检索结果-内蒙古大学图书馆

International Conference on Multimedia Technology

作者： Liao, Liang Zhang, Yanning Zhang, Chao Shaanxi Provincial Key Laboratory of Speech and Image Information Processing Northwestern Polytechnical University Xi'an 710072 China School of Electronic and Information Engineering Zhongyuan University of Technology Zhengzhou 450007 China

ISBN: (纸本)9781612847740

We consider the feature extraction problem based on compressive sampling for supervised image classification. Inspired by recently emerged 1D compressive sampling (1DCS) and 2DPCA techniques, a novel 2D compressive sampling method, called 2DCS, using two random underdetermined projections, is proposed. 2DCS data could be effectively used for pattern representation. Moreover, original data could be exactly reconstructed from 2DCS compression. The proposed method is efficient for feature extraction and data compression, and, compared with 1DCS and 2DPCA, requires lower computational complexity. Combined with the sophisticated classifiers, the efficacy of supervised image classification could be improved. Experimental results show the superiorities of the proposed algorithm. © 2011 IEEE.

关键词： image classification

来源：评论

学校读者我要写书评

暂无评论

image classification via nearest subspace and two-dimensional underdetermined random projection

Image classification via nearest subspace and two-dimensiona...

引用

2012 7th IEEE Conference on Industrial Electronics and Applications, ICIEA 2012

作者： Liu, Zhoufeng Liao, Liang Zhang, Yanning School of Electronic and Information Engineering Zhongyuan University of Technology Zhengzhou 450007 China Shaanxi Provincial Key Laboratory of Speech and Image Information Processing Northwestern Polytechnical University Xi'an 710072 China

ISBN: (纸本)9781457721175

We consider the problem of classification via two-dimensional underdetermined random projection and sparse representation. We contend that the two-dimensional underdetermine random projection has a natural relationship with deterministic underdetermined projections, such as 2DPCA and (2D) 2PCA but is more efficient in terms of the computational complexity for feature extraction. The proposed projection technique, called 2DCS, can be regarded as an extension of the compressive sampling technique which conveniently employs the same 1- norm minimization technique for exact data reconstruction. The proposed method can be favorably used for feature extraction in pattern recognition. Due to its computational efficiency and independence on training data, 2DCS feature has its own advantages for image classification. Our experiments on the publicly available ORL database have shown the effectiveness of the proposed method. © 2012 IEEE.

关键词： image classification

来源：评论

学校读者我要写书评

暂无评论

Error concealment for stereoscopic images using boundary smooth degree

Error concealment for stereoscopic images using boundary smo...

引用

Asia-Pacific Conference on communications

作者： Guijin Tang Xiuchang Zhu Jiangsu Key Laboratory of Image Processing & Image Communication Nanjing University of Posts and Telecommunications Nanjing China

ISBN: (纸本)9781424447848

Error concealment can be regarded as a sort of error resilient coding techniques. This paper proposes a method to recover lost blocks in stereoscopic images. We first utilize the correlation to perform disparity estimation to match the corresponding blocks for lost ones. And then we calculate the boundary smooth degree (BSD) for each recovered block. If BSD exceeds the threshold, it means that the boundary is discontinuous which mainly results from high detailed blocks, edge blocks or occluded blocks. So we consider neighboring blocks' BSD and estimate the content of a lost block, and adaptively use different methods to conceal it. Experimental results show that the proposed algorithm can greatly improve the subjective and objective quality of the reconstructed image.

关键词： Loss measurement image coding image reconstruction Video sequences image processing image communication Feedback Layout Video coding Newton method

来源：评论

学校读者我要写书评

暂无评论

Wideband and Replaceable Cylindrical Dielectric Resonator Antennas

Wideband and Replaceable Cylindrical Dielectric Resonator An...

引用

IEEE MTT-S International Microwave Workshop Series on Advanced Materials and Processes for RF and THz Applications (IMWS-AMP)

作者： Ling Peng Weng Xiao Sheng Fang Jing Yan Kang Ping Shi Guangdong Provincial Key Laboratory of Digital Signal and Image Processing Shantou China

ISBN: (数字)9781728160641

ISBN: (纸本)9781728160658

A wideband and replaceable dielectric resonant antenna (DRA) excited by a probe is investigated. The proposed wideband DRA consists of a probe platform and a solid cylindrical dielectric resonator, and two magnets are applied to fix them. In this way, the dielectric resonator can be easily replaced. Therefore, three kinds of wideband DRAs with impedance bandwidth of 35.8%, 56.6% and 74% are designed. The reflection coefficient, radiation mode and antenna gain of the cylindrical DRA were analyzed by using HFSS ANSYS.

