检索结果-内蒙古大学图书馆

IEEE Asia-Pacific Conference on Services Computing (APSCC)

作者： Ku-Jin Kim Sun-Mi Park Yoo-Joo Choi Department of Computer Engineering Kyungpook National University South Korea Graduate School of EECS Kyungpook National University South Korea Department of Computer Science & Application Seoul University of Venture and Information South Korea

In this paper, we suggest a method to identify the clothing as one approach for identifying a person in the grayscale image captured by a CCTV camera. We use the edge information of the clothing area for extracting the textural feature of the clothing. The edge filter is applied to the clothing area, and the histograms on the edge values are constructed. The feature vector is composed from the histograms. We used Euclidean distance as a similarity measure between feature vectors, and successfully identified the clothing with 77.8% of success rate.

关键词： Clothing Cameras Histograms Gray-scale Pixel Image analysis Elevators Color Surveillance Filters

来源：评论

学校读者我要写书评

暂无评论

Deciding the Number of Color Histogram Bins for Vehicle Color Recognition

Deciding the Number of Color Histogram Bins for Vehicle Colo...

引用

IEEE Asia-Pacific Conference on Services Computing (APSCC)

作者： Ku-Jin Kim Sun-Mi Park Yoo-Joo Choi Department of Computer Engineering Kyungpook National University South Korea Graduate School of EECS Kyungpook National University South Korea Corresponding Author Department of Computer Science & Application Seoul University of Venture and Information South Korea

Given vehicle images, we suggest a way to recognize the color of the vehicle contained in the image. The color feature of a vehicle is represented by a color histogram, and we decide the appropriate number of color histogram bins, which mainly affects the successful recognition rate. After generating the histograms, template matching is used to decide the vehicle color. In HSI (hue saturation intensity) color space, experimental results show that the partition of H, S, and I into 8, 4, 4, respectively, achieves the highest success rate up to 88.34%.

关键词： Histograms Vehicles Image recognition Colored noise Cameras Feature extraction Image segmentation Image classification Pixel Image retrieval

来源：评论

学校读者我要写书评

暂无评论

AN INTELLIGENT HIGH AVAILABLE RFID MIDDLEWARE

AN INTELLIGENT HIGH AVAILABLE RFID MIDDLEWARE

引用

2008 International Conference on Machine Learning and Cybernetics(2008机器学习与控制论国际会议)

作者： HSIN MEI CHIEN-CHANG HSU CHUN-SHO LEE DA-GANG LEE Department of Computer Science and Information Engineering Fu-Jen Catholic University 510 Chung Che Innovative DigiTech-Enabled Application & Services Institute Institute for Information Industry ST.

RFID is applied widely In many domains. RFID middleware plays an Important role in extracting tag information from the reader and forward it to the backend application systems. How to avoid system failure and reduce performance degradation in a complex and high volume tags environment Is a critical issue for RFID applications. Many researchers use hardware failover to achieve high availability. Some other researchers apply software agents to perform load balance. However, none of them provide a robust solution to the above problems between RFID reader and middleware. This work proposes an intelligent highly available system to RFID middleware. The system uses RFID repository to provide dynamic allocation In different types of readers and maintain task information of middleware. The system also uses the technologies of agent negotiation, genetic algorithm, and fuzzy computation to support highly available and load balance for RFID middleware. The system is applied to entrance guard and attendance checking application. The experimental result shows that the system can provide a highly available RFID middleware with high degree of tag Identification accuracy.

关键词： RFID middleware High availability Agent negotiation Genetic algorithm Fuzzy computation

来源：评论

学校读者我要写书评

暂无评论

Effects of average luminance level of displayed images, viewers age, and screen illuminance on preferred luminance of LCDs

引用

Kyokai Joho Imeji Zasshi/Journal of the Institute of Image Information and Television Engineers 2008年第6期62卷 931-936页

作者： Kubota, Satoru Hanehara, Ryo Nakamura, Yoshitomo Nomoto, Kohei Yamakawa, Masaki Faculty of Science and Technology Seikei University 3-3-1 Kichijoji-kitamachi Musashino-shi Tokyo 180-8633 Japan Advanced Technology R and D Center Mitsubishi Electric Corporation 1 Zusho Baba Nagaokakyo-shi Kyoto 617-8550 Japan Industrial Design Center Mitsubishi Electric Corporation 5-1-1 Ofuna Kamakura-shi Kanagawa 247-8501 Japan Computer and Consumer Application Engineering Dept. Renesas Technology Corporation 4-1 Mizuhara Itami-shi Hyogo 664-0005 Japan

