检索结果-内蒙古大学图书馆

IEEE Symposium on Nuclear Science (NSS/MIC)

作者： Qiong Xu Xuanqin Mou Shaojie Tang Yanbo Zhang Institute of Image Processing & Pattern Recognition Xi''an Jiaotong University Xi'an Shaanxi China Department of Radiology Emory University School of Medicine Atlanta GA USA

Reconstruction algorithm based on total variation (TV) minimization has become a hot topic in CT field. In order to make a better balance between suppressing noise and preserving edge, an improved variation is proposed in this paper. An anisotropic strategy is developed to effectively preserve the edges of imaging objects. Simultaneously, the unity weight in the original variation is substituted by an amplitude dependent weight to suppress the smaller variations, which arise from noise effect with a higher possibility. Numerical simulations validated that the CT reconstruction based on the improved variation has a better reconstruction performance as compared to its original counterpart.

关键词： TV image reconstruction Minimization image edge detection Computed tomography Noise

来源：评论

学校读者我要写书评

暂无评论

MULTIMODALITY GENDER ESTIMATION USING BAYESIAN HIERARCHICAL MODEL

MULTIMODALITY GENDER ESTIMATION USING BAYESIAN HIERARCHICAL ...

引用

IEEE International Conference on Acoustics, Speech, and Signal processing

作者： Xiong Li Xu Zhao Huanxi Liu Yun Fu Yuncai Liu Institute of Image Processing & Pattern Recognition Shanghai Jiao Tong University 200240 Shanghai China Department of CSE University at Buffalo (SUNY) NY 14260 USA

ISBN: (纸本)9781424442959

We propose to estimate human gender from corresponding fingerprint and face information with the Bayesian hierarchical model. Different from previous works on fingerprint based gender estimation with specially designed features, our method extends to use general local image features. Furthermore, a novel word representation called latent word is designed to work with the Bayesian hierarchical model. The feature representation is embedded to our multimodality model, within which the information from fingerprint and face is fused at the decision level for gender estimation. Experiments on our internal database show the promising performance.

关键词： Gender estimation fingerprint and face Bayesian hierarchical model latent word representation multimodality

来源：评论

学校读者我要写书评

暂无评论

Three-dimensional ultrasonic data smooth and endocardial extraction

Three-dimensional ultrasonic data smooth and endocardial ext...

引用

International Conference on BioMedical Engineering and Informatics (BMEI)

作者： Xionghu Luo Huilin Xiong Guozhen Chen Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University Shanghai China Department of Heart Center Shanghai Children's Medical Center Shanghai China

This paper presents a new approach for visualizing the surfaces from 3D ultrasound data. 3D ultrasound data usually contain substantial quantity of speckle noise, which makes the extraction of smooth and continuous surfaces extremely difficult. In this paper, combining the partial differential equation model of anisotropic diffusion filter with the Lee filter, we present a new algorithm for handling 3D ultrasound data, aiming to suppress the speckle noise, and meanwhile, smooth the ultrasound image. Additionally, the marching cubes algorithm is applied to extract a smooth endocardial surface. Comparing experiments are presented to illustrate the effectiveness of our approach.

关键词： Noise Mathematical model Anisotropic magnetoresistance Three dimensional displays Speckle Rendering (computer graphics) Filtering algorithms

来源：评论

学校读者我要写书评

暂无评论

Research and Implementation of A multi-Fault Diagnosis Method Based on Case-based Reasoning

Research and Implementation of A multi-Fault Diagnosis Metho...

