检索结果-内蒙古大学图书馆

Photonics and Optoelectronics Meetings, POEM 2009 - Fiber Optic Communication and Sensors

作者： Pan, Jianjun Li, Weilai Zhang, Yefang Key Lab. of Fiber Optic Sensing Technology and Information Processing of Ministry of Education Wuhan University of Technology 122 Luoshi Road Wuhan 430070 China Zhongbei Signal Software Company Limited Beijing China

ISBN: (纸本)9780819479037

FBG (Fiber Bragg Grating) sensor is suitable to detect track strain under harsh environment. In order to optimize its detecting efficiency, the key is to find out where the optimal detecting place is. This paper presents an FEA (Finite Element Analysis) method to analyze strain distribution of a track under load. The strain field is decomposed into three vector fields, and the optimal detecting place is determined by analyzing these vector fields. The related experiment and actual aplication verified the authenticity of this method. © 2009 Copyright SPIE - The International Society for Optical Engineering.

关键词： Finite element method

来源：评论

学校读者我要写书评

暂无评论

Textural Adaptive Learning-Based Super Resolution for Human Face Images

Textural Adaptive Learning-Based Super Resolution for Human ...

引用

Congress on Image and signal processing, CISP

作者： Yang Cao Xiaoguang Li Zhuo Li Lansun Shen Signal & Information Processing Lab. Beijing University of Technology Beijing China

A low-resolution face image is segmented into detailed regions and flat regions. The detailed regions are super resolved using classified predictors according to the local textural structures, while, the flat regions are magnified using bilinear interpolation. Experimental results show that both the visual quality and the computational cost are improved.

关键词： Image resolution Humans Face detection Mouth signal resolution Eyes Nose Image reconstruction Computational efficiency Interpolation

来源：评论

学校读者我要写书评

暂无评论

Noise reduction algorithm for robust speech recognition using MLP neural network

Noise reduction algorithm for robust speech recognition usin...

引用

2009 2nd Asia-Pacific Conference on Computational Intelligence and Industrial Applications, PACIIA 2009

作者： Ghaemmaghami, Masoumeh P. Razzazi, Farbod Sameti, Hossein Dabbaghchian, Saeed BabaAli, Bagher Department of Electrical Engineering Science and Research Branch Azad University Tehran Iran Speech Processing Lab. Department of Computer Engineering Sharif University of Technology Tehran Iran

ISBN: (纸本)9781424446070

We propose an efficient and effective nonlinear feature domain noise suppression algorithm, motivated by the minimum mean square error (MMSE) optimization criterion. Multi Layer Perceptron (MLP) neural network in the log spectral domain minimizes the difference between noisy and clean speech. By using this method as a pre-processing stage of a speech recognition system, the recognition rate in noisy environments is improved. We can extend the application of the system to different environments with different noises without re-training it. We need only to train the preprocessing stage with a small portion ofnoisy data which is created by artificially adding different types of noises from the NOISEX-92 database to the TIMIT speech database. Experimental results show that the proposed method can achieve significant improvement ofrecognition rates. ©2009 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Improving nominal SRL in Chinese language with verbal SRL information and automatic predicate recognition

Improving nominal SRL in Chinese language with verbal SRL in...

引用

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

作者： Li, Junhui Zhou, Guodong Zhao, Hai Zhu, Qiaoming Qian, Peide Jiangsu Provincial Key Lab. for Computer Information Processing Technologies School of Computer Science and Technology Soochow University Suzhou 215006 China Department of Chinese Translation and Linguistics City University of HongKong Hong Kong

This paper explores Chinese semantic role lab.ling (SRL) for nominal predicates. Besides those widely used features in verbal SRL, various nominal SRL-specific features are first included. Then, we improve the performance of nominal SRL by integrating useful features derived from a state-of-the-art verbal SRL system. Finally, we address the issue of automatic predicate recognition, which is essential for a nominal SRL system. Evaluation on Chinese NomBank shows that our research in integrating various features derived from verbal SRL significantly improves the performance. It also shows that our nominal SRL system much outperforms the state-of-the-art ones. © 2009 ACL and AFNLP.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

