检索结果-内蒙古大学图书馆

IEEE International Conference on image processing

作者： Yixiao Yun Keren Fu Irene Yu-Hua Gu Jie Yang Dept. of Signals and Systems Chalmers Univ. of Technology Inst. of Image Processing & Pattern Recognition Shanghai Jiao Tong Univ.

ISBN: (纸本)9781479957521

This paper addresses issues in video object tracking. We propose a novel method where tracking is regarded as a one-class classification problem of domain-shift objects. The proposed tracker is inspired by the fact that the positive samples can be bounded by a closed hypersphere generated by one-class support vector machines (SVM), leading to a solution for robust learning of target model online. The main novelties of the paper include: (a) represent the target model by a set of positive samples as a cluster of points on Riemannian manifolds;(b) perform online learning of target model as a dynamic cluster of points flowing on the manifold, in an alternate manner with tracking;(c) formulate geodesic-based kernel function for one-class SVM on Riemannian manifolds under the log-Euclidean metric. Experiments are conducted on several videos, results have provided support to the proposed method.

关键词： Visual object tracking Support vector machines One-class classification Online learning Riemannian manifold Covariance matrix

来源：评论

学校读者我要写书评

暂无评论

3-D centerline extraction for virtual cardiovascular endoscopy

3-D centerline extraction for virtual cardiovascular endosco...

引用

International Conference on Wavelet Active Media Technology and Information processing (ICWAMTIP)

作者： Jing Li Xin Yang Li Ping Yao Kun Sun Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China Xinhua Hospital Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9781479972098

This paper discusses centerline extraction algorithms for virtual cardiovascular endoscopy system. A fully automatic extraction method is proposed which is significantly enhanced from current distance mapping method. The new approach consists of four steps: preprocessing; construction of improved Distance From Boundary field; centerline extraction; mean value smoothing of centerline. Based on the proposed automatic approach, an interactive extraction method is presented in which a centerline connects specified points selected by cardiologists. This interactive approach makes the viewport closer to pathological changes in the aorta and human heart, so cardiologists can observe focuses more clearly. The two algorithms have been applied to the virtual cardiovascular endoscopy system, and the experiments prove that our methods work well in the process of auxiliary diagnosis.

关键词： Endoscopes Heart Navigation Computed tomography Biomedical imaging Smoothing methods Cavity resonators

来源：评论

学校读者我要写书评

暂无评论

Remote sensing image change detection based on minimum spanning tree clustering

引用

Guangdianzi Jiguang/Journal of Optoelectronics Laser 2014年第12期25卷 2417-2422页

作者： Hu, Xue-Mei Jia, Zhen-Hong Qin, Xi-Zhong Yang, Jie Kasabov, Nikola College of Information Science and Engineering Xinjiang University Urumuqi China Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University Shanghai China Knowledge Engineering and Discovery Research Institute Auckland University of Technology Auckland New Zealand

To obtain complementary information of difference image and gain a better change detection result, this paper proposes an unsupervised change detection algorithm. The technique is based on minimum spanning tree (MST) clustering. First of all, a normalized neighborhood ratio approach is adopted to obtain the difference image of two images acquired in the same geographical area at different moments. Then divide pixels into changed pixels, unchanged pixels and uncertain pixels according to gray difference histogram. Aiming at uncertain pixels, use minimum spanning tree algorithm twice to clustering: texture features and minimum spanning tree algorithm are used for first clustering, then calculate every clustering's average weight, and regarded first clustering results as nodes to calculate the minimum spanning tree again. Finally, on the basis of optimal objective function, the uncertain pixels belong to the two clusters: changed pixels and unchanged pixels. In this paper, the effectiveness of the algorithm is proved by numerical calculation. Mexico data accuracy is 99.01% and operation time is 8.49 s, Sardinia data accuracy is 98.62% and operation time is 8.49 s. Compared with the other three kinds of algorithms, the proposed algorithm can obtain higher detection accuracy and shorter running time.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

An Improvement to Genetic Algorithms for Multimodal Optimization in Noisy Environments: Re-evaluation of All Individuals per Generation

An Improvement to Genetic Algorithms for Multimodal Optimiza...

