检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

1,495 篇 会议
653 篇 期刊文献
9 册 图书

馆藏范围

2,157 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,419 篇 工学
- 815 篇 计算机科学与技术...
- 696 篇 软件工程
- 298 篇 信息与通信工程
- 213 篇 机械工程
- 206 篇 控制科学与工程
- 198 篇 光学工程
- 156 篇 生物工程
- 152 篇 生物医学工程（可授...
- 136 篇 电子科学与技术（可...
- 112 篇 电气工程
- 98 篇 仪器科学与技术
- 62 篇 化学工程与技术
- 41 篇 交通运输工程
- 32 篇 土木工程
- 28 篇 建筑学
- 27 篇 航空宇航科学与技...
- 24 篇 材料科学与工程（可...
- 24 篇 安全科学与工程
772 篇 理学
- 464 篇 数学
- 252 篇 物理学
- 173 篇 生物学
- 143 篇 统计学（可授理学、...
- 60 篇 化学
- 57 篇 系统科学
264 篇 管理学
- 147 篇 管理科学与工程(可...
- 128 篇 图书情报与档案管...
86 篇 医学
- 75 篇 临床医学
- 57 篇 基础医学(可授医学...
- 46 篇 药学(可授医学、理...
29 篇 艺术学
- 28 篇 设计学（可授艺术学...
28 篇 法学
20 篇 农学
11 篇 经济学
10 篇 军事学
9 篇 教育学
5 篇 文学
1 篇 哲学
1 篇 历史学

主题

215 篇 pattern recognit...
197 篇 image processing
134 篇 image segmentati...
134 篇 feature extracti...
78 篇 computer vision
77 篇 shape
68 篇 support vector m...
67 篇 robustness
65 篇 face recognition
65 篇 image reconstruc...
59 篇 cameras
54 篇 principal compon...
53 篇 image analysis
52 篇 image edge detec...
52 篇 image recognitio...
51 篇 training
48 篇 humans
47 篇 object detection
39 篇 data mining
38 篇 pixel

机构

265 篇 institute of ima...
242 篇 institute of ima...
74 篇 image processing...
43 篇 institute of ima...
39 篇 institute of ima...
30 篇 institute of ima...
26 篇 institute of med...
23 篇 school of inform...
21 篇 institute of ima...
21 篇 pattern recognit...
19 篇 institute for pa...
19 篇 inst. of image p...
18 篇 intelligent reco...
18 篇 state key labora...
17 篇 key laboratory o...
17 篇 laboratory of in...
17 篇 institute of ima...
16 篇 department of au...
16 篇 school of softwa...
16 篇 key laboratory o...

作者

195 篇 yang jie
138 篇 jie yang
68 篇 ping guo
58 篇 yuncai liu
54 篇 huang xiaolin
46 篇 pengfei shi
34 篇 yunhong wang
33 篇 zhang tianxu
32 篇 kropatsch walter...
31 篇 guo ping
25 篇 qian yin
25 篇 zhou yue
25 篇 wang yunhong
24 篇 wang lisheng
22 篇 liu jian
21 篇 liu yuncai
20 篇 hong-bin shen
20 篇 杨杰
20 篇 shi pengfei
19 篇 h. bischof

语言

1,963 篇 英文
112 篇 其他
86 篇 中文

检索条件"机构=Pattern Recognition and Image Processing Processing Laboratory"

共 2157 条记录，以下是1141-1150 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Tensor error correction for corrupted values in visual data

Tensor error correction for corrupted values in visual data

引用

IEEE International Conference on image processing

作者： Yin Li Yue Zhou Junchi Yan Jie Yang Xiangjian He Institute of Image Processing & Pattern Recognition Shanghai Jiaotong University China Faculty of Engineering and Information Technology Sydney University of Technology Australia

The multi-channel image or the video clip has the natural form of tensor. The values of the tensor can be corrupted due to noise in the acquisition process. We consider the problem of recovering a tensor L of visual data from its corrupted observations X = L + S, where the corrupted entries S are unknown and unbounded, but are assumed to be sparse. Our work is built on the recent studies about the recovery of corrupted low-rank matrix via trace norm minimization. We extend the matrix case to the tensor case by the definition of tensor trace norm in. Furthermore, the problem of tensor is formulated as a convex optimization, which is much harder than its matrix form. Thus, we develop a high quality algorithm to efficiently solve the problem. Our experiments show potential applications of our method and indicate a robust and reliable solution.

