检索结果-内蒙古大学图书馆

IEEE Conference on Computer Vision and Pattern Recognition

作者： Wen Wang Ruiping Wang Zhiwu Huang Shiguang Shan Xilin Chen Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS

ISBN: (纸本)9781467369657

This paper presents a method named Discriminant Analysis on Riemannian manifold of Gaussian distributions (DARG) to solve the problem of face recognition with image sets. Our goal is to capture the underlying data distribution in each set and thus facilitate more robust classification. To this end, we represent image set as Gaussian Mixture Model (GMM) comprising a number of Gaussian components with prior probabilities and seek to discriminate Gaussian components from different classes. In the light of information geometry, the Gaussians lie on a specific Riemannian manifold. To encode such Riemannian geometry properly, we investigate several distances between Gaussians and further derive a series of provably positive definite probabilistic kernels. Through these kernels, a weighted Kernel Discriminant Analysis is finally devised which treats the Gaussians in GMMs as samples and their prior probabilities as sample weights. The proposed method is evaluated by face identification and verification tasks on four most challenging and largest databases, YouTube Celebrities, COX, YouTube Face DB and Point-and-Shoot Challenge, to demonstrate its superiority over the state-of-the-art.

关键词： Kernel Manifolds Gaussian distribution Face recognition Covariance matrices Data models Adaptation models

来源：评论

学校读者我要写书评

暂无评论

Adaptive sparse recovery based on difference algorithm

引用

Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics 2015年第6期27卷 1047-1052页

作者： Zhang, Fengzhen Zhao, Ruizhen Cen, Yigang Hu, Shaohai Zhang, Yongdong Institute of Information Science Beijing Jiaotong University Beijing100044 China Key Laboratory of Advanced Information Science and Network Technology of Beijing Beijing100044 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China

To improve the disadvantages that iterative reconstruction algorithms of compressed sensing need priori knowledge of the sparsity of original signal or iterative threshold, an adaptive sparse recovery based on difference algorithm is proposed. When the sparsity of original signal is unknown, the proposed algorithm takes advantage of unbalance of correlation coefficient between the measurement matrix and residual. With those properties, the proposed algorithm can select the support set of the original signal, and approach the sparsity of the original signal. Simulation results show that the proposed algorithm obtains better recovery results under the same conditions. Especially in the lower sampling rate, the advantage is more obvious. ©, 2015, institute of computing technology. All right reserved.

关键词： Recovery

来源：评论

学校读者我要写书评

暂无评论

Noisy image super-resolution reconstruction based on sparse representation

引用

Jisuanji Yanjiu yu Fazhan/Computer Research and Development 2015年第4期52卷 943-951页

作者： Dou, Nuo Zhao, Ruizhen Cen, Yigang Hu, Shaohai Zhang, Yongdong Institute of Information Science Beijing Jiaotong University Beijing100044 China Beijing Key Laboratory of Advanced Information Science and Network Technology Institute of Information Science Beijing Jiaotong University Beijing100044 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China

Denoising and super-resolution reconstruction are performed separately in traditional methods for noisy image super-resolution reconstruction, while in the noisy image super-resolution reconstruction method based on sparse representation and dictionary learning the two processes are compounded together. Since an image patch can be well represented as a sparse linear combination of elements from an appropriately chosen over-complete dictionary, two dictionaries are trained respectively from noisy low-and clean high-resolution image patches by enforcing the similarity of two sparse representations with respect to their own dictionary. Given a noisy low-resolution image, sparse representations of low-resolution patches via trained low-dictionary are computed, then the high-resolution image can be reconstructed from high-resolution patches with the help of the related low-resolution sparse representations and trained high-dictionary, after global optimization a clean high-resolution is obtained to accomplish the goal of image super-resolution and denosing simultaneously. The experiments show that zooming low-resolution image to a middle-resolution using locally adaptive zooming algorithm for extracting features can get a better reconstructed image than bicubic interpolation algorithm. By setting the parameter λ, we can obtain the best performance both in super-resolution and denoising with absolute advantages in image quality and visual effect, which demonstrates the validity and robustness of our algorithm. ©, 2015, Science Press. All right reserved.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

The B4-Modalized Propositional Logic

The B4-Modalized Propositional Logic

引用

2015 International Conference on Mechanical,Electronic and information technology Engineering

作者： Cao Cungen Sui Yuefei Deng Shaobo Key Laboratory of Intelligent Information Processing Institute of Computing TechnologyChinese Academy of Science University of Chinese Academy of Sciences

A modalized propositional Belnap-Dunn logic will be proposed in this paper which there are four modalities [t],[T],[⊥],[f]to represent the four values t,T,⊥,f, respectively, and a Gentzentyped deduction system will ... 详细信息

关键词： The Belnap-Dunn logic,modality,the soundness,the completeness

来源：评论

学校读者我要写书评

暂无评论

AgeNet: Deeply Learned Regressor and Classifier for Robust Apparent Age Estimation

AgeNet: Deeply Learned Regressor and Classifier for Robust A...