引用

International Conference on Computational Intelligence and Communication Networks (CICN)

作者： Junhua Li Peng Liu Linxia Zhou Ming Li Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Nanchang Hang Kong University Nanchang China School of Information Engineering Nanchang Hang Kong University Nanchang China

ISBN: (纸本)9781479969302

Optimization in noisy environments is regard as a favorite application domains of genetic algorithms. Different methods for reducing the influence of noise are presented and discussed. A new fitness evaluation method is proposed that reevaluates all survival individuals each generation. Compared with re-sampling and population sizing, the new evaluation approach shows higher probability of searching to the global extremum area and precision of convergence. These results demonstrate that the proposed method is effective for reducing noise effects.

关键词： Noise Noise measurement Genetic algorithms Optimization Sociology Statistics Convergence

来源：评论

学校读者我要写书评

暂无评论

Augmented broadcaster identity-based broadcast encryption

Journal of Digital Information Management

引用

Journal of Digital Information Management 2013年第3期11卷 227-234页

作者： Zhang, Jianhong Xu, Yuwei Chen, Zhipeng Institution of Image Processing and Pattern Recognition North China University of Technology Beijing 100144 China

Identity-based Broadcast Encryption (IBBE) has the inherent key escrow problem that Private Key Generator (PKG) can fully determine the user's private key, which is an obstacle of the application of IBBE. The existing approaches to solving key escrow problem need the user to submit identity to multiple PKGs or interactions between PKG and the user in the private key extraction phase. For Point-to-Multipoint Identity-based Broadcast Encryption (P2MIBBE) that the computing capabilities of receiver are limited, these approaches are impracticable. We propose a new approach what we call Augmented Broadcaster Identity-based Broadcast Encryption (ABIBBE). It requires neither multiple PKGs nor calculation of receiver in the private key extraction phase. We construct a universal scheme to realize AB-IBBE, such that any IND-ID-CPA secure IBBE scheme can be extended to an IND-ID-CPA secure AB-IBBE scheme.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Topological image Analysis and (Normalised) Representations for Plant Phenotyping

Topological Image Analysis and (Normalised) Representations ...

引用

International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC)

作者： Ines Janusch Walter G. Kropatsch Wolfgang Busch Pattern Recognition and Image Processing Group Vienna University of Technology Vienna Austria Gregor Mendel Institute of Molecular Plant Biology Austrian Academy of Sciences Vienna Austria

This paper discusses the use of topological image analysis to derive characteristics needed in plant phenotyping. Due to certain features of root systems (deformation over time, overlaps of branches in a 2D image of the root system) a topological analysis is needed to correctly derive these characteristics. The advantages of such a topological analysis are highlighted in this paper and root phenotyping is presented as a new application for computational topology. Characteristics used in plant phenotyping that can be derived from root images using methods of topological image analysis are further presented. A Reeb graph based representation of root images is shown as an example for such a topological analysis. Based on a graph representation a new, normalised representation of root images is introduced.

关键词： image segmentation Level measurement Topology Length measurement Skeleton image analysis Soil

来源：评论

学校读者我要写书评

暂无评论

An efficient and scalable learning algorithm for Near-Earth objects detection in astronomy big image data

An efficient and scalable learning algorithm for Near-Earth ...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Ke Wang Ping Guo School of computer Science and Technology Beijing Institute of Technology Beijing P.R. China Image Processing and Pattern Recognition Laboratory Beijing Normal University Beijing P.R. China

ISBN: (纸本)9781479938414

In this paper, we investigate the efficiency and scalability of Gaussian mixture model based learning algorithm for the detection of Near-Earth objects in large scale astronomy image data. We propose an effective scheme to reduce the computational complexity of current learning algorithm, this is achieved by adopting the perceptual image hashing method. Our proposed scheme is validated on raw astronomy image data. The experiment results illustrate that both efficiency and scalability are improved significantly in astronomical scenario and other scenario.