关键词： Tensile stress Sparse matrices Nickel Matrix decomposition Optimization Visualization Minimization

来源：评论

学校读者我要写书评

暂无评论

Design and implementation of knowledge base for target recognition in remote sensing images

Design and implementation of knowledge base for target recog...

引用

2010 7th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2010

作者： Chen, Shaobin Cai, Chao Li, Erlang Ding, Mingyue Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology State Key Laboratory for Multi-spectral Information Processing Technologies Wuhan 430074 China School of Life Science and Technology of Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)9781424459346

In this paper, the knowledge modeling, architecture design and detailed implementation of an ontology-based knowledge base for target recognition in remote sensing images is presented. Knowledge base is a critical component of a large ground target recognition system which is a hybrid system that combines knowledge base with remote sensing image processing module. The knowledge base provides necessary knowledge for remote sensing image processing module, and remote sensing image processing module can perform multiple tasks with the support of the knowledge base. The existence of the knowledge base makes the whole recognition system more flexible and more generic than those systems without knowledge base. The effectiveness of the presented knowledge base shows the good prospect of the application of knowledge base in remote sensing image processing domain. ©2010 IEEE.

关键词： Knowledge based systems

来源：评论

学校读者我要写书评

暂无评论

Istree Digital Watermarking Algorithm Based on Contourlet Transform

Istree Digital Watermarking Algorithm Based on Contourlet Tr...

引用

International Conference on Machine Vision and Human-Machine Interface (MVHI)

作者： Fan Zhang Yuli Xu Rui Li Institute of Image Processing and Pattern Recognition Henan University Kaifeng China College of Computer and Information Engineering Henan University Kaifeng China

In order to protect the copyright of the image, in this paper proposed a novel important sub-tree (Istree) digital watermarking algorithm based on contourlet transform. First, Shuffling is applied by watermarking image for increasing robustness. Second, the original image are decomposed three levels by contourlet transform, and then analysis sub-bands in all directions, according to various levels sub-bands in all direction structure like tree. And find important sub-tree, then Scrambling after the watermark image sequence is embedded in important sub-tree. The experimental results show that the algorithm has a certain degree of robustness and can resistance attack.

关键词： Watermarking Discrete wavelet transforms Discrete transforms Wavelet transforms Discrete Fourier transforms Fourier transforms Robustness Wavelet domain image processing image analysis

来源：评论

学校读者我要写书评

暂无评论

An image-sequence compressing algorithm based on homography transformation for unmanned aerial vehicle

An image-sequence compressing algorithm based on homography ...

引用

International Symposium on Intelligence Information processing and Trusted Computing

作者： Gong, Junbin Zheng, Chenlin Tian, Jinwen Wu, Dingxue Institute for Pattern Recognition and Artificial Intelligence National Key Laboratory of Science and Technology on Multi-spectral Information Processing Huazhong University of Science and Technology Wuhan 430074 China College of Computer Science and Technology Huanggang Normal University Huanggang 438000 China

ISBN: (纸本)9780769541969

Focus on the image compressing problem of unmanned aerial vehicle with high compression ratio, fixed compressing ratio and low computational complexity requirement, a low-complexity image-sequence compressing algorithm based on homography transformation was proposed. The image sequences were dynamically divided into framegroups according the data from airborne inertial navigation systems, and the intermediate frames in the same frame-group was bi-directionally predicted by the first-frame and the end-frame with homography transformation. The homography matrix was got approximately by the airborne inertial navigation systems firstly and then was accurately computed by fast multiple sub-areas template matching. At the end the first frame and the residual images of the intermediate frames of the same frame-group was merged into a big image and coded by JPEG2000 to generate fixed-size code streams. The experiment results show that the proposed algorithm was with high compression performance, low computational complexity and excellent capacity for code-size control and will has good prospect in engineer. © 2010 IEEE.

