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

384 篇 会议
263 篇 期刊文献

馆藏范围

647 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

443 篇 工学
- 276 篇 计算机科学与技术...
- 234 篇 软件工程
- 106 篇 信息与通信工程
- 79 篇 光学工程
- 64 篇 生物工程
- 53 篇 控制科学与工程
- 51 篇 电子科学与技术（可...
- 42 篇 机械工程
- 40 篇 生物医学工程（可授...
- 33 篇 电气工程
- 27 篇 化学工程与技术
- 19 篇 仪器科学与技术
- 18 篇 航空宇航科学与技...
- 16 篇 土木工程
- 13 篇 建筑学
- 11 篇 材料科学与工程（可...
- 11 篇 交通运输工程
295 篇 理学
- 149 篇 数学
- 111 篇 物理学
- 73 篇 生物学
- 52 篇 统计学（可授理学、...
- 25 篇 化学
- 20 篇 系统科学
88 篇 管理学
- 45 篇 管理科学与工程(可...
- 44 篇 图书情报与档案管...
- 9 篇 工商管理
27 篇 医学
- 23 篇 临床医学
- 17 篇 基础医学(可授医学...
- 15 篇 药学(可授医学、理...
10 篇 法学
- 7 篇 社会学
6 篇 经济学
5 篇 农学
5 篇 军事学
4 篇 教育学
2 篇 艺术学
1 篇 哲学
1 篇 文学

主题

27 篇 image segmentati...
23 篇 feature extracti...
18 篇 pattern recognit...
18 篇 image processing
18 篇 training
16 篇 convolution
14 篇 face recognition
14 篇 semantics
13 篇 object detection
13 篇 laboratories
12 篇 image reconstruc...
11 篇 computer vision
10 篇 shape
9 篇 deep learning
9 篇 target tracking
9 篇 optimization
9 篇 algorithm design...
9 篇 image classifica...
9 篇 artificial intel...
9 篇 infrared imaging

机构

28 篇 institute of ima...
22 篇 school of inform...
18 篇 state key labora...
17 篇 key laboratory o...
17 篇 institute for pa...
17 篇 anhui province k...
13 篇 school of softwa...
12 篇 national laborat...
11 篇 key laboratory o...
10 篇 key laboratory o...
9 篇 national key lab...
9 篇 pattern recognit...
9 篇 institute of ima...
9 篇 institute of pat...
9 篇 state key labora...
9 篇 university of ch...
9 篇 pattern recognit...
8 篇 key laboratory o...
8 篇 college of infor...
8 篇 pattern recognit...

作者

32 篇 zhang tianxu
25 篇 yang jie
17 篇 huang xiaolin
15 篇 zhou jie
15 篇 tian jinwen
14 篇 jie yang
14 篇 tianxu zhang
14 篇 liu jian
13 篇 jinwen tian
13 篇 jian liu
12 篇 ding mingyue
12 篇 li qishen
11 篇 meng fandong
11 篇 shen hong-bin
10 篇 cai chao
10 篇 qishen li
10 篇 ma zhanyu
9 篇 shao zehui
9 篇 yang yang
9 篇 huang zhixiang

语言

600 篇 英文
25 篇 其他
22 篇 中文

检索条件"机构=Laboratory of Pattern Recognition and Intelligent Information Processing"

共 647 条记录，以下是471-480 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：

A novel automatic motion segmentation method based on optical flow

A novel automatic motion segmentation method based on optica...

引用

International Conference on Multimedia Technology

作者： Lu, Haifeng Zhang, Tianxu Yao, Cong State Key Laboratory for Multispectral Information Processing Technologies Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)9781424478743

Motion segmentation is one of the fundamental problems in digital image processing area. The estimation of velocity field is one of the most notable approaches on the first step of motion segmentation. A novel motion segmentation method is proposed, which is nonparametric and automatically selects value of the segmentation criterion. In particular, we first employ the optical flow to estimate the motion field;then we establish a segmentation criterion and measure the difference between regions of the moving objects and background separated in the segmentation criterion at each level;next we adopt the level of the segmentation criterion which makes the two regions the most different;finally, our approach output regions of moving objects and background from the scene. Experimental results demonstrate that our method is effective, and the procedure is much simpler than the methods often used. ©2010 IEEE.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

A high performance fully pipelined architecture for lossless compression of satellite image

A high performance fully pipelined architecture for lossless...

