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

100 篇 会议

馆藏范围

100 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

35 篇 工学
- 30 篇 计算机科学与技术...
- 27 篇 软件工程
- 5 篇 光学工程
- 5 篇 电气工程
- 4 篇 电子科学与技术（可...
- 3 篇 控制科学与工程
- 2 篇 生物医学工程（可授...
- 1 篇 力学（可授工学、理...
- 1 篇 材料科学与工程（可...
- 1 篇 信息与通信工程
- 1 篇 建筑学
- 1 篇 土木工程
- 1 篇 化学工程与技术
- 1 篇 纺织科学与工程
- 1 篇 农业工程
20 篇 理学
- 16 篇 数学
- 6 篇 物理学
- 3 篇 统计学（可授理学、...
- 1 篇 化学
- 1 篇 系统科学
5 篇 医学
- 5 篇 临床医学
- 1 篇 基础医学(可授医学...
- 1 篇 药学(可授医学、理...
2 篇 管理学
- 1 篇 管理科学与工程(可...
- 1 篇 图书情报与档案管...
1 篇 法学
- 1 篇 社会学
1 篇 农学
- 1 篇 作物学

主题

24 篇 image segmentati...
12 篇 pixel
12 篇 image analysis
11 篇 computer graphic...
10 篇 image processing
10 篇 image reconstruc...
10 篇 layout
8 篇 algorithm design...
7 篇 computer vision
7 篇 shape
7 篇 color
6 篇 digital images
6 篇 image edge detec...
6 篇 humans
6 篇 robustness
6 篇 image resolution
5 篇 neural networks
5 篇 handwriting reco...
5 篇 visualization
5 篇 feature extracti...

机构

6 篇 universidade de ...
3 篇 impa-instituto d...
3 篇 instituto de mat...
3 篇 pontificia unive...
2 篇 pucpr-pontifícia...
2 篇 faculty of elect...
2 篇 univ sao paulo i...
2 篇 instituto de mat...
2 篇 npdi/dcc/ufmg de...
2 篇 universidade est...
2 篇 nucleus of scien...
1 篇 computing and ap...
1 篇 instituto de mat...
1 篇 department of el...
1 篇 grupo sensores i...
1 篇 univ fed mato gr...
1 篇 ets - ecole de t...
1 篇 informatics depa...
1 篇 federal universi...
1 篇 ecole nationale ...

作者

4 篇 wu shin-ting
4 篇 r. sabourin
4 篇 f. bortolozzi
3 篇 r.a. lotufo
3 篇 j. barbera
3 篇 velho luiz
3 篇 a. el yacoubi
3 篇 miranda paulo a....
2 篇 flores franklin ...
2 篇 f.c. flores
2 篇 meyer fernand
2 篇 barrera junior
2 篇 j.m. de carvalho
2 篇 a.d.a. araujo
2 篇 m. gattass
2 篇 a. de albuquerqu...
2 篇 hirata roberto
2 篇 f. meyer
2 篇 s.j.f. guimaraes
2 篇 r.m. cesar

语言

100 篇 英文

检索条件"任意字段=13th Brazilian Symposium on Computer Graphics and Image Processing, SIBGRAPI 2000"

共 100 条记录，以下是1-10 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：

Few-shot Retinal Disease Classification on the brazilian Multilabel Ophtalmological Dataset 37

Few-shot Retinal Disease Classification on the Brazilian Mul...

引用

37th sibgrapi Conference on graphics, Patterns and images (sibgrapi)

作者： Perin, Gabriel J. Hirata, Nina S. T. Univ Sao Paulo Inst Math & Stat Sao Paulo Brazil

ISBN: (纸本)9798350376043;9798350376036

Motivated by the inherent data scarcity in the medical domain, this work studies few-shot retinal disease classification, using the brazilian Multilabel Ophtalmological Dataset. We compare different network architectures and non-trivial data augmentations under the application of the Reptile Algorithm, conducting quantitative and qualitative analysis. Regarding the architectures, we observe that Swin outperforms ViT and ResNet. We also observe that clever data augmentations not only improve performance, but can also generate prediction confidence distributions that are more interpretable and trustworthy. Furthermore, pre-training the models with domain-specific data leads to superior ability of the models to detect the relevant patterns in the images. Code is available at ***/gabjp/few-shot-BRSET.