SAR image despeckling based on edge detection and nonsubsampled second generation bandelets

引用

Journal of Systems Engineering and Electronics 2009年第3期20卷 519-526页

作者： Zhang Wenge~(1,2),Liu Fang~(1,2),Jiao Licheng~(2,3)& Gao Xinbo~(2,3) 1.School of computer Science and technology,Xidian Univ.,Xi’an 710071,P.R.China 2.Key lab.of Intelligent Perception and Image Understanding of Ministry of Education of China,Xi’an 710071,P.R.China 3.Inst,of Intelligent Information processing,Xidian Univ.,Xi’an 710071,P.R.China School of Computer Science and Technology Xidian Univ. Xi'an 710071 P. R. China Key Lab. of Intelligent Perception and Image Understanding of Ministry of Education of China Xi'an 710071 P. R. China Key Lab. of Intelligent Perception and Image Understanding of Ministry of Education of China Xi'an 710071 P. R. China Inst. of Intelligent Information Processing Xidian Univ. Xi'an 710071 P. R. China

To preserve the sharp features and details of the synthetic aperture radar （SAR） image effectively when despeckling, a despeckling algorithm with edge detection in nonsubsampled second generation bandelet transform （NSBT） domain is proposed. First, the Canny operator is utilized to detect and remove edges from the SAR image. Then the NSBT which has an optimal approximation to the edges of images and a hard thresholding rule are used to approximate the details while despeckling the edge-removed image. Finally, the removed edges are added to the reconstructed image. As the edges axe detected and protected, and the NSBT is used, the proposed algorithm reaches the state-of-the-art effect which realizes both despeckling and preserving edges and details simultaneously. Experimental results show that both the subjective visual effect and the mainly objective performance indexes of the proposed algorithm outperform that of both Bayesian wavelet shrinkage with edge detection and Bayesian least square-Gaussian scale mixture （BLS-GSM）.

关键词： computer image processing synthetic aperture radar speckle edge detection nonsubsampled second generation bandelet transform Canny operator threshold shrinkage.

来源：评论

学校读者我要写书评

暂无评论

Doppler ambiguity resolving for SAR ground fast moving target indication

Doppler ambiguity resolving for SAR ground fast moving targe...

引用

2009 Asia-Pacific Conference on Synthetic Aperture Radar, APSAR 2009

作者： Qian, Jiang Wang, Yu Li, Lianghai Xing, Mengdao Li, Bingning National Key Lab. of Radar Signal Processing Xidian Univ. Xi'an 710071 China 704Th Institute of China Aerospace Science and Technology Corporation Beijing 100076 China PLA 61191 Hangzhou 310023 China

ISBN: (纸本)9781424427314

This paper investigates the restrictions of Synthetic Aperture Radar (SAR) ground fast moving target indication based on the conventional clutter suppression method in image domain which ignores the problems of range cell migration (RCM) and azimuth defocus. A technique for fast moving target indication and motion parameter estimation is proposed based on Doppler ambiguity resolving. In range frequency and compressed azimuth time domain of tri-channel SAR/GMTI data, the clutter is suppressed with DPCA technique, and the Doppler ambiguity number can be estimated from the residual signal using Radon transform. This approach exploits the relation between the line slope and the Doppler ambiguity number of fast moving target. Azimuth focusing is carried out with the criterion of entropy-minimization after azimuth cell migration correction (ACMC), and at last the fast moving target is imaged after range compression. The feasibility of the approach is validated by the real airborne data. ©2009 IEEE.