关键词： image compression

来源：评论

学校读者我要写书评

暂无评论

Motion blur detection based on lowest directional high-frequency energy

Motion blur detection based on lowest directional high-frequ...

引用

IEEE International Conference on image processing

作者： Xiaogang Chen Jie Yang Qiang Wu Jiajia Zhao Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University China Centre of Innovation in IT Services and Applications Sydney University of Technology Sydney Australia

Motion blur detection and the relevant blurring parameter estimation are important for many computer vision tasks. The contribution of this paper is in two folds. First, we propose a closed-form solution for motion direction estimation on blurred image. Secondly, a novel method is proposed for motion blurred region detection. The proposed direction estimation is based on measurement of lowest directional high-frequency energy. Compared with traditional methods, it will improve accuracy with less computational cost. Moreover, the proposed motion blurred region detection can efficiently estimate blurred regions without Point Spread Function estimation. Encouraging results are shown by experiments.

关键词： Estimation Pixel image segmentation image restoration Transforms Deconvolution Closed-form solution

来源：评论

学校读者我要写书评

暂无评论

Frequency-DOA Joint Estimation by Ant Colony Optimization

Frequency-DOA Joint Estimation by Ant Colony Optimization

引用

The 2010 International Conference on Computer Application and System Modeling(2010计算机应用与系统建模国际会议 ICCASM 2010)

作者： Yong Jin Yunshan Hou Min Jiang Institute of Image Processing and Pattern Recognition Henan University Kaifeng 475004 China College of Marine Northwestern Polytechnical University Xi'an 710072 China

ISBN: (纸本)9781424472352

The Multiple Signal Classification (MUSIC) method is a typical method for high-resolution Direction Of Arrival(DOA) and frequency estimation. Usually it performs spectrum search in certain grid space, which inevitably leads to high computational cost in the muti-dimensional case, for example the search for frequency and azimuth at the same time. To overcome this problem, in this paper, we introduced Ant Colony Optimization(ACO) to work with MUSIC. A new kind of ACO for continuous domain featured by Gauss kernel function is used to sample the MUSIC spectrum, which is regarded as the fitness function in the process. The resulted estimator is called Ant Colony Optimization based MUSIC (ACO-MUSIC). Simulations show that ACO-MUSIC not only reduces the computational complexity greatly but also maintains the excellent performance of the original MUSIC estimator.

关键词： direction of arrival multiple signal classification ant colony optimization computational complexity

来源：评论

学校读者我要写书评

暂无评论

Action recognition by Multiple Features and Hyper-Sphere Multi-class SVM

Action Recognition by Multiple Features and Hyper-Sphere Mul...

引用

International Conference on pattern recognition

作者： Jia Liu Jie Yang Yi Zhang Xiangjian He Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University Shanghai China Faculty of Engineering and Information Technology Sydney University of Technology Sydney Australia

ISBN: (纸本)9781424475421

In this paper we propose a novel framework for action recognition based on multiple features for improve action recognition in videos. The fusion of multiple features is important for recognizing actions as often a single feature based representation is not enough to capture the imaging variations (view-point, illumination etc.) and attributes of individuals (size, age, gender etc.). Hence, we use two kinds of features: i) a quantized vocabulary of local spatio-temporal (ST) volumes (cuboids and 2-D SIFT), and ii) the higher-order statistical models of interest points, which aims to capture the global information of the actor. We construct video representation in terms of local space-time features and global features and integrate such representations with hyper-sphere multi-class SVM. Experiments on publicly available datasets show that our proposed approach is effective. An additional experiment shows that using both local and global features provides a richer representation of human action when compared to the use of a single feature type.

