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

1,071 篇 会议
41 篇 期刊文献
3 册 图书

馆藏范围

1,115 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

612 篇 工学
- 534 篇 计算机科学与技术...
- 404 篇 软件工程
- 143 篇 电气工程
- 51 篇 光学工程
- 32 篇 控制科学与工程
- 30 篇 机械工程
- 29 篇 信息与通信工程
- 29 篇 生物医学工程（可授...
- 27 篇 电子科学与技术（可...
- 14 篇 生物工程
- 10 篇 仪器科学与技术
- 8 篇 交通运输工程
- 7 篇 建筑学
- 6 篇 土木工程
- 6 篇 农业工程
- 5 篇 材料科学与工程（可...
- 5 篇 化学工程与技术
310 篇 医学
- 295 篇 临床医学
- 42 篇 特种医学
- 25 篇 基础医学(可授医学...
- 7 篇 药学(可授医学、理...
162 篇 理学
- 99 篇 数学
- 67 篇 物理学
- 17 篇 生物学
- 12 篇 统计学（可授理学、...
- 5 篇 化学
- 5 篇 系统科学
29 篇 管理学
- 18 篇 图书情报与档案管...
- 12 篇 管理科学与工程(可...
6 篇 农学
- 6 篇 作物学
4 篇 法学
2 篇 教育学
1 篇 经济学

主题

175 篇 image segmentati...
102 篇 image processing
98 篇 feature extracti...
73 篇 shape
72 篇 image color anal...
70 篇 computer graphic...
68 篇 visualization
67 篇 computer vision
64 篇 image reconstruc...
64 篇 training
58 篇 image analysis
51 篇 rendering (compu...
45 篇 robustness
44 篇 graphics
42 篇 image edge detec...
41 篇 cameras
40 篇 layout
38 篇 pixel
37 篇 biomedical imagi...
34 篇 histograms

机构

11 篇 universidade de ...
10 篇 universidade fed...
9 篇 univ estadual ca...
7 篇 institute of com...
7 篇 univ sao paulo i...
6 篇 universidade est...
5 篇 univ fed minas g...
5 篇 impa rio de jane...
4 篇 univ sao paulo i...
4 篇 impa-instituto d...
4 篇 institute of com...
4 篇 géométrica proje...
4 篇 univ fed rio gra...
3 篇 universidade de ...
3 篇 departamento de ...
3 篇 departamento de ...
3 篇 pontificia univ ...
3 篇 univ fed parana ...
3 篇 univ sao paulo i...
3 篇 inst. of comput....

作者

12 篇 velho luiz
11 篇 luiz velho
11 篇 wu shin-ting
11 篇 falcao alexandre...
10 篇 velho l
9 篇 schwartz william...
9 篇 l. velho
9 篇 silvio jamil f. ...
9 篇 miranda paulo a....
8 篇 luis gustavo non...
7 篇 afonso paiva
7 篇 hirata nina s. t...
7 篇 menotti david
7 篇 r.a. lotufo
7 篇 waldemar celes
7 篇 guimaraes pedron...
6 篇 jefersson a. dos...
6 篇 torres ricardo d...
6 篇 laroca rayson
6 篇 william robson s...

语言

1,106 篇 英文
5 篇 其他
3 篇 葡萄牙文
2 篇 中文

检索条件"任意字段=14th Brazilian Symposium on Computer Graphics and Image Processing"

共 1115 条记录，以下是571-580 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：

Spectral Segmentation Using Cartoon-Texture Decomposition and Inner Product-Based Metric

Spectral Segmentation Using Cartoon-Texture Decomposition an...

引用

brazilian symposium on computer graphics and image processing (SIBGRAPI)

作者： Wallace Casaca Afonso Paiva Luis Gustavo Nonato Instituto de Ciências Matemáticas e de Computação USP Brazil

this paper presents a user-assisted image partition technique that combines cartoon-texture decomposition, inner product-based similarity metric, and spectral cut into a unified framework. the cartoon-texture decomposition is used to first split the image into textured and texture-free components, the latter being used to define a gradient-based inner-product function. An affinity graph is then derived and weights are assigned to its edges according to the inner product-based metric. Spectral cut is computed on the affinity graph so as to partition the image. the computational burden of the spectral cut is mitigated by a fine-to-coarse image representation process, which enables moderate size graphs that can be handled more efficiently. the partitioning can be steered by interactively by changing the weights of the graph through user strokes. Weights are updated by combining the texture component computed in the first stage of our pipeline and a recent harmonic analysis technique that captures waving patterns. Finally, a coarse-to-fine interpolation is applied in order to project the partition back onto the original image. the suitable performance of the proposed methodology is attested by comparisons against state-of-art spectral segmentation methods.

