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

676 篇 会议
143 篇 期刊文献
130 册 图书
9 篇 学位论文

馆藏范围

958 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

632 篇 工学
- 464 篇 计算机科学与技术...
- 213 篇 软件工程
- 135 篇 电气工程
- 126 篇 机械工程
- 114 篇 光学工程
- 72 篇 控制科学与工程
- 49 篇 仪器科学与技术
- 40 篇 信息与通信工程
- 17 篇 电子科学与技术（可...
- 15 篇 生物医学工程（可授...
- 14 篇 生物工程
- 12 篇 材料科学与工程（可...
- 11 篇 测绘科学与技术
- 8 篇 化学工程与技术
- 8 篇 航空宇航科学与技...
- 7 篇 土木工程
- 7 篇 安全科学与工程
- 6 篇 建筑学
272 篇 理学
- 205 篇 物理学
- 89 篇 数学
- 27 篇 统计学（可授理学、...
- 15 篇 生物学
- 10 篇 系统科学
63 篇 医学
- 61 篇 临床医学
- 7 篇 基础医学(可授医学...
42 篇 管理学
- 24 篇 图书情报与档案管...
- 19 篇 管理科学与工程(可...
37 篇 艺术学
- 37 篇 设计学（可授艺术学...
9 篇 法学
- 9 篇 社会学
8 篇 农学
- 7 篇 作物学
2 篇 教育学

主题

267 篇 computer vision
233 篇 pattern recognit...
82 篇 artificial intel...
74 篇 image processing...
58 篇 feature extracti...
49 篇 computer imaging...
44 篇 image segmentati...
43 篇 images
41 篇 information syst...
40 篇 face recognition
39 篇 visualization
36 篇 computer graphic...
35 篇 algorithm analys...
32 篇 cameras
31 篇 training
28 篇 conferences
28 篇 image color anal...
28 篇 user interfaces ...
27 篇 image processing
26 篇 histograms

机构

20 篇 national laborat...
14 篇 computer vision ...
9 篇 huazhong univ sc...
9 篇 institute for pa...
8 篇 computer vision ...
6 篇 chinese acad sci...
6 篇 department of st...
4 篇 shenzhen key lab...
4 篇 department of in...
4 篇 huazhong univ sc...
4 篇 microsoft resear...
4 篇 huazhong univ sc...
4 篇 national laborat...
4 篇 chinese acad sci...
4 篇 college of compu...
4 篇 computer and vis...
3 篇 the ohio state u...
3 篇 queen’s universi...
3 篇 multimedia engin...
3 篇 institute of pat...

作者

11 篇 sang nong
10 篇 umapada pal
10 篇 tian jinwen
8 篇 cao zhiguo
7 篇 bischof horst
7 篇 huang kaiqi
6 篇 li dehua
6 篇 tieniu tan
6 篇 tan tieniu
5 篇 j. k. aggarwal
5 篇 kaiqi huang
5 篇 zhang tianxu
5 篇 horst bischof
5 篇 alireza alaei
5 篇 aggarwal j.k.
4 篇 gabor fichtinger
4 篇 gian luca forest...
4 篇 cai chao
4 篇 sebastian bauer
4 篇 huang yongzhen

语言

909 篇 英文
34 篇 中文
14 篇 其他
1 篇 法文

检索条件"任意字段=MIPPR 2011: Pattern Recognition and Computer Vision"

共 958 条记录，以下是891-900 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：

針對盲人輔助應用之電腦視覺演算法開發與硬體架構設計

針對盲人輔助應用之電腦視覺演算法開發與硬體架構設計

引用

作者：李嘉祥臺灣大學

学位级别：碩士

近年来，在盲人辅助系统上，电脑视觉分析逐渐变为主流研究方向，在现阶段中，最普遍使用的盲人辅助系统为导盲犬与盲人手杖，然而，此种方式包含许多缺点如不方便性及价格昂贵等，在社交的场合或是拥挤的环境中，此种辅助方式极为不适... 详细信息