引用

2010 International Conference on Multimedia Technology, ICMT 2010

作者： Wang, Ze Zhang, Tianxu Yan, Luxin Gong, Cheng State Key Laboratory for Multispectral Information Processing Technologies Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)9781424478743

This paper presents a novel hardware implementation of the adaptive JPEG-LS in field programmable gate array (FPGA), based on the low complexity lossless compression for images (LOCO-I) compression scheme. Differently from what previously reported in literature, this design achieves a much lower complexity and super high data throughput through an improved prediction model by breaking the feedback loop of context parameters updating. The processing speed of this design is up to 75Mpixels per second, while the compression ratio is slightly lower than the standard JPEG-LS compression. Performance evaluation also indicates that design complexity and compression efficiency can be taken account at the same time to achieve satisfactory result. Such an implementation could be used for high-speed compression of satellite remote sensing image onboard. ©2010 IEEE.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

An accurately located method and secure scheme for image authentication

An accurately located method and secure scheme for image aut...

引用

International Conference on Multimedia Technology

作者： Wang, Zuxi Wang, Wenzong Dong, Liefeng Ye, Peng Institute of Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Key Laboratory of Image Processing and Intelligent Control Wuhan China Ningbo Polytechnic Ningbo China

ISBN: (纸本)9781424478743

A novel authentication watermarking scheme for images is proposed in this paper, which holds accuracy location and high security at the same time. In the scheme, different keys are selected for different host data, and the generation and insertion of watermark is dependent on the selected key. Analyzing different pieces of watermarked data in order to launch an attack becomes impossible because of the lack of common characteristics in these pieces. Beside, to increase the security of system, the chaos technology is used to encrypt the watermark and shuffle the location of embedding. A method for tamper detecting based on the running window is proposed in the scheme. Not only can it distinguish malicious attacks from unintentional attacks, but also it can locate the tampered area accurately. Experimental results show this semi-fragile watermarking algorithm is effective and practical for content authentication. ©2010 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

A method of ground-based space object opho-electronic imaging simulation

A method of ground-based space object opho-electronic imagin...

引用

International Conference on Multimedia Technology

作者： Zhang, Putao Zhang, Tianxu State Key Laboratory for Multi-spectral Information Processing Technologies Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)9781424478743

It is very necessary to observe, tracking and recognise interested space object including space debris around the earth. A simulation method about ground-based sensor observing, tracking and imaging space object is researched. It includes the visibility analysis of space object in the STK scene, the attitude description mode of object, the data alternant form and format between STK and Vega, the imaging method of the object through Vega and the visual realization of the process. ©2010 IEEE.

关键词： Space debris

来源：评论

学校读者我要写书评

暂无评论

Unified restoration method for different degraded images

Unified restoration method for different degraded images

引用

2010 International Conference on Optoelectronics and Image processing, ICOIP 2010

作者： Hong, Hanyu Li, Liangcheng Yan, Luxin Zhang, Tianxu Laboratory for Image Processing and Intelligent Control Wuhan Institute of Technology Wuhan 430074 China Institute for Pattern Recognition and AI Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)9780769542522

Blurred images are caused by many factors such as defocus, motion, and atmospheric turbulence. Due to the unknown various factors that cannot be distinguished in the blurred image, it is necessary to propose a unified method for image restoration. In order to solve this problem, a unified restoration method for different degraded images is presented, in which we use edge information of blurred image to predict the blur mode. It operates by locally predicting a sharp image using edge information of blurred image and establishes a nonlinear and spatial anisotropic regularization function from the prediction sharp image and the blurred image. Then we can estimate the point spread function (PSF) and recover the blurred image quickly. A series of restoration experiments for different blured images have been performed to verify the effectiveness of the proposed method. © 2010 IEEE.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

An efficient duplicate image detection method based on Affine-SIFT feature

An efficient duplicate image detection method based on Affin...

引用

2010 3rd IEEE International Conference on Broadband Network and Multimedia Technology, IC-BNMT2010

作者： Cao, Yudong Zhang, Honggang Gao, Yanyan Guo, Jun Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing China College of Electrical and Information Engineering Liaoning University of Technology Jinzhou China

ISBN: (纸本)9781424467709

In this paper, we present a novel scheme to tackle the task of near-duplicate image detection. Given two input images, the algorithm based on the refined similarity measure can judge rightly whether two input image are duplicate images or not. The two images are represented with local feature (i.e, Affine-SIFT) in bag of features model. The Affine-SIFT can undergo larger affine distortions than Hessian-Affine and MSER (Maximally Stable Extremal Region). The refined similarity measure exploits the spatial information between two images. The algorithm is demonstrated on some image pairs with scale change, viewpoint change, blur, noise and spatial deformation. The experimental results show that proposed algorithm is more effective than other state-of-the-art duplicate Image detection algorithm. © 2010 IEEE.

关键词： Affine-SIFT Duplicate detection Image matching

来源：评论

学校读者我要写书评

暂无评论

Second order morphology algorithm for IR small target enhancement in sea clutter background

Second order morphology algorithm for IR small target enhanc...

