检索结果-内蒙古大学图书馆

2010 20th International Conference on pattern recognition, ICPR 2010

作者： Zhang, De Wang, Yunhong Bhanu, Bir Intelligent Recognition and Image Processing Laboratory School of Computer Science and Engineering Beihang University Beijing 100191 China Center for Research in Intelligent Systems University of California Riverside CA 92521 United States

ISBN: (纸本)9780769541099

In this paper we propose a new framework for age classification based on human gait using Hidden Markov Model (HMM). A gait database including young people and elderly people is built. To extract appropriate gait features, we consider a contour related method in terms of shape variations during human walking. Then the image feature is transformed to a lower-dimensional space by using the Frame to Exemplar (FED) distance. A HMM is trained on the FED vector sequences. Thus, the framework provides flexibility in the selection of gait feature representation. In addition, the framework is robust for classification due to the statistical nature of HMM. The experimental results show that video-based automatic age classification from human gait is feasible and reliable. © 2010 IEEE.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

A novel method for boundary condition computation in soft tissue deformation

A novel method for boundary condition computation in soft ti...

引用

2009 WRI World Congress on Computer Science and Information Engineering, CSIE 2009

作者： Shengzheng, Wang Jie, Yang Kai, Xie Merchant Marine College Shanghai Maritime University 200135 Shanghai China Inst. of Image Processing and Pattern Recognition Shanghai Jiaotong University 200240 Shanghai China Methodist Hospital Research Institute Cornell University Houston TX 77030 United States

ISBN: (纸本)9780769535074

Simulating the soft tissue deformation based on bone-related planning is one of the most difficult issues in generating realistic motion of soft tissues. The difficulty of this problem arises from unclear boundary conditions. In facial soft tissue deformation, the boundary conditions of the finite element modeling are related to the bone movements. In order to better map the bone movements to the soft tissue model, a fast and robust computational strategy for boundary conditions is presented in this paper. First, a collision detection algorithm is employed to query contact position after repositioning of bones. Then, an improved 3D discrete distance field algorithm is proposed to perform imposed displacement computation of contact vertices. Finally, boundary conditions are calculated in terms of the imposed displacements. This approach can automatically handle boundary conditions of the complex geometrical modeling without prior assumption or knowledge about the position of contacts. The effectiveness of our method is demonstrated on complex soft tissue deformation. © 2008 IEEE.

关键词： Boundary conditions

来源：评论

学校读者我要写书评

暂无评论

Placement and selection algorithm of reference nodes in WSN localization

Placement and selection algorithm of reference nodes in WSN ...

引用

6th China Conference of Wireless Sensor Networks, CWSN 2012

作者： Min, Lin Li, Hui Guo, Zhengwei Network Information Center Office Henan University Kaifeng Henan 475001 China Henan University Minsheng College Kaifeng Henan 475004 China School of Computer and Information Engineering Institute of Image Processing and Pattern Recognition Henan University Kaifeng Henan 475001 China

ISBN: (纸本)9783642362514

Currently, few studies of wireless sensor network node localization algorithm were focused on the reference nodes, but how to choose and place reference nodes has a great influence on the positioning accuracy. In order to quantitatively study this issue, we proved a theorem, which describes the relationship between the placement of reference nodes and whether the node can be located, then the reference nodes placement method was designed. Finally, a reference nodes selection algorithm was proposed based on the condition number of linear equations, so as to improve the accuracy of range-based localization algorithm. © 2013 Springer-Verlag.

关键词： Number theory

来源：评论

学校读者我要写书评

暂无评论

Printing Technique Classification for Document Counterfeit Detection

Printing Technique Classification for Document Counterfeit D...

引用

International Conference on Computational Intelligence and Security

作者： Christoph H. Lampert Lin Mei Thomas M. Breuel Image Understanding and Pattern Recognition Laboratory German Research Center for Artificial Intelligence Kaiserslautern Germany

ISBN: (纸本)1424406048

The detection of counterfeit in printed documents is currently based mainly on built-in security features or on human expertise. We propose a classification system that supports non-expert users to distinguish original documents from PC-made forgeries by analyzing the printing technique used. Each letter in a document is classified using a support vector machine that has been trained to distinguish laser from inkjet printouts. A color-coded visualization helps the user to interpret the per-letter classification results

关键词： Printing Counterfeiting Forgery Security Humans Laser transitions Spatial databases Data mining Ink Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Improved DV-hop localization algorithm based on RSSI value and hop correction

Improved DV-hop localization algorithm based on RSSI value a...

引用

6th China Conference of Wireless Sensor Networks, CWSN 2012

作者： Guo, Zhengwei Min, Lin Li, Hui Wu, Wenjian School of Computer and Information Engineering Institute of Image Processing and Pattern Recognition Henan University Kaifeng Henan 475001 China Network Information Center Office Henan University Kaifeng Henan 475001 China Henan University Minsheng College Kaifeng Henan 475004 China

ISBN: (纸本)9783642362514

On the basis of the analysis of the relation between network's topologyand localization precisionan improved DV-Hop algorithm based on hop correction is put forward. Firstly, RSSI value is used to correct the distance between unknown node and reference nodes in the range of single hop;secondly, a certain amount of correction value is added to the original hop between unknown node and reference nodes to further reduce the distance error between them. Simulation result shows that improved algorithm improves the localization precision. © 2013 Springer-Verlag.

关键词： correction DV-Hop WSN

来源：评论

学校读者我要写书评

暂无评论

Dynamic monitoring technique for remote-sensing image of invasive alien plant species

Dynamic monitoring technique for remote-sensing image of inv...

