检索结果-内蒙古大学图书馆

2012 IEEE 11th International Conference on Signal processing(ICSP 2012)

作者： Tianliang Liu Liang Wang Xiuchang Zhu Jiangsu Provincial Key Lab of Image Processing and Image Communication College of Telecommunications and Information Engineering Nanjing University of Posts and Telecommunications

ISBN: (纸本)9781467321969

This paper proposes a global stereo correspondence using robust matching likelihoods and minimum spanning tree （MST） leveraged smooth priors in a probabilistic graphical model framework. The matching likelihoods of the stereo correspondence can be robustly constructed as data term by aggregating initial matching costs from Weber local descriptors using an unsymmetrical guided filtering in a linear model. The disparity priors are devised as smooth term to characterize the smoothness constraints leveraged by the MST structure. The presented stereo approach provides an effective and efficient way to reflect robust visual dissimilarity and resolve local and regional discontinuities. Experiments demonstrate that the proposed global stereo matching method can produce piecewise smooth, accurate and dense disparity map, while removing effectively the visual ambiguity of the stereo matching problem.

关键词： stereo vision Markov random field Weber descriptor minimun spanning tree QPBO optimization

来源：评论

学校读者我要写书评

暂无评论

pNovo+: De Novo Peptide Sequencing and Assembly Using Complementary HCD and ETD Tandem Mass Spectra

pNovo+: De Novo Peptide Sequencing and Assembly Using Comple...

引用

第八届中国蛋白质组学大会

作者： Hao Chi Haifeng Chen Kun He Long Wu Bing Yang Rui-Xiang Sun Jianyun Liu Wen-Feng Zeng Chun-Qing Song Si-Min He Meng-Qiu Dong Key Lab of Intelligent Information Processing Institute of Computing TechnologyChinese Academy of SciencesBeijing 100190China National Institute of Biological SciencesBeijingBeijing 102206China Laboratory of Intelligent Recognition and Image ProcessingBeijing Key Laboratory of Digital MediaBeihang UniversityBeijing100191China

来源：评论

学校读者我要写书评

暂无评论

Hybrid Deep Neural Network--Hidden Markov Model (DNN-HMM) Based Speech Emotion Recognition

Hybrid Deep Neural Network--Hidden Markov Model (DNN-HMM) Ba...

引用

International Conference on Affective Computing and Intelligent Interaction and Workshops, ACII

作者： Longfei Li Yong Zhao Dongmei Jiang Yanning Zhang Fengna Wang Isabel Gonzalez Enescu Valentin Hichem Sahli VUB-NPU Joint AVSP Research Lab Northwestern Polytechnical University Xi'an China Shaanxi Provincial Key Lab on Speech and Image Information Processing VUB-NPU Joint AVSP Research Lab Vrije Universiteit Brussel Brussels Belgium Electronics & Informatics Department

Deep Neural Network Hidden Markov Models, or DNN-HMMs, are recently very promising acoustic models achieving good speech recognition results over Gaussian mixture model based HMMs (GMM-HMMs). In this paper, for emotion recognition from speech, we investigate DNN-HMMs with restricted Boltzmann Machine (RBM) based unsupervised pre-training, and DNN-HMMs with discriminative pre-training. Emotion recognition experiments are carried out on these two models on the eNTERFACE'05 database and Berlin database, respectively, and results are compared with those from the GMM-HMMs, the shallow-NN-HMMs with two layers, as well as the Multi-layer Perceptrons HMMs (MLP-HMMs). Experimental results show that when the numbers of the hidden layers as well hidden units are properly set, the DNN could extend the labeling ability of GMM-HMM. Among all the models, the DNN-HMMs with discriminative pre-training obtain the best results. For example, for the eNTERFACE'05 database, the recognition accuracy improves 12.22% from the DNN-HMMs with unsupervised pre-training, 11.67% from the GMM-HMMs, 10.56% from the MLP-HMMs, and even 17.22% from the shallow-NN-HMMs, respectively.

