检索结果-内蒙古大学图书馆

2012 5th IAPR International Conference on Biometrics, ICB 2012

作者： Huang, Di Ardabilian, Mohsen Wang, Yunhong Chen, Liming Laboratory of Intelligent Recognition and Image Processing School of Computer Science and Engineering Beihang University Beijing 100191 China Université de Lyon CNRS UMR5205 Lyon 69134 France

ISBN: (纸本)9781467303941

Recently, asymmetric 3D-2D face recognition has been paid increasing attention. It enrolls in textured 3D faces and performs identification using only 2D facial images, therefore it generally achieves a better result than 2D algorithms do, and avoids inconvenience of data acquisition and computation of 3D methods as well. In this paper, a biological vision-based facial representation, namely Oriented Gradient Maps (OGMs), is introduced for such an application. It simulates the response of complex neurons to gradient information within a pre-defined neighborhood, and thus can describe local texture changes of 2D faces and local geometry variations of 3D faces at the same time. Due to its property of being highly distinctive, these OGMs improve accuracies of both matching steps of asymmetric face recognition, i.e. (1) 3D-2D matching using Canonical Correlation Analysis (CCA);(2) 2D-2D matching using LBP histogram based features and Sparse Representation Classifier (SRC). Some comparative experiments are carried out on the complete FRGC v2.0 database, and the achieved results clearly highlight the effectiveness of the biological vision-based facial description and its successful application to asymmetric face recognition. © 2012 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Integrating Segmentation and Classification Accuracy for Accuracy Assessment in Object-based image Analysis

Integrating Segmentation and Classification Accuracy for Acc...

引用

International Conference on Audio, Language and image processing

作者： Nan Li Hong Huo Tao Fang Institute of Image Processing and Pattern Recognition Department of Automation Shanghai Jiao Tong University and Key Laboratory of System Control and Information Processing Ministry of Education Institute of Image Processing and PatternRecognition Department of Automation Shanghai Jiao Tong University and Key Laboratory of System Control and Information Processing Ministry of Education

ISBN: (纸本)9781467301732

An accuracy assessment method that integrates segmentation and classification accuracy is proposed to meet the requirements of object-based image analysis. Segmentation errors are measured by establishing the relationship between pixels and their corresponding segments according to the overlaps of segments and reference polygons. Then, two improved confusion matrices that take the segmentation errors into consideration are used: one for pixel-level classification results, and the other for object-level classification results. A final accuracy assessment combines the statistics of these two confusion matrices. The proposed method can be applied to segmentation scale selection in the hierarchical interpretation system. An experiment on a SPOT5 image demonstrates the effectiveness of this method for segmentation scale selection, which can guide the fusion of objects of different scales to obtain a higher accuracy.

关键词： segmentation image analysis Segmentation object orientation confusion matrix pixel

来源：评论

学校读者我要写书评

暂无评论

An adaptive image denoising method based on anisotropic diffusion equation

引用

ICIC Express Letters 2012年第7期6卷 1877-1882页

作者： Zhang, Meng-Meng Yang, Zhi-Hui Ma, Ling Institute of Image Processing and Pattern Recognition North China University of Technology No. 5 Jinyuanzhuang Road Shijingshan District Beijing 100144 China

An adaptive filtering method based on the anisotropic diffusion equation is proposed in this paper. Firstly, the denoising principal of the anisotropic diffusion equation is studied. And then, adaptive filtering of image is realized by combining the improved image structural similarity algorithm with the anisotropic diffusion equation. Experiment results show that the improved structural similarity algorithm has good robustness and advantages in the application of adaptive filtering. © 2012 ICIC International.

关键词： Adaptive filtering

来源：评论

学校读者我要写书评

暂无评论

An improved method of identification based on thermal palm vein image 1

引用

19th International Conference on Neural Information processing, ICONIP 2012

作者： Wang, Ran Wang, Guoyou Chen, Zhong Liu, Jianguo Shi, Yu National Key Laboratory of Science and Technology on Multi-spectral Information Processing Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology 1037 Luoyu Road Hongshan District 430074 Wuhan Hubei Province China

ISBN: (数字)9783642344817

ISBN: (纸本)9783642344800

Biological characteristics based on face, fingerprint and iris images have been extensively studied and used for the identification in the past few decades. As a new-born method, thermal palm vein pattern is gathering more and more attention all over the world. An improved method of identification based on thermal palm vein image is presented in the paper. Five steps are needed to have a person verified: 1) acquisition of infrared palm vein image;2) detection of ROI (region of interest);3) enhancement of the palm vein image;4) features extraction of the palm vein patterns;5) matching the features between the real palm vein and sample data. Experiments have been carried out on 178 different images and 176 images of them are correctly recognized with two in failure. Experiments show the detection rate is satisfied. © 2012 Springer-Verlag.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Maximum margin clustering on evolutionary data 12

Maximum margin clustering on evolutionary data

引用

21st ACM International Conference on Information and Knowledge Management, CIKM 2012

作者： Fan, Xuhui Zhu, Lin Cao, Longbing Cui, Xia Ong, Yew-Soon Advanced Analytics Institute Faculty of Engineering and Information Technology University of Technology Sydney Sydney NSW Australia Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China School of Computer Engineering Nanyang Technological University Signapore Singapore

