检索结果-内蒙古大学图书馆

Multiuser-based gray-level watermarking sharing system

Journal of Multimedia 2009年第6期4卷 341-348页

作者： Luo, Bin Wu, Youqing Tang, Jin Lv, Wanli Gu, Wei Key Lab of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei Anhui China

A novel watermarking sharing system having the ability of sharing gray-level secret images with multi-user is proposed. Multiple-based number system is used to split the secret into n meaningless shares, each share is embedded into respective cover image with controlled distortion and to be assigned to each user afterwards. The architecture of the proposed watermarking system is an open issue, which means the system is easy to be implemented according to the purposes and concerns of the users. The main feature of the proposed system is sharing a secret of gray-level image among multi-users;another application of such system is ownership verification. To reveal the secret, the necessary amount of shares has to be presented. That is, the secret can be recovered even if some shares were lost. Simulation results show that the recovered secret has robustness against a wide range of imaging processing operations. © 2009 ACADEMY PUBLISHER.

关键词： Numbering systems

来源：评论

学校读者我要写书评

暂无评论

Sub-sentence division for tree-based machine translation

Sub-sentence division for tree-based machine translation

引用

Joint Conference of the 47th Annual Meeting of the Association for Computational Linguistics and 4th International Joint Conference on Natural Language processing of the AFNLP, ACL-IJCNLP 2009

作者： Xiong, Hao Xu, Wenwen Mi, Haitao Liu, Yang Liu, Qun Key Lab. of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences P.O. Box 2704 Beijing 100190 China Key Lab. of Computer System and Architecture Institute of Computing Technology Chinese Academy of Sciences P.O. Box 2704 Beijing 100190 China

ISBN: (纸本)9781617382581

Tree-based statistical machine translation models have made significant progress in recent years, especially when replacing 1-best trees with packed forests. However, as the parsing accuracy usually goes down dramatically with the increase of sentence length, translating long sentences often takes long time and only produces degenerate translations. We propose a new method named subsentence division that reduces the decoding time and improves the translation quality for tree-based translation. Our approach divides long sentences into several sub-sentences by exploiting tree structures. Large-scale experiments on the NIST 2008 Chinese-to-English test set show that our approach achieves an absolute improvement of 1.1 BLEU points over the baseline system in 50% less time. © 2009 ACL and AFNLP.

关键词： Machine translation

来源：评论

学校读者我要写书评

暂无评论

Improving Statistical Machine Translation Using Domain Bilingual Multiword Expressions

Improving Statistical Machine Translation Using Domain Bilin...

引用

2009 Workshop on Multiword Expressions: Identification, Interpretation, Disambiguation, Applications, MWE 2009

作者： Ren, Zhixiang Lü, Yajuan Cao, Jie Liu, Qun Huang, Yun Key Lab. of Intelligent Info. Processing Institute of Computing Technology Chinese Academy of Sciences P.O. Box 2704 Beijing100190 China Department of Computer Science School of Computing National University of Singapore Computing 1 Law Link Singapore117590 Singapore

ISBN: (纸本)1932432604

Multiword expressions (MWEs) have been proved useful for many natural language processing tasks. However, how to use them to improve performance of statistical machine translation (SMT) is not well studied. This paper presents a simple yet effective strategy to extract domain bilingual multiword expressions. In addition, we implement three methods to integrate bilingual MWEs to Moses, the state-of-the-art phrase-based machine translation system. Experiments show that bilingual MWEs could improve translation performance significantly. © 2009 ACL and AFNLP

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Performance analysis of an HMM-based gesture recognition using a wristwatch device

Performance analysis of an HMM-based gesture recognition usi...

引用

7th IEEE/IFIP International Conference on Embedded and Ubiquitous computing, EUC 2009

作者： Amstutz, Roman Amft, Oliver French, Brian Smailagic, Asim Siewiorek, Dan Tröster, Gerhard Wearable Computing Lab. ETH Zurich Zurich CH-8092 Switzerland Signal Processing Systems TU Eindhoven MB Eindhoven NL-5600 Netherlands Carnegie Mellon University Pittsburgh PA 15213 United States

ISBN: (纸本)9780769538235

Interaction with mobile devices that are intended for everyday use is challenging since such systems are continuously optimized towards small outlines. Watches are a particularly critical as display size, processing capabilities, and weight are tightly constraint. This work presents a watch device with an integrated gesture recognition interface. We report the resource-optimized implementation of our algorithmic solution on the watch and demonstrate that the recognition approach is feasible for such constraint devoices. The system is wearable during everyday activities and was evaluated with eight users to complete questionnaires through intuitive one-hand movements. We developed a procedure to spot and classify input gestures from continuous acceleration data acquired by the watch. The recognition procedure is based on hidden Markov models (HMM) and was fully implemented on a watch. The algorithm achieved an average recall of 79% at 93% precision in recognizing the relevant gestures. The watch implementation of continuous gesture spotting showed a delay below 3ms for feature computation, Viterbi path processing, and final classification at less than 4KB memory usage. © 2009 IEEE.