关键词： Hidden Markov models Emotion recognition Training Speech recognition Speech Databases Neural networks

来源：评论

学校读者我要写书评

暂无评论

Stereo matching using aggregated likelihood and multi-scale prior

Stereo matching using aggregated likelihood and multi-scale ...

引用

2012 3rd IEEE/IET International Conference on Audio, Language and image processing, ICALIP 2012

作者： Wang, Liang Liu, Tianliang Zhu, Xiuchang Jiangsu Provincial Key Lab. of Image Processing and Image Communication Nanjing University of Posts and Telecommunications Nanjing 210003 China

ISBN: (纸本)9781467301718

This paper proposes a novel global stereo matching method using aggregated likelihoods and multi-scale priors. The likelihoods of dense stereo correspondences as data term can be robustly expressed by aggregated matching costs based on Weber feature descriptors in an asymmetrical linear filtering model. The multi-scale priors on disparity surface are designed to capture scene smooth term from larger neighborhood besides 4-connected neighborhood. The presented stereo approach being relatively simple does not rely on image segmentation and any scene semantic analysis. Experiments demonstrate that the proposed stereo matching algorithm can produce the dense smooth disparity results comparable to those of excellent stereo matching techniques. © 2012 IEEE.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

NiuTrans: An open source toolkit for phrase-based and syntax-based machine translation 50

NiuTrans: An open source toolkit for phrase-based and syntax...

引用

50th Annual Meeting of the Association for Computational Linguistics, ACL 2012

作者： Xiao, Tong Zhu, Jingbo Zhang, Hao Li, Qiang Natural Language Processing Lab Northeastern University Key Laboratory of Medical Image Computing Ministry of Education

ISBN: (纸本)9781937284275

We present a new open source toolkit for phrase-based and syntax-based machine translation. The toolkit supports several state-of-the-art models developed in statistical machine translation, including the phrase-based model, the hierachical phrase-based model, and various syntax-based models. The key innovation provided by the toolkit is that the decoder can work with various grammars and offers different choices of decoding algrithms, such as phrase-based decoding, decoding as parsing/tree-parsing and forest-based decoding. Moreover, several useful utilities were distributed with the toolkit, including a discriminative reordering model, a simple and fast language model, and an implementation of minimum error rate training for weight tuning. © 2012 Association for Computational Linguistics

关键词： Machine translation

来源：评论

学校读者我要写书评

暂无评论

Prediction of tourists flow distribution based on transition probability matrix

Prediction of tourists flow distribution based on transition...

引用

8th International Conference on Information Science and Digital Content Technology, ICIDT 2012

作者： Hu, Yuting Xie, Rong Zhang, Wenjun Xu, Yi Institute of Image Communication and Information Processing Shanghai Digital Media Processing and Transmission Key Lab. Shanghai Jiaotong University Shanghai China

ISBN: (纸本)9788988678695

A new prediction algorithm of tourists flow distribution based on transition probability matrix (TPM) is proposed in this paper. In order to analyze the visitor transition-behavior and the tourists distribution model, the tourists flow distribution of 5 zones at Shanghai Expo site is predicted based on the TPM, which is estimated by use of multivariate linear regression in optimization. The extensive experimental results verify the efficiency and the correctness of the proposed algorithm over the wavelet neural network prediction method. © 2012 AICIT.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A robust homography estimation method based on keypoint consensus and appearance similarity

A robust homography estimation method based on keypoint cons...

引用

2012 13th IEEE International Conference on Multimedia and Expo, ICME 2012

作者： Yan, Qing Xu, Yi Yang, Xiaokang Institute of Image Communication and Information Processing Shanghai Key Lab. of Digital Media Processing and Transmition Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9781467316590

In this paper, a robust homography estimation method is proposed to match multiview images in the uncalibrated case. This method formulates a new loss function to verify homography hypothesis, which combines models of key-point consensus and appearance similarity. In the consensus model, Lap lace distribution is exploited to better characterize the imprecision of key points. And in the appearance model, a truncated exponential function is utilized to represent the distribution of image similarity values. With these improvements, our method can be more robust in complex situations when a rather high percentage of key points are ambiguous and unreliable, and can output a more accurate homography that satisfies most pixels' geometric relationship. The experimenttal results highlight the robustness and accuracy of our method in the matching tasks of both synthetic images and real life photos. © 2012 IEEE.