近年来，在盲人辅助系统上，电脑视觉分析逐渐变为主流研究方向，在现阶段中，最普遍使用的盲人辅助系统为导盲犬与盲人手杖，然而，此种方式包含许多缺点如不方便性及价格昂贵等，在社交的场合或是拥挤的环境中，此种辅助方式极为不适用。此外，当盲人在行走於户外环境时，它们无法提供环境的分析与障碍物的侦测，相较之下，电子辅助系统是较为理想的解决方式，它们提供了更多环境资讯与导航能力。然而最新的电子辅助系统较为笨重且功能受到限制，在本篇论文中，我们设计了携带式视觉分析盲人辅助系统与视觉分析导航系统，此系统帮助盲人行走并提供重要之环境资讯。首先，我们发展出智慧型以深度图(Depth Map)为基准之障碍物侦测系统，此系统的高准确度使得盲人可以快速且轻易闪避障碍物，根据深度图的切割(Segmentation)与空间分布关系，我们提出的演算法可以高达95%以上的准确，当障碍物被抓取之後，系统会提供障碍物的资讯例如深度、方向等，更进一步使用物体追踪演算法(Object Tracking)来记录障碍物之方向与路径的轨迹，藉此可以预测障碍物未来动线以提早闪避，接着第二部份，为了使盲人了解环境资讯，我们提出深度特性模型(Depth Characteristic Mode)来抽取环境资讯，例如：道路、楼梯与墙壁，此功能可以使得盲人能更了解周遭环境，抽取出这些特定的资讯来使得盲人安全的行走道路、攀爬楼梯、沿着墙壁行走等，在第三部份更透过结合图形辨识功能(pattern recognition)，设计出以全球卫星定位系统GPS(Globe Positioning System)为基准之视觉导航系统(vision-based Navigation System)，这使得盲人可以在陌生的环境中，更精确定位所在的位置，借此我们可以达到更精确的导航功能，在论文最後，我们挑出了两项在系统架构中最为耗时的区块来做硬体加速，使得此系统可以达到即时侦测的功能，此两区块分别为图形切割与型态学操作(Morphology)，我们所用的制程为台积电(TSMC)提供之 65 奈米(nm)制程，此晶片可以操作在200MHz 之频率，所耗的功率为56 毫瓦(mW)，透过我们的硬体架构设计，在解析度640*480 之下可以达到2000 张每秒的处理速度，在最为复杂的情况下，也可以有28 张每秒的处理速度。总合来说，我们提出了一套的盲人辅助系统之演算法与硬体架构设计，其中包含三大部分软体演算法，分别为障碍物侦测、深度特性模型侦测与视觉导航系统，并且对於其中运算量最高之部份做硬体加速，在65 奈米制程下可使得整体系统可以达到即时侦测之功能。

关键词：盲人輔助系電腦視覺深度圖物體追蹤圖形辨識視覺導航系統深度特性模型硬體架構設計型態學操作

来源：评论

学校读者我要写书评

暂无评论

Interclass Visual Similarity Based Visual Vocabulary Learning

Interclass Visual Similarity Based Visual Vocabulary Learnin...

引用

第一届亚洲模式识别会议

作者： Guangming Chang Chunfen Yuan Weiming Hu National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beij National Laboratory of Pattern RecognitionInstitute of Automation Chinese Academy of SciencesBeijin

Visual vocabulary is now widely used in many video analysis tasks, such as event detection, video retrieval and video classification. In most approaches the vocabularies are solely based on statistics of visual features and generated by clustering. Little attention has been paid to the interclass similarity among different events or actions. In this paper, we present a novel approach to mine the interclass visual similarity statistically and then use it to supervise the generation of visual vocabulary. We construct a measurement of interclass similarity, embed the similarity to the Euclidean distance and use the refined distance to generate visual vocabulary iteratively. The experiments in Weizmann and KTH datasets show that our approach outperforms the traditional vocabulary based approach by about 5％.

关键词： Vocabulary Visualization Clustering algorithms pattern recognition Conferences Vectors computer vision

来源：评论

学校读者我要写书评

暂无评论

Robust upper body detection in unconstrained posture

Robust upper body detection in unconstrained posture

引用

International Conference on Multimedia Technology

作者： Diping Li Beiji Zou Department of Math & Information Technology Hanshan Normal University Chaozhou China School of Information Science and Engineering Central South University Changsha China

ISBN: (纸本)9781612847719

This paper presents an efficient approach to detecting upper body in unconstrained posture based on Shape Context and Histograms of Orient Gradients. The method contains two steps. Shape context matching is used to get the candidates of upper bodies in the images at first, and then validation of each candidate is performed by using the Histograms of Orient Gradients. The method has two advantages, comparing with existing body detection methods. One is that it can detect upper bodies in all kinds of postures other than upright standing posture, and the other is that it significantly speeds up the computation.