关键词： Synthetic aperture radar

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

Image retrieval based on character-matching technology

Image retrieval based on character-matching technology

引用

5th International Conference on Information Assurance and Security, IAS 2009

作者： Shan, Zhao Jing, Liu School of Computer Science and Technology Henan Polytechnic University Jiaozuo 454003 China Jiangsu Province Key Lab. on Image Processing and Image Communication Nanjing University of Posts and Communication Nanjing 210003 China

ISBN: (纸本)9780769537443

In order to introduce effective text-retrieval technologies into content-based image retrieval, a novel method based on string-matching technology was presented incorporating the different sensitivity along variant directions of human visual system. The image is firstly divided into non-overlapped blocks and sub-feature is extracted according to the human visual feature. Then, a novel descriptor is defined. Based on which, the sub-features is mapping into characters and the image into the text. Finally, the technology of the character string matching is adopted as the similarity measurement. Meantime, the situation information of character is considered, an adjusted method is proposed. Experimental results show that the proposed method has sound and robust retrieval performance. © 2009 IEEE.

关键词： Content based retrieval

来源：评论

学校读者我要写书评

暂无评论

Highly stable bottom-gate nanocrystalline silicon thin film transistor fabricated employing ICP-CVD

Highly stable bottom-gate nanocrystalline silicon thin film ...

引用

Thin Film Transistors 9, TFT 9 - 214th ECS Meeting

作者： Kim, Sun-Jae Han, Sang-Myeon Kwon, Jang-Yeon Jung, Ji-Sim Hana, Min-Koo Department of Electrical Engineering and Computer Science Seoul National University Seoul 151-741 Korea Republic of Display Device and Processing Lab. Samsung Advanced Institute of Technology Yong-In 446-712 Korea Republic of

ISBN: (纸本)9781566776554

Bottom-gate nanocrystalline silicon (nc-Si) thin film transistors (TFTs) were fabricated and evaluated their characteristics and electrical stability under various stress condition. nc-Si with high crystallinity was deposited employing Inductively coupled plasma chemical vapor deposition(ICP-CVD) system. We employed helium gas diluted deposition and all the process temperature was kept under 350°C. We fabricated conventional inverted-staggered nc-Si TFTs. Fabricated nc-Si TFTs showed fine electrical characteristics, such as electrical mobility of 0.64-0.77 cm2/***. We investigated its stability through constant-voltage stress and constant-current stress. The threshold voltage shift after 30, 000 seconds gate bias (10V) stress was only 0.098V, which is considerably less compared to a-Si:H TFT. Under the static current stress condition, the threshold voltage of the nc-Si TFT was shifted less than that of a-Si:H TFT. It demonstrates that nc-Si TFT exhibit better stability than conventional a-Si:H TFT. ©The Electrochemical Society.

关键词： Thin film transistors

来源：评论

学校读者我要写书评

暂无评论

Image retrieval based on bit-plane distribution feature

Image retrieval based on bit-plane distribution feature

引用

6th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2009

作者： Shan, Zhao Jing, Lui School of Computer Science and Technology Henan Polytechnic University Jiaozuo 454003 China Jiangsu Prov. Key Lab. on Image Processing and Image Communication Nanjing University of Posts and Communication Nanjing 210003 China

ISBN: (纸本)9780769537351

Based on the analysis of color histogram for image retrieval, a new descriptor, bit-plane distribution feature(BPDF), is proposed in this paper. The image is firstly divided into eight bit-planes. Meantime, the Gray code of bit-planes is used to avoid the effect of changes in the intensity values on bit-planes. Then, according to the distribution of each bit-plane, a feature vector is constructed by the first four significant planes which contain most of the structural information of the image. Finally, the Mahalanobis distance is adopted to measure the similarity because of the correlation between the concerned vectors after designing a correlation-weighted matrix. Comparisons are conducted between BPDF and other descriptors. Experimental results show that the proposed method provides more significantly retrieval results than the traditional ones. © 2009 IEEE.

关键词： Image retrieval

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：