关键词： Exponential functions

来源：评论

学校读者我要写书评

暂无评论

Clearance of flight control law based on H-infinity theory

Clearance of flight control law based on H-infinity theory

引用

2012 International Conference on Modelling, Identification and Control, ICMIC 2012

作者： Dong, Shuai Wang, Zhishen Liu, Lei Ou, Liuli Wang, Yongji Key Lab for Image Processing and Intelligent Control Department of Control Science and Engineering Huazhong University of Science and Technology 1037 Luoyu Road Wuhan China

ISBN: (纸本)9780956715715

The H approach is used for the clearance of flight control laws when some parameters in the flight control system vary in a certain range. The proposed H approach is developed from general H theory and is applied to the clearance of a flight control law for a missile. Based on bounded real lemma, two theorems about clearance are deduced, and the clearance problem is transformed to a general linear matrix inequality problem. A BTT missile is chosen as an example to test the proposed method. The simulation result shows that the proposed method is convenient and efficient. © 2012 Huazhong Univ of Sci & Tec.

关键词： Flight control systems

来源：评论

学校读者我要写书评

暂无评论

Adaptive correlation noise model based Wyner-Ziv distributed video coding

International Journal of Digital Content Technology and its ...

引用

International Journal of Digital Content Technology and its Applications 2012年第14期6卷 456-468页

作者： Xiaofei, Hu Xiuchang, Zhu Key Lab of Image Processing and Image Communication College of Geography and Biological Information Nanjing University of Posts and Telecommunications Nanjing 210003 China Key Lab of Image Processing and Image Communication Key Lab ofBroadband Wireless Communication and Sensor Network Technology Nanjing University of Posts and Telecommunications Ministry of Education Nanjing 210003 China

Distributed video coding (DVC) is a novel video coding paradigm. One approach to DVC is Wyner-Ziv distributed video coding. The accuracy of the correlation noise model can influence the performance of the video coder directly. In order to enhance the accuracy of the distribution model, EM algorithm based mixture Laplace-uniform distribution model and basic Laplace-uniform distribution model for DCT alternating current coefficients are established. Then the model is selected adaptively using fuzzy inference. Experimental results suggest that the proposed mixture correlation noise model can describe the heavy tail and sudden change of the noise accurately at high rate and make significant improvement on the coding efficiency compared with the DISCOVER's noise model. Meanwhile, fuzzy inference based adaptive noise model selection method can reduce the operation complexity to some extent, while not influencing rate-distortion performance.

关键词： image coding

来源：评论

学校读者我要写书评

暂无评论

image demosaicing by non-local similarity and local correlation

Image demosaicing by non-local similarity and local correlat...

引用

International Conference on Signal processing Proceedings (ICSP)

作者： Guo-gang Wang Xiu-chang Zhu Zong-liang Gan Province Key Lab on Image Processing and Image Communication Nanjing University of Posts and Telecommunications Nanjing China

Conventional single-chip digital cameras use color filter arrays(CFA) to sample different spectral components. image demosaicing is a problem of interpolating these data to complete red, green, and blue values for each image pixel, to produce an RGB image. Many color demosaicing(CDM) methods assume that the high local spatial redundancy exists among the color samples. Such an assumption, however, may be fail for images with high color saturation and sharp color transitions. This paper presents an adaptive demosaicing algorithm by exploiting both the non-local similarity and the local correlation(NLS-LC) in the color filter array image. First, the most flattest nonlocal image patches are searched in the searching window centered on the estimated pixel. Second, the patch, which is the most similar to the current patch, is selected among the most smoothest nonlocal patches. Third, according to the similar degree and the local correlation degree, the obtained nonlocal image patch and the current patch are adaptively chosen to estimate the missing color samples. Experimental results indicate that the proposed method exhibits superior performance over many state-of-the-art color interpolation methods.

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：