引用

The 8th World Congress on Intelligent Control and Automation(第八届智能控制与自动化世界大会 WCICA 2010)

作者： Gan Zhihua Lu Yang Chai Xiuli Institute of Complex Intelligent Network System Henan University Kaifeng Henan Province China Institute of Image Processing and Pattern Recognition Henan University Kaifeng Henan Province Chin

In this paper, a multiple fault diagnosis method based on case-based reasoning (CBR) is presented. And the characteristics of multiple fault modes are studied, then the case knowledge library is established for multiple faults, finally a twostep case retrieval strategy is proposed. The candidate case generation method based on the membership weights is employed to initially retrieve, which can reduce the number of candidate cases efficiently. Then, through calculating the case similarity using the grey relational analysis, the most probable fault case is obtained. It can avoids the problem of time-consuming computation resulting from the combination explosion of multiple faults. Finally, an example is applied to illustrate the proposed scheme, the results mean that the above method is effective, and it can be adopted in the actual industrial production.

关键词： Fault diagnosis Libraries Cognition Correlation Rotors Artificial intelligence Testing

来源：评论

学校读者我要写书评

暂无评论

An interactive method for computing tooth-root orientation from 3D CT image

An interactive method for computing tooth-root orientation f...

引用

International Conference on Medical image Analysis and Clinical Applications (MIACA)

作者： Jie Xie Yang Liu Jilin Yin Tiantian Qiu Yuanliang Huang Lisheng Wang Institute of Image Processing and Pattern Recognition Department of Automation Shanghai Jiaotong University Shanghai China Department of Dentistry Shanghai East Hospital University of Tongji Shanghai China

ISBN: (纸本)9781424480111

In tooth implantation surgery, dentist or surgeon needs to derive quantitative information about the place each implant should be go, the length and width of each implant should be, as well as the angle each implant should be inserted, based on the 3D CT image of jaw of a patient. In existing techniques, the information is measured from such slices that are generated from virtually cutting teeth-ridge along the direction perpendicular to teeth-ridge. However, according to the clinical experience and anatomical knowledge, usually the largest length of each implant should be measured on such slice that is generated by cutting teeth-ridge along the tooth root direction. Besides, for each defect tooth, the most suitable angle or orientation to insert an implant is the tooth root orientation. Thus, in surgical planning of dental implant, it is much important to compute or estimate tooth root orientation from 3D CT image of jaw. To our knowledge, this problem is seldom studied in existing literature. In this paper, we try to discuss this problem.

关键词： Computed tomography Teeth Implants Dentistry Surgery Length measurement Bones Surges image restoration Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

A watermark technology of print-scan resilient based on DFT transform

引用

Beijing Gongye Daxue Xuebao/Journal of Beijing University of Technology 2010年第SUPPL. 1期36卷 113-117页

作者： Zou, Jian-Cheng Si, Jian-Min Institute of Image Processing and Pattern Recognition North China University of Technology Beijing 100144 China

A method of printing and certificate forgery based on digital watermarking is presented. This method embeds watermark in the DFT domain using the principles that middle and low frequency coefficients have little changes in print-scan process, and using HOUGH transform for image correction to resist rotation attacks when extracting watermarks. The experimental results show that this method has strong robustness to first print-scan images, which can be detected right watermarks, while for the second print-scan images robustness drops about 20%. Therefore the algorithm can be used to identify the authenticity of printing and certificates by the correction of the watermarks and can be used to all types of copyright protection and certificates security.

关键词： Copyrights

来源：评论

学校读者我要写书评

暂无评论

A new replica selection strategy based on combination algorithm

A new replica selection strategy based on combination algori...

引用

International Conference on Internet Technology and Applications, ITAP 2010

作者： Guo, Zheng-Wei Li, Ning Li, Hui Shi, Nan College of Computer and Information Engineering Institute of Image Processing and Pattern Recognition Henan University Kaifeng Henan China College of Computer and Information Engineering Henan University Kaifeng Henan China

ISBN: (纸本)9781424451432

In the data grid environment, when users access to files, how to select the best site to obtain files from multiple replicas and reach the highest QOS(quality of service) in the cost of same price is a problem that need to be studied urgently, that is replica selection. In this paper, it proposes a new combination algorithm based on genetic algorithm and ant algorithm, which not only solves the inefficient disadvantage of genetic algorithm, but also solves the problem of solving problems slowly in the early period in ant algorithm. This strategy is analyzed and simulated by data grid simulator OptorSim, and the results show that this new algorithm can be effective in reducing data access latency, improve data access speed, speed up job completion time, and achieve load balancing. ©2010 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Fast Marine Route Planning for UAV Using Improved Sparse A* Algorithm

Fast Marine Route Planning for UAV Using Improved Sparse A* ...