引用

International Conference on Computer Vision Workshops (ICCV Workshops)

作者： Xin Liu Shaoxin Li Meina Kan Jie Zhang Shuzhe Wu Wenxian Liu Hu Han Shiguang Shan Xilin Chen Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology Beijing China Tencent BestImage Team Shanghai China

Apparent age estimation from face image has attracted more and more attentions as it is favorable in some real-world applications. In this work, we propose an end-to-end learning approach for robust apparent age estimation, named by us AgeNet. Specifically, we address the apparent age estimation problem by fusing two kinds of models, i.e., real-value based regression models and Gaussian label distribution based classification models. For both kind of models, large-scale deep convolutional neural network is adopted to learn informative age representations. Another key feature of the proposed AgeNet is that, to avoid the problem of over-fitting on small apparent age training set, we exploit a general-to-specific transfer learning scheme. Technically, the AgeNet is first pre-trained on a large-scale web-collected face dataset with identity label, and then it is fine-tuned on a large-scale real age dataset with noisy age label. Finally, it is fine-tuned on a small training set with apparent age label. The experimental results on the ChaLearn 2015 Apparent Age Competition demonstrate that our AgeNet achieves the state-of-the-art performance in apparent age estimation.

关键词： Estimation Encoding Robustness Neural networks Face Aging Standards

来源：评论

学校读者我要写书评

暂无评论

A novel level set model based on multi-scale local structure operation for texture image segmentation

引用

Journal of information and Computational Science 2015年第1期12卷 9-20页

作者： Min, Hai Wang, Xiaofeng Department of Automation University of Science and Technology of China Hefei China Intelligent Computing Lab Hefei Institute of Intelligent Machines Chinese Academy of Sciences Hefei China Key Lab of Network and Intelligent Information Processing Department of Computer Science and Technology Hefei University Hefei China

Regional level set method is a popular approach for image segmentation that uses inside and outside information of contour to extract object boundary. Unfortunately, in many cases, such method is not adequate to model complex textured objects. In this paper, we propose a natural texture image segmentation method which incorporates the pixel-level feature into region-level feature. The multi-scale local structure operation is proposed as pixel-level feature to describe the texture structure of image. So the problems of multi-scale and rotation invariance of inhomogeneous texture are addressed by introducing multi-scale local structure operation into level set energy functional. Then, the global intensity information is extracted as the region-level feature and integrated with multi-scale local structure operation. Further, we propose a so-called vector level set method to obtain the segmentation results. Here, we extend the traditional regional level set model into the vector formulation so that the multi-scale local structure operation can be suitably combined with the global intensity information to achieve the more superior image segmentation performance than that of the traditional segmentation methods for texture images. Experiments on some synthesis texture images and real natural scene images demonstrate the excellent performance of the proposed method which successfully combines local structure information and global intensity information to extract the object boundary.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Whole genome/proteome based phylogeny reconstruction for prokaryotes using higher order Markov model and chaos game representation

引用

Molecular phylogenetics and evolution 2016年 96卷 102-111页

作者： Wei-Feng Yang Zu-Guo Yu Vo Anh Hunan Key Laboratory for Computation and Simulation in Science and Engineering and Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan University Hunan 411105 PR China Department of Mathematics and Physics Hunan Institute of Engineering Hunan 411104 PR China. Electronic address: yangweifeng09@***. School of Mathematical Sciences Queensland University of Technology GPO Box 2434 Brisbane QLD 4001 Australia. Electronic address: yuzuguo@***. School of Mathematical Sciences Queensland University of Technology GPO Box 2434 Brisbane QLD 4001 Australia. Electronic address: v.anh@qut.edu.au.