关键词： Watches

来源：评论

学校读者我要写书评

暂无评论

Automatic speech recognition technical for Náhuatl language isolated words.

引用

The Journal of the Acoustical Society of America 2010年第4_SUPPLEMENT期128卷 2324-2324页

作者： Sergio Suarez Guerra Jose Luis Oropeza Rodriguez Juan Carlos Flores Paulin Dept. Comput. Eng. Res Lab. of Digital Signal Processing Ctr. for Computing Res Natl. Polytechnic Inst. Juan de Dios Batiz esq. Miguel Othón de Mendizabal s/n P.O. 07038 Mexico

Automatic speech recognition (ASR) represents a great expectative in communications systems where interaction between computers and humans is present. In the last three decades it has been grounded. The use of computer techniques helps people who speak in a native language or with physical limitation to make transactions, leave messages, obtain information, or control some device using voice expressions. This work shows results obtained when using different techniques of ASR into the Náhuatl language. Náhuatl language is a native language spoken in Mexico and is the most important because there are many people speaking it. Náhuatl language has around 49 variants. Preserving language is important because language is the most efficient means of transmitting a culture and it is the owners of that culture who lose the most when the language dies. Mel cepstrum coefficients, vector quantization, and hidden Markov models of continuous density were used. The experiments reported 99% accuracy in ASR on Náhuatl numerals corpus employed. This work represents the first step for implementing an automatic speech recognition translator into Spanish from the Náhuatl language, with closed sentences.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A new population diversity model in swarm intelligence

引用

Journal of Information and Computational Science 2009年第4期6卷 1891-1898页

作者： Feng, Jiqiang Xie, Weixin Xu, Chen Huang, Jianjun Key Lab. for Intelligent Information Processing Shenzhen University Shenzhen 518060 China Institute of Intelligent Computing Science Shenzhen University Shenzhen 518060 China

Many researchers of swarm intelligence (SI) algorithms take their ideas from physical and biological systems. This approach, however, is mostly qualitative and many ideas remain vague and ill-defined. In this paper, a mathematical framework based on probability theory is presented that enables us to analyze one important aspect of SI algorithms: the population diversity. Firstly the population density is defined for the population in the SI algorithms. The population diversity is then discussed from the point of view of the normal distribution in statistics. We show that there is a close connection between the distribution and population diversity and that the essential structure of population diversity is quite similar to that of the distribution. A detailed construction of the population diversity model is then given that is based on probability distributions and the convergence of the model is theoretically discussed for single peak value case. The paper concludes with a generic numerical example that validates the population diversity model. © 2009 Binary Information Press.

关键词： Normal distribution

来源：评论

学校读者我要写书评

暂无评论

A point pattern matching algorithm based on minimize spanning tree and Fiedler vector

A point pattern matching algorithm based on minimize spannin...

引用

1st International Conference on Information Science and Engineering, ICISE2009

作者： Xuan, Shan-Li Liang, Dong Zhu, Ming Fan, Yi Zheng Wang, Nian Key Lab. Intelligent Computing and Signal Ministry of Education Anhui University Hefei 230039 China School of Mathematical Sciences Anhui University Hefei 230039 China School of Computer and Information HeFei University of Technology Hefei 230009 China

ISBN: (纸本)9780769538877

Based on the minimize spanning tree and Fiedler vector, a new feature matching algorithm is proposed in this paper. Firstly, a weighted complete graph is constructed with the feature points of each image respectively, then search the minimal spanning tree in each complete graph. Secondly, perform spectral decomposition on the Gaussian-weighted Laplace matrix of the minimize spanning tree respectively, and divide the feature points into several different sets based on the vector(Fiedler vector) corresponding to the second smallest eigenvalue of Laplace matrix , then the corresponding relation between sets is obtained. And construct Gaussian-weighted Laplace matrices between the corresponding sets, then submit the matrices to spectral decomposition. Finally, complete the feature matching by constructing matching matrix with eigenvalues and eigenvectors. Experiment results indicate that the algorithm has a high accuracy. ©2009 IEEE.