关键词： Shape Context Humans Histograms computer vision Support vector machines pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Classification of facial expressions by sparse coding

Classification of facial expressions by sparse coding

引用

IEEE Signal Processing and Communications Applications (SIU)

作者： Nesli Erdoğmuş Jean-Luc Dugelay Multimedia Communications Department Eurecom Institute Sophia-Antipolis France

Expression variations in facial images is one of the most crucial and difficult problems in face-based computer vision applications. Although numerous systems have been proposed for robustness against facial expressions, so far it still persists to be an open *** that the knowledge on the type of the expression in a facial image would greatly facilitate the solution of this issue, in this paper we present an analysis for facial expressions classification in 2D frontal views. With the motivation of the success that sparse coding achieved in face recognition, similar principals are applied for to both original and dimension-reduced (via PCA) images and the resulting codes are classified based on two different approaches: minimum residual error and maximum interclass summation of the coefficients. Extensive tests are conducted on Bosphorus database, in which different expressions are available for 105 persons.

关键词： Conferences Face recognition Face Signal processing pattern analysis Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Detect saliency to understand a photo

Detect saliency to understand a photo

引用

International Conference on Multimedia Technology

作者： Lin Cong Ruo-Feng Tong Da-Yong Bao College of Computer Science and Technology University of Zhejiang Hangzhou Zhejiang China

Visual saliency is an extremely hot topic in image and video processing. Our paper addresses a novel method for saliency detection, which conveys the photographers' idea of a scene. It consists of analyzing the photo elements like color, depth-of-field (DOF) and composition. We use the color spatial distribution feature to calculate the initial saliency. A simple but efficient classifier is trained to discriminate the low DOF image. For this kind of images we find the focal area to refine the initial saliency. The saliency map will be further adjusted by an image composition analysis step to generate the final output. We compare our framework with state-of-the-art algorithms. Experimental results show that, our method out-performs the previous methods in many cases, especially in the low DOF situation.

关键词： Image color analysis Visualization Image edge detection Conferences computer vision pattern recognition Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Occlusion robust multi-camera face tracking

Occlusion robust multi-camera face tracking

引用

IEEE computer Society Conference on computer vision and pattern recognition Workshops (CVPRW)

作者： Josh Harguess Changbo Hu J. K. Aggarwal Computer & Vision Research Center / Department of ECE University of Texas Austin USA

This paper presents a novel approach to object tracking by using multiple views to assist with handling occlusion which improves the overall tracking result. The approach is applied to face tracking using a 3D cylinder head model, but any 3D rigid object may be tracked using this approach. All cameras in the system are used to estimate a joint motion model of the face, which is updated at each frame. Self-occlusion is handled by a weighted mask that depends on the pose of the face. Full face occlusion is first detected automatically by measuring and comparing image histograms of the current tracking result and a face template. If an occlusion from a camera is reported, it is not used in the global tracking result of the face from the multi-camera system. Experiments demonstrate that our method succeeds in tracking in both cases of self-occlusion and full face occlusion. Comparisons are made between single camera tracking, multi-camera tracking and occlusion robust multi-camera tracking using results from pose estimation. The performance of the occlusion robust multi-camera face tracking method is shown to produce more accurate estimates of the face pose and is able to estimate the face pose even under severe face occlusion.

关键词： Face Cameras Three dimensional displays Tracking Solid modeling Robustness Histograms

来源：评论

学校读者我要写书评

暂无评论

The magic sigma

The magic sigma

引用

Conference on computer vision and pattern recognition (CVPR)

作者： Dirk Padfield One Research Circle GE Global Research Center Niskayuna NY USA

With the explosion in the usage of mobile devices and other smart electronics, embedded devices are becoming ubiquitous. Most such embedded architectures utilize fixed-point rather than floating-point computation to meet power, heat, and speed requirements leading to the need for integer-based processing algorithms. Operations involving Gaussian kernels are common to such algorithms, but the standard methods of constructing such kernels result in approximations and lack a property that enables efficient bitwise shift operations. To overcome these limitations, we present how to precisely combine the power of integer arithmetic and bitwise shifts with intrinsically real valued Gaussian kernels. We prove mathematically that there exist a set of what we call “magic sigmas” for which the integer kernels exactly represent the Gaussian function whose values are all powers-of-two, and we discovered that the maximum sigma that leads to such properties is about 0.85. We also designed a simple and precise algorithm for designing kernels composed exclusively of integers given any arbitrary sigma and show how this can be exploited for Gaussian filter design. Considering the ubiquity of Gaussian filtering and the need for integer computation for increasing numbers of embedded devices, this is an important result for both theoretical and practical purposes.