We investigated what influences the average luminance level (ALL) of displayed images, screen illuminance, and viewers ages had on the preferred luminance of LCDs. Twenty young subjects (mean age: 21.8) and 24 seniors (mean age: 68.9) adjusted the luminance of a 17-inch 1000: 1 LCD monitor to their preferred levels under different experimental conditions. The results indicate that the preferred luminance of LCDs corresponded to the following formula: Lp=k x ALLα. This is where Lp is the peak white luminance of the LCDs, k is a constant, and ALL is the average luminance level of the displayed images. Here, α is a constant from -0.19 to -0.20 for the seniors and from -0.14 to -0.17 for the young subjects. The influences of age-related changes in vision and ambient lighting on the luminance requirements for LCDs are also discussed. These results can be applied to the design of luminance-control systems for LCDs.

关键词： Liquid crystal displays

来源：评论

学校读者我要写书评

暂无评论

Evolutionary algorithm for a genetic robot’s personality

Evolutionary algorithm for a genetic robot’s personality

引用

IEEE International Workshop on Robot and Human Communication (ROMAN)

作者： Kang-Hee Lee Hyun-Sik Shim Woo-Sup Han Kwang-Choon Kim Jong-Hwan Kim Fundamental Technology Team Mechatronics & Manufacturing Technology Center Corporate Technology Operations Samsung Electronics Company Limited South Korea Application Technology Laboratory Telecommunication Research and Development Center Telecommunication Network Business Samsung Electronics Company Limited South Korea Faculty of Department of Electrical Engineering and Computer Science Korea Advanced Institute of Science and Technology South Korea

This paper proposes a new concept of the genetic robot which has its own robot genome, in which each chromosome consists of many genes that contribute to defining the robotpsilas personality. The large number of genes also allows for a highly complex system, however it becomes increasingly difficult and time-consuming to ensure reliability, variability and consistency for the robotpsilas personality while manually initializing values for the individual genes. To overcome this difficulty, this paper proposes an evolutionary algorithm for a genetic robotpsilas personality (EAGRP). EAGRP evolves a gene pool that customizes the robotpsilas genome so that it closely matches a simplified set of features desired by the user. It does this using several new techniques. It acts on a 2 dimensional individual upon which a new masking method, the Eliza-Meme scheme, is used to derive a plausible individual given the restricted preference settings desired by the user. The proposed crossover method allows reproduction for the 2-dimensional genome. Finally, the evaluation procedure for individuals is carried out in a virtual environment using tailored perception scenarios.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

Multiplicative versus Additive Bias Field Models for Unified Partial-Volume Segmentation and Inhomogeneity Correction in Brain MR Images

Multiplicative versus Additive Bias Field Models for Unified...

引用

IEEE Symposium on Nuclear science (NSS/MIC)

作者： Su Wang Lihong Li Hongbing Lu Zhengrong Liang Department of Radiology State University of New York Stony Brook NY USA Department of Engineering Science and Physics College of Staten Island City University of New York Staten Island NY USA Department of Computer application Fourth Military Medical University Shaanxi China Department of Radiology and Physics State University of New York Stony Brook NY USA

It has been widely accepted that for brain MR images, both the image density inhomogeneity (slowly-varying intensity changes across the field of view) and partial-volume effect (PVE) (more than one tissue type present in a single voxel) considerably reduce the accuracy and reliability of quantitative analysis for various clinical purposes. This paper presents a unified expectation-maximization (EM) approach, where PVE and intensity inhomogeneity are combined together into a built-in-one statistical model in additive and multiplicative formats. It assumes that each tissue type follows a conditionally-independent normal distribution, based on which the summation of all tissue contributions multiplied or added by the bias term leads to mean density value at each voxel. Meanwhile, the summation of all the tissue mixtures, which is unobservable but could be estimated via EM framework (many-to-one mapping), multiplied or added by the bias term would lead to the observed image density at each voxel. In doing so, both the inhomogeneity and tissue mixtures are updated voxel-by-voxel until the convergence of a stable solution. Comprehensive tests on simulated brain MR images strongly demonstrated the feasibilities of additive/multiplicative bias models and the effectiveness of the unified EM approach. In addition, additive and multiplicative bias field models reflect advantages in terms of stability and robustness.