关键词： Dielectrics Wideband Dielectric resonator antennas Frequency measurement Antenna measurements Gain measurement

来源：评论

学校读者我要写书评

暂无评论

MRI image segmentation based on fast kernel clustering analysis

引用

Frontiers of Electrical and Electronic Engineering in China 2011年第2期6卷 363-373页

作者： Liang LIAO Yanning ZHANG Shaanxi Provincial Key Laboratory of Speech and Image Information Processing(SAIIP) School of Computer ScienceNorthwestern Polytechnical UniversityXi’an 710129China School of Electric and Information Engineering Zhongyuan University of TechnologyZhengzhou 450007China

Kernel-based clustering is supposed to provide a better analysis tool for pattern classification,which implicitly maps input samples to a highdimensional space for improving pattern *** this implicit space map,the kernel trick is believed to elegantly tackle the problem of“curse of dimensionality”,which has actually been more challenging for kernel-based clustering in terms of computational complexity and classification accuracy,which traditional kernelized algorithms cannot effectively deal *** this paper,we propose a novel kernel clustering algorithm,called KFCM-III,for this problem by replacing the traditional isotropic Gaussian kernel with the anisotropic kernel formulated by Mahalanobis ***,a reduced-set represented kernelized center has been employed for reducing the computational complexity of KFCM-I algorithm and circumventing the model deficiency of KFCM-II *** proposed KFCMIII has been evaluated for segmenting magnetic resonance imaging(MRI)*** this task,an image intensity inhomogeneity correction is employed during image segmentation *** a scheme called preclassification,the proposed intensity correction scheme could further speed up image *** experimental results on public image data show the superiorities of KFCM-III.

关键词： kernel-based clustering dimensionality reduction speeding-up scheme magnetic resonance imaging(MRI)image segmentation intensity inhomogeneity correction

来源：评论

学校读者我要写书评

暂无评论

A nowcasting model for the prediction of typhoon tracks based on a long short term memory neural network

引用

Acta Oceanologica Sinica 2018年第5期37卷 8-12页

作者： GAO Song ZHAO Peng PAN Bin LI Yaru ZHOU Min XU Jiangling ZHONG Shan SHI Zhenwei North China Sea Marine Forecasting Center of State Oceanic Administration State Oceanic Administration Qingdao 266061 China Shandong Provincial Key Laboratory of Marine Ecological Environment and Disaster Prevention and Mitigation Qingdao 266061 China Image Processing Center School of Astronautics Beihang University Beijing 100191 China

It is of vital importance to reduce injuries and economic losses by accurate forecasts of typhoon tracks. A huge amount of typhoon observations have been accumulated by the meteorological department, however, they are yet to be adequately utilized. It is an effective method to employ machine learning to perform forecasts. A long short term memory（LSTM） neural network is trained based on the typhoon observations during 1949–2011 in China＇s Mainland, combined with big data and data mining technologies, and a forecast model based on machine learning for the prediction of typhoon tracks is developed. The results show that the employed algorithm produces desirable 6–24 h nowcasting of typhoon tracks with an improved precision.

关键词： typhoon tracks machine learning LSTM big data

来源：评论

学校读者我要写书评

暂无评论

A brief analysis about boundary region partition reduction standard

A brief analysis about boundary region partition reduction s...

引用

2007 Workshop on Intelligent Information Technology Application, IITA 2007

作者： Du, Weifeng Yue, Guangxue Cheng, Xu School of Information Engineering Jiaxing University Jiaxing 314001 China School of Computer and Communication Hunan University Changsha 410000 China Provincial Key Lab. of Image Processing and Imagecom Communication Nanjing University of Pos and Telecommunications Nanjing 210003 China

ISBN: (纸本)076953063X

In his paper, Prof. Ye Dongyi pointed out that the reduction approach introduced by Hu Xiaohua etc. will give wrong result in some situation. In this paper we come to a conclusion by analysis that the reduction approach is to keep boundary region partition unchangeable virtually. It is just different from the reduction approach given by Ye Dongyi. Then, we analyze the logic characteristic of boundary region partition reduction standard. © 2007 IEEE.

