检索结果-内蒙古大学图书馆

International Conference on pattern recognition

作者： Ziyi Xu Li Lu Pengfei Shi Institute of Image Processing and Pattern Recognition Shandong Jiaotong University Shanghai China

ISBN: (纸本)9781424421749

Recently, gender classification from face images has attracted a great deal of attention. It can be useful in many places. In this paper, a novel hybrid face coding method by fusing appearance features and geometry features is presented. We choose Haar wavelets to represent the appearance features and use AdaBoost algorithm to select stronger features. Geometry features are regarded as apriori knowledge to help improve the classification performance. In this work, active appearance model (AAM) locates 83 landmarks, Thus we can get 3403 geometry features, from which 10 most significant features are picked, normalized and fused with the appearance features. Experimental results show the effectiveness and robustness of the proposed approach regarding expression, illumination and pose variation in some degree.

关键词： Geometry Feature extraction Face Active appearance model Nose Data mining image processing pattern recognition image coding Robustness

来源：评论

学校读者我要写书评

暂无评论

A novel fragments-based tracking algorithm using mean shift

A novel fragments-based tracking algorithm using mean shift

引用

International Conference on Control, Automation, Robotics and Vision (ICARCV)

作者： Fanglin Wang Shengyang Yu Jie Yang Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University Shanghai China

Multiple image fragments have been used to represent the target for tracking in a video sequence. It is proved to be able to maintain spatial information of the target. In this paper, following the idea that represents the target with multiple image fragments, we propose a framework that can efficiently combine multiple spatially distributed fragment histograms for robust tracking. The framework ranks the importance of each fragment adaptively, which can increase the robustness to partial occlusions and pose variation. We derive a mean shift type algorithm for the framework that allows efficient target tracking with very low computational overhead. Extensive experiments on challenging real video sequences clearly demonstrate the benefits of our tracker.

关键词： Target tracking Histograms Robustness Video sequences Robotics and automation Automatic control Robot control Robot vision systems image processing pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Age Estimation Robust to Expression Variations

Age Estimation Robust to Expression Variations

引用

International Conference on Computational Intelligence for Modelling, Control and Automation, and International Conference on Intelligent Agents, Web Technologies and Internet Commerce

作者： Li Lu Ziyi Xu Yuan Hu Pengfei Shi Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University Shanghai China

In this paper, we present a novel age estimation method that is able to deal with varying face expressions. We construct two efficient descriptors for face appearance which are robust to expression variations. One is termed as Proportion Descriptor constructed by proportion indices based on facial geometric features, the other is termed as Local Descriptor based on local facial texture features extracted by Modular Principle Component Analysis (MPCA). We set up experiments for evaluating the performance of the two facial descriptors in the presence of facial expressions.

关键词： Robustness Face detection Aging image texture analysis Eyes Principal component analysis Lighting image analysis Performance analysis Nose

来源：评论

学校读者我要写书评

暂无评论

Probability evolutionary algorithm for functional and combinatorial optimization

Probability evolutionary algorithm for functional and combin...

引用

World Congress on Intelligent Control and Automation (WCICA)

作者： Shuhan Shen Yuncai Liu Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University Shanghai China

A novel evolutionary algorithm called probability evolutionary algorithm (PEA) is proposed, which is inspired by the quantum computation and quantum-inspired evolutionary algorithm (QEA). The individual in PEA is encoded by a probabilistic superposed bit which can represent a linear superposition of the states 0 to k (k ges 1). The observing step is used in PEA to obtain the observed individual, and the update method is used to evolve the population. The function optimization and 0-k knapsack problem experiments show that PEA has apparent superior in application area, searching capability and computation time compared with QEA and canonical genetic algorithm (CGA).

关键词： Probabilistic logic Evolutionary computation Optimization Quantum computing Encoding Genetic algorithms Convergence

来源：评论

学校读者我要写书评

暂无评论

A Modified Greedy Distance Routing Algorithm for Wireless Sensor Networks

A Modified Greedy Distance Routing Algorithm for Wireless Se...

引用

China-Japan Joint Microwave Conference

作者： Q. Q. Shi H. Huo T. Fang D. R. Li Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University Shanghai China

ISBN: (纸本)9781424438211

Geographic routing protocols for wireless sensor networks (WSNs) have received more attentions in recent years and greedy forwarding algorithm is a main component in geographic routing. In this paper, we investigate the forwarding criterions in greedy forwarding algorithms and present a greedy routing algorithm using a new criterion combining the characteristics of both distance-based criterion and direction-based criterion. Simulation is provided to compare the performance of our algorithm with those of the algorithm with distance-based criterion and the algorithm with direction-based criterion. The results show that our proposed algorithm is a preferred option in terms of the trade-off between transformation delay and energy consumption in the routing.

关键词： Wireless sensor networks Routing protocols image processing pattern recognition Euclidean distance Joining processes Delay Energy consumption Network topology Computer architecture

来源：评论

学校读者我要写书评

暂无评论

Automatic needle segmentation using 3D Gray-level Hough Transform in 3D ultrasound images

引用

Journal of Computational Information Systems 2008年第5期4卷 2021-2026页

作者： Qiu, Wu Ding, Mingyue Yuchi, Ming Image Processing and Intelligence Control Key Lab. of Education Ministry of China Institute of Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan 430074 China Department of Biomedical Engineering School of Life Science and Technology Huazhong University of Science and Technology Wuhan 430074 China

This paper describes a novel 3D needle segmentation algorithm for 3DUS data. The algorithm includes the 3D Gray-level Hough Transform (3DGHT), which is based on the representation (ψ, θ, ρ, α) of straight lines in 3D space and Local Dimensionality Estimator (GST). Different from the traditional Hough transformation the process of binarization is not needed, because the proposed algorithm adopts the original gray level image directly. We tested it with the synthetic data and water phantom. The results show that our algorithm works well in 3D US images with angular deviation less than 1° and position deviation less than 1 mm. © 2008 Binary Information Press.