关键词： Support vector machines Humans Videos Feature extraction Clouds image recognition pattern recognition

来源：评论

学校读者我要写书评

暂无评论

A Novel Robust Watermarking Method for Certificates Based on DFT and Hough Transforms

A Novel Robust Watermarking Method for Certificates Based on...

引用

International Conference on Intelligent Information Hiding and Multimedia Signal processing (IIHMSP)

作者： Jiancheng Zou Xin Yang Shaozhang Niu Institute of Image Processing and Pattern Recognition North-China University of Technology Beijing China School of Computer Beijing University of Posts and Telecommunications Beijing China

Based on the discrete Fourier transformation (DFT) and Hough transforms, a novel digital watermarking method is proposed. The experiment results show that the algorithm is more robust than the traditional watermark algorithm. The proposed algorithm can endure severe attacks such as printing-scanning, very high loss in its data or data packets, scaling and rotating. The most advantage of the algorithm presented in this paper is that it is robust for the first time of print and scan, but fragile for the second time of print and scan. So this method can be used in the anti counterfeit of certificates.

关键词： Watermarking Discrete Fourier transforms Robustness Signal processing algorithms Pixel Binary codes

来源：评论

学校读者我要写书评

暂无评论

Fast Marine Route Planning for UAV Using Improved Sparse A* Algorithm

Fast Marine Route Planning for UAV Using Improved Sparse A* ...

引用

International Conference on Genetic and Evolutionary Computing (ICGEC)

作者： Xin Yang Ming-yue Ding Cheng-ping Zhou Institute for Pattern Recognition and Artificial Intelligence (IPRAI) Image Processing and Intelligence Control Key Laboratory of Education Ministry of China Huazhong University of Science and Technology Wuhan Hubei China School of Life Science and Technology Image Processing and Intelligence Control Key Laboratory of Education Ministry of China Huazhong University of Science and Technology Wuhan Hubei China Institute for Pattern Recognition and Artificial Intelligence (IPRAI) State Key Laboratory for Multispectral Information Processing Technologies Huazhong University of Science and Technology Wuhan Hubei China

This paper focuses on route planning, especially for unmanned aircrafts in marine environment. Firstly, new heuristic information is adopted such as threat-zone, turn maneuver and forbid-zone based on voyage heuristic information. Then, the cost function is normalized to obtain more flexible and reasonable routes. Finally, an improved sparse A* search algorithm is employed to enhance the planning efficiency and reduce the planning time. Experiment results showed that the improved algorithm for aircraft in maritime environment could find a combinational optimum route quickly, which detoured threat-zones, with fewer turn maneuver, totally avoiding forbid-zones, and shorter voyage.

关键词： Unmanned aerial vehicles Planning Synthetic aperture sonar Cost function Algorithm design and analysis Heuristic algorithms Leg

来源：评论

学校读者我要写书评

暂无评论

Data Classification on Multiple Manifolds

Data Classification on Multiple Manifolds

引用

International Conference on pattern recognition

作者： Rui Xiao Qijun Zhao David Zhang Pengfei Shi Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University China Department of Computer Science Hong Kong Polytechnic University Hong Kong China

ISBN: (纸本)9781424475421

Unlike most previous manifold-based data classification algorithms assume that all the data points are on a single manifold, we expect that data from different classes may reside on different manifolds of possible different dimensions. Therefore, better classification accuracy would be achieved by modeling the data by multiple manifolds each corresponding to a class. To this end, a general framework for data classification on multiple manifolds is presented. The manifolds are firstly learned for each class separately, and a stochastic optimization algorithm is then employed to get the near optimal dimensionality of each manifold from the classification viewpoint. Then, classification is performed under a newly defined minimum reconstruction error based classifier. Our method could be easily extended by involving various manifold learning methods and searching strategies. Experiments on both synthetic data and databases of facial expression images show the effectiveness of the proposed multiple manifold based approach.

关键词： Manifolds Classification algorithms Accuracy Databases Training Tuning image reconstruction

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共216页 << < 111 112 113 114 115 116 117 118 119 120 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：