关键词： Kernel Equations Approximation methods Hardware Algorithm design and analysis Mathematical model computer vision

来源：评论

学校读者我要写书评

暂无评论

Subspace System Identification of Separable-in-Denominator 2-D Stochastic Systems

Subspace System Identification of Separable-in-Denominator 2...

引用

IEEE Conference on Decision and Control

作者： Jose A. Ramos Paulo J. Lopes dos Santos Nova Southeastern University Farquhar College of Arts and Sciences Division of Mathematics Science and Technology 3301 College Avenue Fort Lauderdale FL 33314 Faculdade de Engenharia da Universidade do Porto Departamento de Engenharia Electrotecnica e de Computadores Rua Dr. Roberto Frias Porto Portugal 4200 465

ISBN: (纸本)9781612848006

The fitting of a causal dynamic model to an image is a fundamental problem in image processing, pattern recognition, and computer vision. There are numerous other applications that require a causal dynamic model, such as in scene analysis, machined parts inspection, and biometric analysis, to name only a few. There are many types of causal dynamic models that have been proposed in the literature, among which the autoregressive moving average (ARMA) and state-space models are the most widely known. In this paper we introduce a 2-D stochastic state-space system identification algorithm for obtaining stochastic 2-D, causal, recursive, and separable-in-denominator (CRSD) models in the Roesser state-space form. The algorithm is tested with a real image and the reconstructed image is shown to be almost indistinguishable to the true image.

关键词： Separable autoregressive moving average System identification real image stochastic systems computer vision Subspace Image State space models

来源：评论

学校读者我要写书评

暂无评论

An Empirical Study of Visual Features for Part Based Model

An Empirical Study of Visual Features for Part Based Model

引用

第一届亚洲模式识别会议

作者： Junge Zhang Yinan Yu Shuai Zheng Kaiqi Hua National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences National Laboratory of Pattern RecognitionInstitute of Automation Chinese Academy of Sciences

ISBN: (纸本)9781457701221

Object detection is a fundamental task in computer vision. Deformable part based model has achieved great success in the past several years, demonstrating very promising performance. Many papers emerge on part based model such as structure learning, learning more discriminative features. To help researchers better understand the existing visual features’ potential for part based object detection and promote the deep research into part based object representation, we propose an evaluation framework to compare various visual features’ performance for part based model. The evaluation is conducted on challenging PASCAL VOC2007 dataset which is widely recognized as a benchmark database. We adopt Average Precision (AP) score to measure each detector’s performance. Finally, the full evaluation results are present and discussed.

关键词： Histograms Object detection Image color analysis Visualization computer vision Deformable models Color

来源：评论

学校读者我要写书评

暂无评论

Handwritten Street Name recognition for Indian Postal Automation

Handwritten Street Name Recognition for Indian Postal Automa...

引用

International Conference on Document Analysis and recognition

作者： Umapada Pal Ramit Kumar Roy Fumitaka Kimura Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India Saint Xavier's College Kolkata India Graduate School of Engineering Mie University TSU Japan

Although for postal automation there are many pieces of work towards street name recognition on non-Indian languages, to the best of our knowledge there is no work on street name recognition on Indian languages. In this paper we proposed a scheme for recognition of Indian street name written in Bangla script. Because of the writing style of different individuals some of the characters in a street name may touch with its neighboring characters. Accurate segmentation of such touching into individual characters is a difficult task. To avoid such segmentation, here we consider a street name string as word and the street name recognition problem is treated as lexicon driven word recognition. Some of the street names may contain two or more words and we have concatenated these words to have a single word. In the proposed method, at first, street names are binarized and pre-segmented into possible primitive components (individual characters or its parts) analyzing their cavity portions. Pre-segmented components of a street name are then merged into possible characters to get the best street name. Dynamic programming (DP) is applied for the merging using total likelihood of characters as the objective function. To compute the likelihood of a character, modified quadratic discriminant function (MQDF) is used. Our proposed system shows 99.03% reliability with 18.80% rejection, and 0.79% error rates when tested on 4450 handwritten Bangla street name samples.

关键词： Handwriting recognition Accuracy Cavity resonators Automation Feature extraction Dynamic programming Image segmentation

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96页 << < 86 87 88 89 90 91 92 93 94 95 > >>

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：