关键词： image segmentation image edge detection Measurement Pipelines Vectors Eigenvalues and eigenfunctions Interpolation

来源：评论

学校读者我要写书评

暂无评论

Progressive Background image Generation of Surveillance Traffic Videos Based on a Temporal Histogram Ruled by a Reward/Penalty Function

Progressive Background Image Generation of Surveillance Traf...

引用

brazilian symposium on computer graphics and image processing (SIBGRAPI)

作者： Rensso Mora Colque Guillermo C´mara-Ch´vez Departamento de Computação Universidade Federal de Ouro Preto Ouro Preto Brazil

In most surveillance traffic systems the background image is used for segmenting the moving objects. In this paper, we propose a method for progressive and constant renewal of the background image of a video sequence. Our method is divided in three parts: frame difference to get an actual information of the video sequence, reward and penalty function that modifies a temporal histogram, and the background generation uses the information found in the histogram. the principal characteristic of the method is the constant regeneration of the histogram using neighborhood information of intensity levels, penalizing the occurrence of foreign objects and rewarding the values of static objects. For that, the histogram values are modified regionally and its variation correspond to a normal distribution. the principal advantages of our proposed method lies in the progressive increment of the background pixel intensity occurrences, the fast reaction to changes between foreground and background segments and the simplicity of the method that can be used in real time applications. At the end of this paper, experimental results demonstrated the feasibility of the proposed technique in different weather conditions and traffic situations.

关键词： Histograms Vehicles Indexes Cameras Video sequences Videos Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Corner Detection within a Multiscale Framework

Corner Detection within a Multiscale Framework

引用

brazilian symposium on computer graphics and image processing (SIBGRAPI)

作者： I´lis Paula F´tima Medeiros Francisco Nivando Bezerra Daniela Ushizima Departamento de Engineering de Teleinformática Universidade Federal do Cearà Fortaleza Ceara Brazil Ciência e Tecnologia Institute Fed. de Educação Maracana Ceara Brazil Math and Visualization Groups Lawrence Berkeley National Laboratory Berkeley CA USA

We present a new multi scale method for corner detection. the proposed algorithm embodies an undecorated wavelet decomposition of the angulations signal of a shape contour to identify significant points on it. It detects peaks that persist through several scales from the correlation signal between scales of its non-orthogonal sub-band decompositions. these peaks correspond to high curvature points (HCPs). Furthermore, we compare the proposed method with others available in the literature, including the well-known curvature scale-space (CSS) method. the quantitative assessment of the algorithms is provided by some figures of merit (FOM) measures that indicate which method better detects the relevant points in terms of compaction and shape reconstruction.

关键词： Shape Detectors Correlation Cascading style sheets Feature extraction Equations image edge detection

来源：评论

学校读者我要写书评

暂无评论

Elucidating the Relations among Seeded image Segmentation Methods and their Possible Extensions

Elucidating the Relations among Seeded Image Segmentation Me...

引用

brazilian symposium on computer graphics and image processing (SIBGRAPI)

作者： Paulo Miranda Alexandre Falcao Department of Computer Science IME University of São Paulo Sao Paulo Sao Paulo Brazil Information Systems Department LIV-Institute of Computing Unicamp Campinas Sao Paulo Brazil

Many image segmentation algorithms have been proposed, specially for the case of binary segmentation (object/background) in which hard constraints (seeds) are provided interactively. Recently, several theoretical efforts were made in an attempt to unify their presentation and clarify their relations. these relations are usually pointed out textually or depicted in the form of a table of parameters of a general energy formulation. In this work we introduce a more general diagram representation which captures the connections among the methods, by means of conventional relations from set theory. We formally instantiate several methods under this diagram, including graph cuts, power watersheds, fuzzy connectedness, grow cut, distance cuts, and others, which are usually presented as unrelated methods. the proposed diagram representation leads to a more elucidated view of the methods, being less restrictive than the tabular representation. It includes new relations among methods, besides bringing together the connections gathered from different works. It also points out some promising unexplored intermediate regions, which can lead to possible extensions of the existing methods. We also demonstrate one of such possible extensions, which is used to effectively combine the strengths of region and local contrast features.