ISBN: (纸本)9781450311564

Evolutionary data, such as topic changing blogs and evolving trading behaviors in capital market, is widely seen in business and social applications. The time factor and intrinsic change embedded in evolutionary data greatly challenge evolutionary clustering. To incorporate the time factor, existing methods mainly regard the evolutionary clustering problem as a linear combination of snapshot cost and temporal cost, and reflect the time factor through the temporal cost. It still faces accuracy and scalability challenge though promising results gotten. This paper proposes a novel evolutionary clustering approach, evolutionary maximum margin clustering (e-MMC), to cluster large-scale evolutionary data from the maximum margin perspective. e-MMC incorporates two frameworks: Data Integration from the data changing perspective and Model Integration corresponding to model adjustment to tackle the time factor and change, with an adaptive label allocation mechanism. Three e-MMC clustering algorithms are proposed based on the two frameworks. Extensive experiments are performed on synthetic data, UCI data and real-world blog data, which confirm that e-MMC outperforms the state-of-the-art clustering algorithms in terms of accuracy, computational cost and scalability. It shows that e-MMC is particularly suitable for clustering large-scale evolving data. © 2012 ACM.

关键词： Clustering algorithms

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

One-Class SVM assisted accurate tracking

One-Class SVM assisted accurate tracking

引用

ACM/IEEE International Conference on Distributed Smart Cameras, ICDSC

作者： Keren Fu Chen Gong Yu Qiao Jie Yang Irene Guy Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China Ministry of Education of China Key Laboratory of System Control and Information Processing Shanghai China Chalmers tekniska hogskola Goteborg SE

Recently, tracking is regarded as a binary classification problem by discriminative tracking methods. However, such binary classification may not fully handle the outliers, which may cause drifting. In this paper, we argue that tracking may be regarded as one-class problem, which avoids gathering limited negative samples for background description. Inspired by the fact the positive feature space generated by One-Class SVM is bounded by a closed sphere, we propose a novel tracking method utilizing One-Class SVMs that adopt HOG and 2bit-BP as features, called One-Class SVM Tracker (OCST). Simultaneously an efficient initialization and online updating scheme is also proposed. Extensive experimental results prove that OCST outperforms some state-of-the-art discriminative tracking methods on providing accurate tracking and alleviating serious drifting.

关键词： Target tracking Support vector machines Training Feature extraction Face Boosting Semisupervised learning

来源：评论

学校读者我要写书评

暂无评论

Feedback-free and hybrid distributed video coding using neural networks

Feedback-free and hybrid distributed video coding using neur...

引用

International Symposium on Signal processing and Its Applications (ISSPA)

作者： Isaac Nickaein Mohammad Rahmati Saeed Shiry Ghidary Abtin Zohrabi Image Processing and Pattern Recognition Lab Amirkabir University of Technology Tehran Iran Abtin Zohrabi University of New Brunswick Canada

Distributed Video Coding (DVC) is a new class of video coding techniques with the aim of coding the decentralized video sources. While the Stanford Wyner-Ziv codec is a well-known architecture in DVC literature, one of its main drawbacks is the presence of a feedback channel from the decoder to the encoder. This feedback channel makes the use of the codec impractical in some applications. Since the only application of the feedback channel is in requesting more parity bits from the encoder, it could be omitted if the encoder estimates the required parity bits and sends them at once. In this paper, a new method of bitrate estimation using a neural network trained by a new set of features is proposed. In addition, a Hybrid mode is proposed that reduces computational complexity at the decoder in a conventional Wyner-Ziv codec.

关键词： Bit rate Decoding Encoding Estimation Video coding Neural networks Video sequences

来源：评论

学校读者我要写书评

暂无评论

Document understanding of graphical content in natively digital PDF documents 12

Document understanding of graphical content in natively digi...

引用

2012 ACM Symposium on Document Engineering, DocEng 2012

作者： Gabdulkhakova, Aysylu Hassan, Tamir Department of Computing Mathematics and Cybernetics Ufa State Aviation Technical University K. Marx str. 12 450000 Ufa Russia Pattern Recognition and Image Processing Group Technische Universität Wien Favoritenstraße 9-11 1040 Wien Austria

ISBN: (纸本)9781450311168

This paper presents an object-based method for analysing the content drawn by graphical operators in natively digital PDF documents. We propose that graphical content in a document can be classified either as structural or nonstructural and present an output model for our analysis result. Heuristic techniques are used to group the instructions into regions and determine their logical role in the document's structure. Experimental results demonstrate the effectiveness of the algorithm. Copyright © 2012 by the Association for Computing Machinery, Inc. (ACM).

关键词： Structural analysis

来源：评论

学校读者我要写书评

暂无评论

Ethnicity classification based on fusion of face and gait

Ethnicity classification based on fusion of face and gait

引用

IAPR International Conference on Biometrics (ICB)

作者： De Zhang Yunhong Wang Zhaoxiang Zhang Maodi Hu Intelligent Recognition and Image Processing Laboratory School of Computer Science and Engineering Beihang University Beijing China

The recognition of ethnicity of an individual can be very useful in a video-based surveillance system. In this paper, we propose a multimodal biometric system involving an integration of frontal face and lateral gait, for the specific problem of ethnicity classification. This system performs a feature fusion to improve the discrimination of human ethnicity. Face features are extracted by means of the uniform LBP operator and gait information is characterized by a spatio-temporal representation. Afterwards, canonical correlation analysis (CCA), as a powerful tool to relate two sets of measurements, is used to fuse the two modalities at the feature level. A database including 36 walking people from East Asia and South America is built for the purpose of ethnicity classification. The experimental results show that the ethnicity recognition rate is improved by fusing face and gait information.

关键词： Face Feature extraction Databases Support vector machines Cameras Vectors Legged locomotion

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：