关键词： Astronomy Scalability Big data Data mining Gaussian distribution Hamming distance Gaussian mixture model

来源：评论

学校读者我要写书评

暂无评论

Analysis of the Pencil of Conics with Double Complex Contact and Its Application to Camera Calibration

引用

Journal of Shanghai Jiaotong university(Science) 2013年第1期18卷 1-6页

作者：蔡琴王宸昊阎炎刘允才 Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University Information and Communication Technology Department University of Trento

In this paper, we introduce a novel class of coplanar conics, the pencil of which can doubly contact to calibrate camera and estimate pose. We first analyze the properties of con-axes and con-eccentricity ellipses, which consist of a naturM extending pattern of concentric circles. Then the general case that two ellipses have two repeated complex intersection points is presented. This degenerate configuration results in a one-parameter family of homographies which map the planar pattern to its image. Although it is unable to compute the complete homography, an indirect 3-degree polynomial or 5-degree polynomial constraint on intrinsic parameters from one image can also be used for camera calibration and pose estimation under the minimal conditions. Furthermore, this nonlinear problem can be treated as a polynomial optimization problem （POP） and the global optimization solution can be also obtained by using SparsePOP （a sparse semidefinite programming relaxation of POPs）, Finally, the experiments with simulated data and real images are shown to verify the correctness and robustness of the proposed technique.

关键词： camera calibration homography con-axes and con-eccentricity ellipse concentric circle polynomial optimization problem （POP）

来源：评论

学校读者我要写书评

暂无评论

Computer-aided 3D reconstruction and implant planning of auricular prosthesis

Computer-aided 3D reconstruction and implant planning of aur...

引用

2014年上海市研究生学术论坛:生物医疗仪器

作者： Shuang.Li Chunlong.Fang Liuyao.Duan Yuanliang.Huang Lisheng.Wang Institute of Image Processing and Pattern Recognition Department of AutomationShanghai Jiaotong UniversityShanghaiChina Department of dentistryShanghai East Hospital affiliated to Tongji UniversityShanghai 200210China

Auricular-prosthesis-based techniques have been developed for years to repair ears with *** order to obtain good aesthetics and functional effects of the auricular prosthesis,the following two steps are necessary: generate a suitable 3D model of the auricular prosthesis and implant the auricular prosthesis on the patient's ***,there may exist some problems in the current methods,generation of an auricular prosthesis might be costly,imprecise,and ***,clinical physicians usually make a preoperative surgery planning just based on their observation on the series of 2D X-ray images or CT images,which increase the uncertainty of the *** consideration of the limitations in the existing techniques,we develop a computer-aided ear-repairing system to solve these *** mainly contains two parts: 3D reconstruction of auricular prosthesis model and preoperative surgery planning for implanting the auricular ***,the system provides an interactive technique to reconstruct a good 3D model of auricular prosthesis from the patient's CT *** to the model,a high-quality auricular prosthesis can be fabricated by the CAD/CAM technique or 3D print ***,through this system,preoperative surgery planning of implanting can be done and the implanting result can be *** the surgery planning,the surgeon can implant an auricular prosthesis on the patient's skull stably and *** results show that the proposed system can improve the accuracy,safety and intuition of the surgical planning and enhance the functional and aesthetics effects of auricular prosthesis.

关键词： CT imaging auricular prosthesis 3D reconstruction implant surgery planning

来源：评论

学校读者我要写书评

暂无评论

Global matching to enhance the strength of local intensity order pattern feature descriptor

Global matching to enhance the strength of local intensity o...

引用

10th International Symposium on Neural Networks, ISNN 2013

作者： Dawood, Hassan Dawood, Hussain Guo, Ping Image Processing and Pattern Recognition Laboratory Beijing Normal University Beijing 100875 China

ISBN: (纸本)9783642390647

Local intensity order pattern feature descriptor is proposed to extract the feature of image recently. However, it did not provide the global information of an image. In this paper, a simple, efficient and robust feature descriptor is presented, which is realized by adding the global information to local intensity features. A descriptor, which utilizes local intensity order pattern and/or global matching, is proposed to gather the global information with local intensity order. Experimental results shows that the proposed hybrid approach outperform over the state-of-the art feature extraction method like scale-invariant feature transform, local intensity order pattern and DAISY for standard oxford dataset. © Springer-Verlag Berlin Heidelberg 2013.

关键词： Feature extraction

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：