UNlabELLED:Traditional methods for sequence comparison and phylogeny reconstruction rely on pair wise and multiple sequence alignments. But alignment could not be directly applied to whole genome/proteome comparison and phylogenomic studies due to their high computational complexity. Hence alignment-free methods became popular in recent years. Here we propose a fast alignment-free method for whole genome/proteome comparison and phylogeny reconstruction using higher order Markov model and chaos game representation. In the present method, we use the transition matrices of higher order Markov models to characterize amino acid or DNA sequences for their comparison. The order of the Markov model is uniquely identified by maximizing the average Shannon entropy of conditional probability distributions. Using one-dimensional chaos game representation and linked list, this method can reduce large memory and time consumption which is due to the large-scale conditional probability distributions. To illustrate the effectiveness of our method, we employ it for fast phylogeny reconstruction based on genome/proteome sequences of two species data sets used in previous published papers. Our results demonstrate that the present method is useful and efficient. AVAIlabILITY AND IMPLEMENTATION:The source codes for our algorithm to get the distance matrix and genome/proteome sequences can be downloaded from ftp://121.199.20.25/. The software Phylip and EvolView we used to construct phylogenetic trees can be referred from their websites.

关键词： Alignment-free whole proteome comparison Chaos game representation Higher order Markov model Phylogenetic tree Shannon entropy

来源：评论

学校读者我要写书评

暂无评论

A fast classification method using SVM based on affinity propagation clustering algorithm

引用

Journal of Computational information Systems 2015年第16期11卷 6073-6080页

作者： Xu, Li Ding, Shifei Huang, Huajuan School of Computer Science and Technology China University of Mining and Technology Xuzhou China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

The classification speed of SVM is inversely proportional to the number of Support Vectors (SVs). Therefore, the less SVs mean the more sparseness and the higher classification speed. In order to reduce the number of SVs but without lossing of generalization performance, a new algorithm called Fast Classification Method Using SVM Based on Affinity Propagation clustering algorithm (FCSVM-AP) is proposed, which employs Affinity Propagation (AP) clustering algorithm to cluster the original SVs and the cluster centers are used as the new SVs, then aiming to minimize the classification gap between SVM and FCSVM-AP, a quadratic programming model is built for obtaining the optimal coefficients of the new SVs. Meanwhile, it is proven that when clustering the original SVs, the minimal upper bound of the error between the original decision function and the fast decision function can be achieved by AP. Finally, experiments show that compared with original SVs, the number of SVs decreases and the speed of classification increases using FCSVM-AP, while the loss of accuracy is in the acceptable level. © 2015 by Binary information Press

关键词： Quadratic programming

来源：评论

学校读者我要写书评

暂无评论

A hybrid deep learning CNN-ELM model and its application in handwritten numeral recognition

引用

Journal of Computational information Systems 2015年第7期11卷 2673-2680页

作者： Guo, Lili Ding, Shifei School of Computer Science and Technology China University of Mining and Technology Xuzhou China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

Convolutional Neural Network (CNN) is a typical algorithm structure of deep learning and it has applied in image recognition field widely. Based on CNN, this paper puts forward a novel hybrid deep learning model CNN-ELM. In this model, CNN is in charge of feature extraction and Extreme Learning Machine (ELM) performs as a classifier to complete the final classification so as to integrate the synergy of two classifiers. We have took experiments on MNIST digit database. Comparisons with CNN and ELM on the same database, CNN-ELM achieved an error rate of 0.67%, which indicate that CNN-ELM has achieved better generalization performance. ©, 2015, Binary information Press. All right reserved.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

Social sensing enhanced time estimation for bus service

Social sensing enhanced time estimation for bus service

引用

作者： Liu, Jin Li, Juan Cui, Xiaohui Niu, Xiaoguang Sun, Xiaoping Zhou, Jing State Key Lab. of Software Engineering Computer School Wuhan University Wuhan China Guangxi Key Laboratory of Trusted Software Guilin University of Electronic Technology Guilin China International School of Software Wuhan University Wuhan China Computer School Wuhan University Wuhan China Key Lab of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science Communication University of China China

The precise prediction of bus routes or the arrival time of buses for a traveler can enhance the quality of bus service. However, many social factors influence people's preferences for taking buses. These social factors may include heavy traffic cost, traffic congestion, poor air quality and so forth. Existing prediction techniques rarely consider social sensing when predicting the bus arrival time. Accordingly, this paper proposes a social sensing enhanced service for predicting bus routes, which integrates sensing ability and social networks to understand and measure the influence between social events and vehicle velocity. We focus on the analysis of two different attributions: PT service quality attributions PEAs and road condition attributions PRCAs. Both of them synthesize the social sensing in their evaluation of bus routes. PEA represents individual preferences and PRCA represents physical factors that significantly influence vehicle velocity. Bus relevant social events were further categorized into PEA events or PRCA events. PEAs of buses were scored according to the tendency of bus conditions reflected in social events. Furthermore, an artificial neural network prediction model is established to estimate the bus travel time. © 2015 John Wiley & Sons, Ltd.

关键词： Buses

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：