引用

International Conference on Genetic and Evolutionary Computing (ICGEC)

作者： Xin Yang Ming-yue Ding Cheng-ping Zhou Institute for Pattern Recognition and Artificial Intelligence (IPRAI) Image Processing and Intelligence Control Key Laboratory of Education Ministry of China Huazhong University of Science and Technology Wuhan Hubei China School of Life Science and Technology Image Processing and Intelligence Control Key Laboratory of Education Ministry of China Huazhong University of Science and Technology Wuhan Hubei China Institute for Pattern Recognition and Artificial Intelligence (IPRAI) State Key Laboratory for Multispectral Information Processing Technologies Huazhong University of Science and Technology Wuhan Hubei China

This paper focuses on route planning, especially for unmanned aircrafts in marine environment. Firstly, new heuristic information is adopted such as threat-zone, turn maneuver and forbid-zone based on voyage heuristic information. Then, the cost function is normalized to obtain more flexible and reasonable routes. Finally, an improved sparse A* search algorithm is employed to enhance the planning efficiency and reduce the planning time. Experiment results showed that the improved algorithm for aircraft in maritime environment could find a combinational optimum route quickly, which detoured threat-zones, with fewer turn maneuver, totally avoiding forbid-zones, and shorter voyage.

关键词： Unmanned aerial vehicles Planning Synthetic aperture sonar Cost function Algorithm design and analysis Heuristic algorithms Leg

来源：评论

学校读者我要写书评

暂无评论

General moving objects recognition method based on graph embedding dimension reduction algorithm

引用

Journal of Zhejiang University-Science A(Applied Physics & Engineering) 2009年第7期10卷 976-984页

作者： Yi ZHANG Jie YANG Kun LIU Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai 200240 China

Effective and robust recognition and tracking of objects are the key problems in visual surveillance systems. Most existing object recognition methods were designed with particular objects in mind. This study presents a general moving objects recognition method using global features of targets. Targets are extracted with an adaptive Gaussian mixture model and their silhouette images are captured and unified. A new objects silhouette database is built to provide abundant samples to train the subspace feature. This database is more convincing than the previous ones. A more effective dimension reduction method based on graph embedding is used to obtain the projection eigenvector. In our experiments, we show the effective performance of our method in addressing the moving objects recognition problem and its superiority compared with the previous methods.

关键词： Moving objects recognition Adaptive Gaussian mixture model Principal component analysis Linear discriminant analysis Marginal Fisher analysis

来源：评论

学校读者我要写书评

暂无评论

Bayesian moving object detection in dynamic scenes using an adaptive foreground model

引用

Journal of Zhejiang University-Science A(Applied Physics & Engineering) 2009年第12期10卷 1750-1758页

作者： Sheng-yang YU Fang-lin WANG Yun-feng XUE Jie YANG Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai 200240 China

Accurate detection of moving objects is an important step in stable tracking or recognition. By using a nonparametric density estimation method over a joint domain-range representation of image pixels, the correlation between neighboring pixels can be used to achieve high levels of detection accuracy in the presence of dynamic background. However, color similarity between foreground and background will cause many foreground pixels to be misclassified. In this paper, an adaptive foreground model is exploited to detect moving objects in dynamic scenes. The foreground model provides an effective description of foreground by adaptively combining the temporal persistence and spatial coherence of moving objects. Building on the advantages of MAP-MRF (the maximum a posteriori in the Markov random field) decision framework, the proposed method performs well in addressing the challenging problem of missed detection caused by similarity in color between foreground and background pixels. Experimental results on real dynamic scenes show that the proposed method is robust and efficient.

关键词： Moving object detection Foreground model Kernel density estimation （KDE） MAP-MRF estimation

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：