Computing Technology Chinese Academy of Science Graduate University Chinese Academy of Sciences

ISBN: (纸本)0780394224

The process of nondominated sorting is one of main time-consuming parts of multiobjective evolutionary algorithm (MOEA). Designing a fast nondominated sorting algorithm is crucial to improve the performance of MOEA. The paper uses a Better function to compare solutions, and theoretical analysis shows that the Better function has the properties of general symmetry and transitivity. Based on these properties, the Better nondominated sorting algorithm (BNS) is designed to reduce the comparisons among solutions distinctly. Through the simulation experiments and comparing study, the new algorithm is found to speed up the process of nondominated sorting in deed. © 2005 IEEE.

关键词： Sorting

来源：评论

学校读者我要写书评

暂无评论

Simulation study of phase retrieval for hard X-ray in-line phase contrast imaging

引用

Science China(Physics,Mechanics & Astronomy) 2005年第4期48卷 450-458页

作者： YU Bin1,2, PENG Xiang1,2, TIAN Jindong1, NIU Hanben1, DIAO Luhong3 & LI Hua3 1. Key laboratory of Optoelectronic Devices and Systems of Ministry of Education, Institute of Optoelec- tronics, Shenzhen University, Shenzhen 518060, China 2. State Key laboratory of Precision Measuring technology and Instruments, Tianjin University, Tianjin 300072,China 3. Key laboratory of intelligent information Processing, Institute of computing technology, Chinese Academy of Sciences, Beijing 100080,China 1. Key Laboratory of Optoelectronic Devices and Systems of Ministry of Education Institute of Optoelectronics Shenzhen University 518060 Shenzhen China 2. State Key Laboratory of Precision Measuring Technology and Instruments Tianjin University 300072 Tianjin China 3. Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences 100080 Beijing China

Two algorithms for the phase retrieval of hard X-ray in-line phase contrast imaging are presented. One is referred to as Iterative Angular Spectrum Algorithm (IASA) and the other is a hybrid algorithm that combines IASA with TIE (transport of intensity equation). The calculations of the algorithms are based on free space propagation of the angular spectrum. The new approaches are demonstrated with numerical simulations. Comparisons with other phase retrieval algorithms are also performed. It is shown that the phase retrieval method combining the IASA and TIE is a promising technique for the application of hard X-ray phase contrast imaging.

关键词： X-ray optics, phase contrast imaging, phase retrieval, angular spectrum, hard X-ray.

来源：评论

学校读者我要写书评

暂无评论

Fisher score based naïve Bayesian classifier

Fisher score based naïve Bayesian classifier

引用

2005 International Conference on Neural Networks and Brain Proceedings, ICNNB'05

作者： Zhongzhi, Shi Youping, Huang Sulan, Zhang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100080 China Graduate School Chinese Academy of Science Beijing 100039 China

ISBN: (纸本)0780394224

The naïve Bayesian classifier (NBC) is a simple yet very efficient classification technique in machine learning. But the unpractical condition independence assumption of NBC greatly degrades its performance. There are two primary ways to improve NBC's performance. One is to relax the condition independence assumption in NBC. This method improves NBC's accuracy by searching additional condition dependencies among attributes of the samples in a scope. It usually involves in very complex search algorithms. Another is to change the representation of the samples by creating new attributes from the original attributes, and construct NBC from these new attributes while keeping the condition independence assumption. Key problem of this method is to guarantee strong condition independencies among the new attributes. In the paper, a new means of making attribute set, which maps the original attributes to new attributes according to the information geometry and Fisher score, is presented, and then the FS-NBC on the new attributes is constructed. The condition dependence relation among the new attributes theoretically is discussed. We prove that these new attributes are condition independent of each other under certain conditions. The experimental results show that our method improves performance of NBC excellently. © 2005 IEEE.

关键词： Classification (of information)

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：