引用

2010 International Conference on Optics, Photonics and Energy Engineering, OPEE 2010

作者： Xiao, Zhou Xingang, Mou Guilin, Zhang Natl. Key Laboratory of Science and Technology on Multi-spectral Information Processing Technologies Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9781424452354

The framework of a second order morphology algorithm is proposed to enhance the dim small infrared target in sea clutter background with strong detector noise. First, a morphological filters bank is given. Each filter in the bank is designed to suppress its corresponding type texture. The second order process can be accomplished in two steps. The original infrared image is first filtered using each filter separately, and then the first order result is obtained by the combination of the filtered result images. The other step is essentially the same as the first one except the combination manner of the filtered result images. Second, the traditional SNR gain based evaluation of different small target enhancement algorithms is examined and a more reasonable method based on the distance between the target and the maximal background (DTMB) is described in this paper. Third, using the new evaluation method, the comparison is given by experiment through a sequence of infrared images with a dim small target. Experimental results demonstrate that the new proposed algorithm performs better in sea clutter background with strong detector noise than the traditional ones. © 2010 IEEE.

关键词： Morphology

来源：评论

学校读者我要写书评

暂无评论

On realization of visualization system for global ocean simulation

On realization of visualization system for global ocean simu...

引用

International Conference on Audio, Language and Image processing

作者： Ming, De-Lie Gao, Peng-Fei Wang, Mi State Key Laboratory for Multi-spectral Information Processing Technology Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan Hubei Province 430074 China

ISBN: (纸本)9781424458653

Simulating and rendering realistic ocean is always one of the most popular and difficult tasks in computer graphics and oceanography. However, because of the restriction of computer software and hardware conditions, mass data and real-time, there are less people to research global ocean simulation. Under the background of global environment simulation, the paper describes a solution for the application of global ocean simulation on the basis of previous work, and realizes the visualization system successfully using OSG (OpenSceneGraph) API and all kinds of open-source libraries, and demonstrates the result of cross-sea flight. At last, we analysis the deficiencies of our solution and make some improvement suggestions. ©2010 IEEE.

关键词： Computer hardware

来源：评论

学校读者我要写书评

暂无评论

A new roadmap constitution method based on dividing grid and level-set

A new roadmap constitution method based on dividing grid and...

引用

International Symposium on Intelligence information processing and Trusted Computing

作者： Li, Shidong Ding, Mingyue Cai, Chao Institute for Information Engineering of Hubei University for Nationalities Enshi Hubei China Institute for Pattern Recognition and Artificial Intelligence National Lab. for Multi-spectral Information Processing Technologies HUST Wuhan China College of Life Science and Technology Image Processing and Intelligent Control Key Laboratory of Education Ministry of China HUST Wuhan China

ISBN: (纸本)9780769541969

Roadmap methods were widely used in route planning fields, both for robots and unmanned aircrafts. Traditional roadmap is constituted by connecting the vertexes of convex obstacle, which is related to the locations of start and goal of route, so the roadmap can not be reused when anyone of start and goal changed. Absence of reusability reduces the efficiency of route planning by using roadmap. A new roadmap constitution method was proposed in this paper, which is build on dividing the 2D configuration space into multi-scale grids and setting nodes of roadmap on grid boundary using Level-Set method, same method was used to construct the map cells of roadmap between any two nodes lays on same grid . The roadmap constituted with new method can be reused when the start or goal was changed;it is efficient for replanning problem. © 2010 IEEE.

关键词： Reusability

来源：评论

学校读者我要写书评

暂无评论

Learning human actions with an adaptive codebook

Learning human actions with an adaptive codebook

引用

2010 16th International Conference on Virtual Systems and Multimedia, VSMM 2010

作者： Kong, Yu Zhang, Xiaoqin Hu, Weiming Jia, Yunde Beijing Laboratory of Intelligent Information Technology School of Computer Science Beijing Institute of Technology Beijing 100081 China College of Mathematics and Information Science Wenzhou University Zhejiang China National Laboratory of Pattern Recognition Institute of Automation China

ISBN: (纸本)9781424490264

Learning a compact and yet discriminative codebook for classifying human actions is a challenging problem. One difficulty lies in that the learning procedure is split into two independent phases (dimension reduction and clustering) and thus results in the loss of discriminative information which clustering requires. Besides, traditional used principal component analysis is not optimized for class separability and may not help to improve data separation. In this paper, we propose a novel optimization framework which unifies dimension reduction and clustering. In contrast to previous methods, our method enables to dynamically select indispensable and crucial dimensions for building a discriminative codebook. We add metric learning before clustering to provide the clustering method with an optimized distance metric. Experimental results show that our approach constructs a highly discriminative codebook and achieves comparable results to other state-of-the-art approaches. ©2010 IEEE.

关键词： Principal component analysis

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65页 << < 44 45 46 47 48 49 50 51 52 53 > >>

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：