关键词： data reduction formal logic rough set theory boundary region partition reduction standard logic characteristics Rough set theory Formal logic data reduction boundary regions

来源：评论

学校读者我要写书评

暂无评论

Content-Adaptive Interpolation for Spatial Error Concealment

Content-Adaptive Interpolation for Spatial Error Concealment

引用

International Conference on Information and Computing Science, ICIC

作者： Hua-yan Luo Zong-liang Gan Xiu-chang Zhu Jiangsu Province Key Laboratory on Image Processing & Image Communication Nanjing University of Posts and Telecommunications Nanjing China

When transmitting encoded images over a communication channel, the reconstructed image quality can be substantially degraded by channel errors. This paper presents a spatial error concealment algorithm that utilizes variance of surrounding pixels, and then classifies each error block (EB) into two categories: uniform block and edge block. For uniform block, nearest border prior spatial interpolation is adopted to restore missing pixels. We use the Wiener interpolation algorithm and special interpolation sequence for edge block. Experimental results indicate the proposed algorithm can attain well restored quality of intra-frames both subjectively and objectively. Meanwhile, the computational cost of the proposed algorithm can be significantly reduced, compared to Lipsilas method. And the restored quality is almost the same, sometimes even much better.

关键词： Interpolation image reconstruction image quality image restoration Video compression Telecommunication computing Gallium nitride image processing image communication Electronic mail

来源：评论

学校读者我要写书评

暂无评论

Dual-microphone noise reduction based on semi-blind DUET

Dual-microphone noise reduction based on semi-blind DUET

引用

International Symposium on Chinese Spoken Language processing

作者： Zhong-Hua Fu Lei Xie Domg-Mei Jiang Shaanxi Provincial Key Laboratory of Speech and Image Information Processing Northwestern Polytechnical University Xi'an Shaanxi Provincial Key Laboratory of Speech and Image Information Processing Northwestern Polytechnical University Xi'an China

Noise reduction is a fundamental requirement of many speech applications. Sometimes the major interferences, such as music, song, cross-talking, etc., coming from loudspeakers nearby make it a more challenging problem. In this paper, by supposing the locations of interferences are fixed, a semi-blind Degenerate Unmixing Estimation Technique (DUET) approach using dual-microphone is proposed. Firstly, during system initialization, the spatial feature distribution of the interferences is estimated precisely. Then the feature distribution of unknown target speech is obtained using model adaptation. Finally, a time-frequency binary mask estimated based on likelihood comparison is used to separate the target speech. The experimental results show that the performances of our approach in adverse noise reduction are significant. 77.9% interferences are eliminated and the speech quality is preserved very well. The results are close to those of un-blind approach, where the locations of all sound sources are known.

关键词： Speech

来源：评论

学校读者我要写书评

暂无评论

Quantitative Analysis of Reconstructed Conductivity images Using Phase-based Electrical Properties Method at 3T MR 8

Quantitative Analysis of Reconstructed Conductivity Images U...

引用

8th IEEE R10 Humanitarian Technology Conference, R10-HTC 2020

作者： Sun, Xiangdong Lu, Lijun Zhang, Shuangyang Qi, Li Liu, Xiaoyun Chen, Wufan University of Electronic Science and Technology of China School of Automation Engineering Chengdu China Southern Medical University Guangdong provincial key laboratory of medical image processing School of Biomedical Engineering Guangzhou China

ISBN: (纸本)9781728111100

The phase-based electrical properties tomography (EPT) derives the distribution of tissue's conductivity using radi of requency phase information of magnetic resonance, which can be obtained by standard MR sequences. However, this method depends on the assumption that the conductivity value is much larger than the product of Larmor frequency and permittivity. In this study, we investigate the validity of this assumption under different electrical properties (EPs) distribution, which is conductivity and permittivity. This study simulates the birdcage coil loaded with a homogeneous phantom and obtains the simulation phase data with varied EPs. We calculate the reconstructed errors of conductivity images using the phase-based method and then analyze the relationship between these errors with EPs distribution. This work indicates that the suitable range of EPs is 2ωϵ © 2020 IEEE.

关键词： Magnetic resonance imaging

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：