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

Method with the center of graph for point pattern matching

Method with the center of graph for point pattern matching

引用

9th International Conference on Electronic Measurement and Instruments, ICEMI 2009

作者： Xuan, Shanli Liang, Dong Zhu, Ming Fan, Yizheng Wang, Nian Key Lab. Intelligent Computing and Signal Ministry of Education Anhui University Hefei 230039 China School of Computer and Information HeFei University of Technology Hefei 230009 China School of Mathematical Sciences Anhui University Hefei 230039 China

ISBN: (纸本)9781424438624

Based on the center of graph, a point pattern feature matching method is proposed here. Firstly, a weighted complete graph is constructed with the feature points of each image, and then the center of each graph is found respectively. With the vertex sets of the centers, the feature points are divided into several layers according to the distance from the center, and then the corresponding relation between layers is obtained. Secondly, the Gaussian-weighted Laplace matrices are constructed between the corresponding layers. And then the matrices are submitted to singular-value decomposition(SVD). Finally, represent the feature points with eigenvectors obtained from SVD, and then construct matching matrix to obtain the final matching results. Synthetic data and real world data both indicate that our method has a higher accuracy than theirs, and it can deal with the matching problem with more feature points effectively. ©2009 IEEE.

关键词： Singular value decomposition

来源：评论

学校读者我要写书评

暂无评论

Automatic adaptation of annotation standards: Chinese word segmentation and POS tagging - A case study

Automatic adaptation of annotation standards: Chinese word s...

引用

Joint Conference of the 47th Annual Meeting of the Association for Computational Linguistics and 4th International Joint Conference on Natural Language processing of the AFNLP, ACL-IJCNLP 2009

作者： Jiang, Wenbin Huang, Liang Liu, Qun Key Lab. of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences P.O. Box 2704 Beijing 100190 China Google Research 1350 Charleston Rd. Mountain View CA 94043 United States

ISBN: (纸本)9781617382581

Manually annotated corpora are valuable but scarce resources, yet for many annotation tasks such as treebanking and sequence lab.ling there exist multiple corpora with different and incompatible annotation guidelines or standards. This seems to be a great waste of human efforts, and it would be nice to automatically adapt one annotation standard to another. We present a simple yet effective strategy that transfers knowledge from a differently annotated corpus to the corpus with desired annotation. We test the efficacy of this method in the context of Chinese word segmentation and part-of-speech tagging, where no segmentation and POS tagging standards are widely accepted due to the lack of morphology in Chinese. Experiments show that adaptation from the much larger People's Daily corpus to the smaller but more popular Penn Chinese Treebank results in significant improvements in both segmentation and tagging accuracies (with error reductions of 30.2% and 14%, respectively), which in turn helps improve Chinese parsing accuracy. © 2009 ACL and AFNLP.

关键词： Forestry

来源：评论

学校读者我要写书评

暂无评论

Bilingually-constrained (monolingual) shift-reduce parsing

Bilingually-constrained (monolingual) shift-reduce parsing

引用

2009 Conference on Empirical Methods in Natural Language processing, EMNLP 2009, Held in Conjunction with ACL-IJCNLP 2009

作者： Huang, Liang Jiang, Wenbin Liu, Qun Google Research 1350 Charleston Rd. Mountain View CA 94043 United States Key Lab. of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences P.O. Box 2704 Beijing 100190 China

Jointly parsing two languages has been shown to improve accuracies on either or both sides. However, its search space is much bigger than the monolingual case, forcing existing approaches to employ complicated modeling and crude approximations. Here we propose a much simpler alternative, bilingually-constrained monolingual parsing, where a source-language parser learns to exploit reorderings as additional observation, but not bothering to build the target-side tree as well. We show specifically how to enhance a shift-reduce dependency parser with alignment features to resolve shift-reduce conflicts. Experiments on the bilingual portion of Chinese Treebank show that, with just 3 bilingual features, we can improve parsing accuracies by 0.6% (absolute) for both English and Chinese over a state-of-the-art baseline, with negligible (∼6%) efficiency overhead, thus much faster than biparsing. © 2009 ACL and AFNLP.

关键词： Forestry

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：