关键词： image segmentation Communities Labeling Frequency control Transforms Force

来源：评论

学校读者我要写书评

暂无评论

High Level Classification for Pattern Recognition

High Level Classification for Pattern Recognition

引用

brazilian symposium on computer graphics and image processing (SIBGRAPI)

作者： thiago Silva thiago Cupertino Liang Zhao Department of Computer Sciences Institute of Mathematics and Computer Science (ICMC) University of São Paulo Sao Carlos Sao Paulo Brazil

Traditional data classification techniques consider only physical features of input data in order to construct their hypotheses. On the other hand, the human (animal) brain performs both low and high order learning and it has facility to identify patterns according to the semantic meaning of input data. In this paper, we propose a data classification technique by combining the low level and the high level learning. the low level term can be implemented by any classification technique, while the high level classification is realized by the extraction of features of the underlying network constructed from the input data. thus, the former classifies data instances by their physical features, while the latter measures the compliance to the pattern formation of the data. Our study shows that the proposed technique can not only realize classification according to the pattern formation, but it is also able to improve the performance of traditional classification techniques. An application on handwritten digits recognition is performed, revealing that higher classification rates can be obtained when we have a proper mixture of low and high level classifiers.

关键词： Semantics Feature extraction Complex networks Pattern formation Artificial neural networks Training Data mining

来源：评论

学校读者我要写书评

暂无评论

Watershed-Based Segmentation of the Midsagittal Section of the Corpus Callosum in Diffusion MRI

Watershed-Based Segmentation of the Midsagittal Section of t...

引用

brazilian symposium on computer graphics and image processing (SIBGRAPI)

作者： Pedro Freitas Leticia Rittner Simone Appenzeller Roberto Lotufo School of Electrical and Computer Engineering State University of Campinas-UNICAMP Campinas Sao Paulo Brazil Department of Medicine Rheumatology Unit State University of Campinas-UNICAMP Campinas Sao Paulo Brazil

the corpus callosum (CC) is one of the most important white matter structures of the brain, interconnecting the two cerebral hemispheres. the corpus callosum is related to several neurodegenerative diseases and, as segmentation is usually the first step for studies in this structure, it is important to have a robust method for CC segmentation. We propose here a new approach for fully automatic segmentation of the CC in the magnetic resonance diffusion tensor images. the method uses the watershed transform and is performed on the fractional anisotropy (FA) map weighted by the projection of the principal eigenvector in the left-right direction. It first computes the section of the CC in the midsagittal slice and uses it as a seed for the 3D volume segmentation. Experiments with real diffusion MRI data showed that the proposed method is able to quickly segment the CC without any user intervention, with great results when compared to manual segmentation. Since it is simple, fast and does not require parameter settings, the proposed method is well suited for clinical applications.

关键词： image segmentation Transforms Diffusion tensor imaging Anisotropic magnetoresistance three dimensional displays Tensile stress Manuals

来源：评论

学校读者我要写书评

暂无评论

View Clustering of Wide-Baseline N-views for Photo Tourism

View Clustering of Wide-Baseline N-views for Photo Tourism

引用

brazilian symposium on computer graphics and image processing (SIBGRAPI)

作者： Aveek Brahmachari Sudeep Sarkar Computer Science and Engineering University of South Florida Tampa FL USA

the problem of view clustering is concerned with finding connected sets of overlapping views in a collection of photographs. the view clusters can be used to organize a photo collection, traverse through a collection, or for 3D structure estimation. For large datasets, geometric matching of all image pairs via pose estimation to decide on content overlap is not viable. the problem becomes even more acute if the views in the collection are separated by wide baselines, i.e. we do not have a dense view sampling of the 3D scene that leads to increase in computational cost of epipolar geometry estimation and matching. We propose an efficient algorithm for clustering of such many weakly overlapping views, based on opportunistic use of epipolar geometry estimation for only a limited number of image pairs. We cast the problem of view clustering as finding a tree structure graph over the views, whose weighted links denote likelihood of view overlap. the optimization is done in an iterative fashion starting from an minimum spanning tree based on photometric distances between image pairs. At each iteration step, we rule out edges with low confidence of overlap between the respective views, based on epipolar geometry estimates. the minimum spanning tree is recomputed and the process is repeated until there is no further change in the link structure. We show results on the images in the 2010 Nokia Grand Challenge Dataset that contains images with low overlap with each other.

关键词： Geometry Estimation Cameras Training three dimensional displays Global Positioning System Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Discriminant Component Analysis and Self-Organized Manifold Mapping for Exploring and Understanding image Face Spaces

Discriminant Component Analysis and Self-Organized Manifold ...