关键词： Brain modeling Image segmentation Frequency estimation Random processes Gaussian distribution Image analysis Robust stability Magnetic resonance imaging Biomedical imaging Radiology

来源：评论

学校读者我要写书评

暂无评论

A perimeter intrusion detection system using dual-mode wireless sensor networks

A perimeter intrusion detection system using dual-mode wirel...

引用

2007 2nd International Conference on Communications and Networking in China, ChinaCom 2007

作者： Yuheng, Liu Chao, Li Yang, He Jing, Wu Zhang, Xiong Computer Application Institute School of Computer Science and Engineering Beihang University Beijing China

ISBN: (纸本)9781424410095

In recent years, wireless technologies have been employed by Perimeter Intrusion Detection Systems (PIDS) to reduce the cost of wiring, especially for some secure sites which are not wiring-friendly, However, the PIDS based on state-of-art wireless media such as WLAN, ZigBee, or UWB, suffers from remote distance and noisy wireless links which are easy to fail due to obstacles, signal shadowing and fading. In this paper we propose a PIDS using GPRS and CDMA dual-mode wireless sensor networks (DM-WSNs) to deliver an optimal data transmission service. Moreover. Auto Shutdown mechanism is proposed to address the energy conservation for battery powered sensor devices. We deploy the DW-WSNs in the PIDS of an airport in China, to safeguard the parking apron against illegal intrusion. Practice experience indicates that the DM-WSNs can achieve a better network quality and fully satisfy the first-response requirement of airport security.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Automatic summarization oriented Chinese word extraction and statistics system

引用

Journal of Computational Information Systems 2007年第3期3卷 941-948页

作者： Suo, Hongguang Zhao, Xinxin Duan, Yatao Zhang, Yan Liu, Yushu School of Computer Science and Technology Beijing Institute of Technology Beijing 100081 China School of Computer and Communication Engineering China University of Petroleum Dongying 257061 China Beijing Institute of Computer Application China North Industries Group Corporation Beijing 100089 China School of Electronic Engineering and Computer Science Peking University Beijing 100081 China

Automatic word segmentation is the foundation in Chinese text processing. It is a direction that to study different word segmentation method according to different purpose. Word segmentation and statistics are basic procedures in Chinese automatic summarization based on extraction. A pretreatment system is presented which combined word segmentation and statistics and achieved by 'Positional Remembering and Jump Matching with Statistics' in one scanning process. The experimental results show that it has a high speed and better effect in summarization.

关键词： Text processing

来源：评论

学校读者我要写书评

暂无评论

Self-adjusting predicted particle swarm optimization

引用

Journal of Information and Computational science 2007年第2期4卷 483-496页

作者： Cui, Zhihua Zeng, Jianchao Sun, Guoji State Key Laboratory for Manufacturing Systems Engineering Xi'an Jiaotong University Xi'an 710049 China Division of System Simulation and Computer Application Taiyuan University of Science and Technology Taiyuan 030024 China

Predicted particle swarm optimization is an enhanced version aiming to increase the utilization ratio of velocity information, and the performance heavily relies upon the parameters settings. According to control theory, the trajectories of position and velocity vectors of each particle can be both viewed as oscillatory links, and the relationship between inertia weight and accelerator coefficients is obtained. Thus, a self-adjusting parameter strategy is proposed. Simulation results show the new proposed strategy is powerful and useful.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Research on passage retrieval in Chinese question answering system

引用

Journal of Computational Information Systems 2007年第6期3卷 2367-2373页

作者： Yu, Zhengtao Han, Lu Wan, Zhou Xiang, Fenghong Mao, Cunli Guo, Jianyi School of Information Engineering and Automation Kunming University of Science and Technology Kunming 650051 China Computer Technology Application Key Laboratory of Yunnan Province Institute of Intelligent Information Processing Kunming 650051 China

In Chinese Question Answering System, in order to improve the accuracy of the passage retrieval which includes answers, this paper presents a method to compute the weight of passage based on the analysis of current passage retrieval methods. The word frequency of query words and query expansion words in passage, the length of passage;the distribution density and minimum match span of query words and query expansion words in passage are considered. The weight calculation of the answer passage is realized. And candidate passage set is retrieved on the basis of the weight Calculation. The experiment result on passage retrieval shows that this method has good effects that the MRR value equals 0.50.

关键词： Search engines

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：