引用

2013 International Conference on Geo-Informatics in Resource Management and Sustainable Ecosystem, GRMSE 2013

作者： Hesen, Rabigul Jia, Zhenhong Yang, Jie Hu, Raphael College of Information Science and Engineering Xinjiang University Urumqi 830046 China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai 200240 China Knowledge Engineering and Discovery Research Institute Auckland University of Technology Auckland 1020 New Zealand

ISBN: (纸本)9783642419072

Invasive Alien Plant Species (IAPS) could seriously affect the local ecosystem balance, and pose a threat to the ecological security. In order to effectively monitor and control invasive alien plants, it needs to monitor the spatial distribution and dynamic changes of IAPS. It will cite the method of nonsubsampled contourlet transform (NSCT) combination with fuzzy C-means clustering algorithm in this paper, which is used in remote sensing image change detection, for monitoring the dynamic changes of biological invasive species in this paper, to get a better detection result. © Springer-Verlag Berlin Heidelberg 2013.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Single landmark based self-localization of mobile robots

Single landmark based self-localization of mobile robots

引用

3rd Canadian Conference on Computer and Robot Vision, CRV 2006

作者： Bais, Abdul Sablatnig, Robert Gu, Jason Institute of Computer Technology Vienna University of Technology Vienna Austria Pattern Recognition and Image Processing Group Institute of Computer Aided Automation Vienna University of Technology Vienna Austria Robotics Research Group Department of Electrical and Computer Engineering Dalhousie University Halifax Canada

ISBN: (纸本)0769525423

In this paper we discuss landmark based absolute localization of tiny autonomous mobile robots in a known environment. Landmark features are naturally occurring as it is not allowed to modify the environment with special navigational aids. These features are sparse in our application domain and are frequently occluded by other robots. This makes simultaneous acquisition of two or more landmarks difficult. Therefore, we propose a system that requires a single landmark feature. The algorithm is based on range measurement of a single landmark from two arbitrary points whose displacement can be measured using dead-reckoning sensors. Range estimation is done with a stereo vision system. Simulation results show that the robot can localize itself if it can estimates range of the same landmark from two different position and if the displacement between the two position is known. © 2006 IEEE.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

A Robust, Real-Time Voice Activity Detection Algorithm for Embedded Mobile Devices

引用

Journal of Sol-Gel Science and Technology 1997年第2期8卷 133-146页

作者： Bian Wu Xiaolin Ren Chongqing Liu Yaxin Zhang Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University Shanghai People's Republic of China Motorola Labs China Research Center W. Shanghai People's Republic of China

When an Automatic Speech recognition (ASR) system is applied in noisy environments, Voice Activity Detection (VAD) is crucial to the performance of the overall system. The employment of the VAD for ASR on embedded mobile systems will minimize physical distractions and make the system convenient to use. Conventional VAD algorithm is of high complexity, which makes it unsuitable for embedded mobile devices; or of low robustness, which holds back its application in mobile noisy environments. In this paper, we propose a robust VAD algorithm specifically designed for ASR on embedded mobile devices. The architecture of the proposed algorithm is based on a two-level decision making strategy, where there is an interaction between a lower features-based level and subsequent decision logic based on a finite-state machine. Many discriminating features are employed in the lower level to improve the robustness of the VAD. The two-level decision strategy allows different features to be used in different states and reduces the cost of the algorithm, which makes the proposed algorithm suitable for embedded mobile devices. The evaluation experiments show the proposed VAD algorithm is robust and contribute to the overall performance gain of the ASR system in various acoustic environments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On ancient coin classification

On ancient coin classification

引用

8th International Symposium on Virtual Reality, Archaeology, and Intelligent Cultural Heritage, VAST 2007

作者： Zaharieva, M. Huber-Mörk, R. Nölle, M. Kampel, M. TU Vienna Institute for Computer Aided Automation Pattern Recognition and Image Processing Group Favoritenstr. 9/183-2 A-1040 Vienna Austria ARC Seibersdorf Research GmbH Smart Systems Division High Performance Image Processing A-2444 Seibersdorf Austria ARC Seibersdorf Research GmbH Smart Systems Division Quantum Technologies A-2444 Seibersdorf Austria

ISBN: (纸本)9783905674019

Illegal trade and theft of coins appears to be a major part of the illegal antiques market. image based recognition of coins could substantially contribute to fight against it. Central component in the permanent identification and traceability of coins is the underlying classification and identification technology. The first step of a computer aided system is the segmentation of the coin in the image. Next, a feature extraction process measures the coin in order to describe the coin unambiguously. In this paper, we focus on the segmentation task, followed by a comparison of features relevant for coin classification. Results of the algorithms implemented are presented for an image database of ancient coins. © The Eurographics Association 2007.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Multi-sensor cost reference particle filtering algorithm based on consistency weight fusion

引用

Journal of Information and Computational Science 2012年第6期9卷 1675-1681页

作者： Hu, Zhentao Fu, Chunling Liu, Xianxing Li, Jie Institute of Image Processing and Pattern Recognition Henan University Kaifeng 475004 China Basic Experiment Teaching Center Henan University Kaifeng 475004 China

Aiming at the state estimation of nonlinear system in multi-sensor observation uncertainty, a novel cost reference particle filter algorithm based on consistency weight fusion is proposed in this paper. Firstly, the cost function and the risk function are introduced to realize reasonable utilization of the latest observation. Secondly, the relative distance, the support degree function and matrix which are subject to the membership function characteristic of fuzzy set theory, are constructed to extract and use the redundancy and complementary information among particles weights measured by multi-sensor observation. Finally, particles weights are calculated by the information fusion method. The theoretical analysis and experimental results show the algorithm precision are effectively improved relative to standard particle filter and cost reference particle filter. © 2012 by Binary Information Press.

关键词： Cost functions

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：