引用

Tutorials of the brazilian symposium on computer graphics and image processing (SIBGRAPI TUTORIALS)

作者： Gilson A. Giraldi Edson C. Kitani Emilio Del-Moral-Hernandez Carlos E. thomaz Department of Computer Science National Laboratory for Scientific Computing Petropolis Brazil Polytechnic School University of São Paulo Sao Paulo Brazil Department of Electrical Engineering Centro Universitario da FEI Sao Bernardo do Campo Brazil

Face recognition is a multidisciplinary field that involves subjects in neuroscience, computer science and statistical learning. Some recent research in neuroscience has indicated that the ability of our memory relies on the capability of orthogonalizing (pattern separation) and completing (pattern prototyping) partial patterns in order to encode, store and recall information. From a computational viewpoint, pattern separation can be cast in the subspace learning area while pattern prototyping is closer to manifold learning methods. So, subspace (or manifold) learning techniques have a close biological inspiration and reasonability in terms of computational methods to possibly exploring and understanding the human behavior of recognizing faces. therefore, the aim of this paper is threefold. Firstly, we review some theoretical aspects about perceptual and cognitive processes related to the mechanisms of pattern separation and pattern prototyping. then, the paper presents the basic idea of manifold learning and its relationship with subspace learning with focus on the dimensionality reduction problem. Finally, we present the Discriminant Principal Component Analysis (DPCA) and the Self-Organized Manifold Mapping (SOMM) algorithm to exemplify respectively pattern separation and completion techniques. We show experimental results to demonstrate the effectiveness of DPCA and SOMM algorithms on well-framed face image analysis.

关键词： Manifolds Humans Face recognition Vectors Support vector machines Neurons Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning for Human Action Recognition

Transfer Learning for Human Action Recognition

引用

brazilian symposium on computer graphics and image processing (SIBGRAPI)

作者： Ana Paula Lopes Elerson Santos Eduardo Valle Jussara Almeida Arnaldo Araujo Depart. of Exact and Tech. Sciences - Universidade Estadual de Santa Cruz (UESC) Ilhéus BA Brazil Depart. of Computer Science - Universidade Federal de Minas Gerais (UFMG) Belo Horizonte MG Brazil Institute of Computation - Universidade Estadual de Campinas (UNICAMP) Campinas SP Brazil

To manually collect action samples from realistic videos is a time-consuming and error-prone task. this is a serious bottleneck to research related to video understanding, since the large intra-class variations of such videos demand training sets large enough to properly encompass those variations. Most authors dealing with this issue rely on (semi-) automated procedures to collect additional, generally noisy, examples. In this paper, we exploit a different approach, based on a Transfer Learning (TL) technique, to address the target task of action recognition. More specifically, we propose a framework that transfers the knowledge about concepts from a previously labeled still image database to the target action video database. It is assumed that, once identified in the target action database, these concepts provide some contextual clues to the action classifier. Our experiments with Caltech256 and Hollywood2 databases indicate: (a) the feasibility of successfully using transfer learning techniques to detect concepts and, (b) that it is indeed possible to enhance action recognition with the transferred knowledge of even a few concepts. In our case, only four concepts were enough to obtain statistically significant improvements for most actions.

关键词： Videos Databases Training Kernel Feature extraction Support vector machines Visualization

来源：评论

学校读者我要写书评

暂无评论

Combining Dialectical Optimization and Gradient Descent Methods for Improving the Accuracy of Straight Line Segment Classifiers

Combining Dialectical Optimization and Gradient Descent Meth...

引用

brazilian symposium on computer graphics and image processing (SIBGRAPI)

作者： Rosario Medina Rodriguez Ronaldo Hashimoto Institute of Mathematics and Statistics IME Department of Computer Science University of Sao Paulo Sao Paulo Brazil

A recent published pattern recognition technique called Straight Line Segment (SLS) uses two sets of straight line segments to classify a set of points from two different classes and it is based on distances between hese points and each set of straight line segments. It has been demonstrated that, using this technique, it is possible to generate classifiers which can reach high accuracy rates for supervised pattern classification. However, a critical issue in this technique is to find the optimal positions of the straight line segments given a training data set. this paper proposes a combining method of the dialectical optimization method (DOM) and the gradient descent technique for solving this optimization problem. the main advantage of DOM, such as any evolutionary algorithm, is the capability of escaping from local optimum by multi-point stochastic searching. On the other hand, the strength of gradient descent method is the ability of finding local optimum by pointing the direction that maximizes the objective function. Our hybrid method combines the main characteristics of these two methods. We have applied our combining approach to several data sets obtained from artificial distributions and UCI databases. these experiments show that the proposed algorithm in most cases has higher classification rates with respect to single gradient descent method and the combination of gradient descent with genetic algorithms.

关键词： Training Optimization methods Probability density function Pattern recognition Training data Vectors

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112页 << < 54 55 56 57 58 59 60 61 62 63 > >>

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：