关键词： Hough transforms

来源：评论

学校读者我要写书评

暂无评论

Extracting key postures in a human action video sequence

Extracting key postures in a human action video sequence

引用

2008 IEEE 10th Workshop on Multimedia Signal processing, MMSP 2008

作者： Chen, Yan Wu, Qiang He, Xiangjian Du, Chunhua Yang, Jie Falculty of Information Technology University of Technology Sydney PO Box 123 Broadway NSW 2007 Australia Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai 200240 China

ISBN: (纸本)9781424422951

Human key posture extraction from videos will benefit video storage, video retrieval, human action recognition, human behaviour understanding and so on. This paper presents an approach to select key postures from human action sequences using 2D information. There are two steps in the proposed method. Information measurement which is a kind of global feature of a frame is used to roughly find key posture candidates. Then, a body skeleton feature which is a kind of local feature is applied to select final key postures from the candidates obtained in the first step. The experiments show that the proposed method is efficient. © 2008 IEEE.

关键词： Behavioral research

来源：评论

学校读者我要写书评

暂无评论

On Determining the Projected Sphere Center and Its Application in Optical Tracking Systems

On Determining the Projected Sphere Center and Its Applicati...

引用

International Conference on BioMedical Engineering and Informatics (BMEI)

作者： Yinqiang Zheng Yuncai Liu Image Processing and Pattern Recognition Institute Shanghai Jiaotong University Shanghai China

In this article, we explain why and how to identify the projected sphere center, i.e. the projection of the sphere center, in passive-mode based optical tracking systems using infrared reflective spheres as markers. We first present the algebraic representation of the 'deviation', defined by their Euclidian distance in the image coordinate system, between the projected sphere center and the center of the elliptical contour of the sphere's image, and show that the common approximation to substitute the later for the former is not always appropriate in terms of accuracy. Then, we give the projective equation of a sphere in matrix form, thus paving the way for the linear estimation of the projected sphere center. Sufficient experiments indicate that this proposed method enlarges the manipulating volume of the optical tracking system and improves the precision of locating surgical instruments.

关键词： Surgical instruments Biomedical optical imaging Cameras Surgery Matrices Calibration Nonlinear equations Biomedical engineering Biomedical informatics image processing

来源：评论

学校读者我要写书评

暂无评论

An Improved Random Sampling LDA for Face recognition

An Improved Random Sampling LDA for Face Recognition

引用

Congress on image and Signal processing, CISP

作者： Yunfei Jiang Xinyu Chen Ping Guo Hanqing Lu Laboratory of Image Processing and Pattern Recognition Beijing Normal University Beijing China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy and Sciences Beijing China

Linear Discriminant Analysis (LDA) is one of the most used feature extraction techniques for face recognition. However, it often suffers from the small sample size problem with high dimension setting. Random Subspace Method (RSM) is a popular combining technique to improve weak classifier. Nevertheless, it remains a problem how to construct an optimal random subspace for discriminant analysis. In this paper, we propose an improved random sampling LDA for face recognition. Firstly, AdaBoost is adopted to select Gabor feature and remove redundant information. Secondly, in the selected Gabor feature space, we combine principal component analysis and RSM approaches to construct optimal random subspaces for LDA. After that, direct LDA (D-LDA) and R-LDA is applied in each subspace, respectively. Final results are obtained by combining all the LDA classifiers using a fusion rule. Experiments with both the ORL and FERET face databases demonstrate the effectiveness of our proposed method, and it shows promising results compared with previous approaches.

关键词： Sampling methods Linear discriminant analysis Face recognition Principal component analysis pattern recognition Laboratories Feature extraction Scattering Signal processing image sampling

来源：评论

学校读者我要写书评

暂无评论

Multi-scale Nonlinear Contrast Enhancement of Radiographies Based on Human Contrast Sensitivity

Multi-scale Nonlinear Contrast Enhancement of Radiographies ...

引用

2008 5th International Conference on Visual Information Engineering (VIE 2008)

作者： Min Zhang Xuanqin Mou Institute of Image Processing and Pattern Recognition Xi'an Jiaotong University Xi'an Shaanxi China

Medical imaging techniques like computed/digital radiography (CR/DR) have introduced a formidably powerful tool in medicine. image enhancement takes an important roll in the CR/DR computerized analysis process. Much effort has been put into the area of image enhancement. However, conventional multi-scale methods have the drawback of the introduction of severe visible artifacts while large structures are enhanced strongly. This paper presents a nonlinear multi-scale medical image contrast enhancement method for the improvement of medical image quality. More specifically, a novel nonlinear enhancement function is proposed incorporated with human visual local perceptual contrast. The proposed work provides the advantages of enhancing or preserving image contrast while suppressing visible artifacts. To quantitatively compare the performance of the proposed method, the average local variances are used as comparison criteria. Results demonstrate the superiority of the proposed method. Our results show that the proposed method has the potential to become useful for improvement of image quality of medical images.

关键词：

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：