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

Extending the Differential image Foresting Transform to Root-based Path-cost Functions with Application to Superpixel Segmentation 30

Extending the Differential Image Foresting Transform to Root...

引用

30th Conference on graphics, Patterns and images (sibgrapi)

作者： Condori, Marcos A. T. Cappabianco, Fabio A. M. Falcao, Alexandre X. Miranda, Paulo A. V. Univ Sao Paulo Inst Math & Stat Sao Paulo SP Brazil Univ Fed Sao Paulo Inst Ciencia & Tecnol Sao Jose Dos Campos SP Brazil Univ Estadual Campinas Inst Comp Campinas SP Brazil

ISBN: (纸本)9781538622193

the image Foresting Transform (IFT) is a general framework to develop image processing tools for a variety of tasks such as image segmentation, boundary tracking, morphological filtering, pixel clustering, among others. the Differential image Foresting Transform (DIFT) comes in handy for scenarios where multiple iterations of IFT over the same image with small modifications on the input parameters are expected, reducing the processing complexity from linear to sublinear with respect to the number of pixels. In this paper, we propose an enhanced variant of the DIFT algorithm that avoids inconsistencies, when the connectivity function is not monotonically incremental. Our algorithm works with the classical and non-classifical connectivity functions based on root position. Experiments were conducted on a superpixel task, showing a significant improvement to a state-of-the-art method.

关键词： image segmentation Transforms Cost function graphics

来源：评论

学校读者我要写书评

暂无评论

Multi-Object Segmentation by Hierarchical Layered Oriented image Foresting Transform 30

Multi-Object Segmentation by Hierarchical Layered Oriented I...

引用

30th sibgrapi Conference on graphics, Patterns and images Tutorials (sibgrapi-T)

作者： Castaneda Leon, Leissi M. Miranda, Paulo A. V. Univ Sao Paulo Inst Math & Stat Sao Paulo SP Brazil

ISBN: (纸本)9781538622193

this paper introduces a new method for multi-object segmentation in images, named as Hierarchical Layered Oriented image Foresting Transform (HLOIFT). As input, we have an image, a tree of relations between image objects, with the individual high-level priors of each object coded in its nodes, and the objects' seeds. Each node of the tree defines a weighted digraph, named as layer. the layers are then integrated by the geometric interactions, such as inclusion and exclusion relations, extracted from the given tree into a unique weighted digraph, named as hierarchical layered digraph. A single energy optimization is performed in the hierarchical layered weighted digraph by Oriented image Foresting Transform (OIFT) leading to globally optimal results satisfying all the high-level priors. We evaluate our framework in the multi-object segmentation of medical and synthetic images, obtaining results comparable to the state-of-the-art methods, but with low computational complexity. Compared to multi-object segmentation by min-cut/max-flow algorithm, our approach is less restrictive, leading to globally optimal results in more general scenarios.

关键词： image segmentation Transforms Optimization Vegetation Object segmentation Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Oriented image Foresting Transform Segmentation: Connectivity Constraints with Adjustable Width 29

Oriented Image Foresting Transform Segmentation: Connectivit...

引用

29th sibgrapi Conference on graphics, Patterns and images (sibgrapi)

作者： Mansilla, Lucy A. C. Miranda, Paulo A. V. Univ Sao Paulo Dept Comp Sci BR-05508090 Sao Paulo SP Brazil

ISBN: (纸本)9781509035687

In this work, we extend a novel seed-based segmentation algorithm, which provides global optimum solutions according to a graph-cut measure, subject to high-level boundary constraints: the simultaneously handling of boundary polarity and connectivity constraints. the proposed method incorporates the connectivity constraint in the Oriented image Foresting Transform (OIFT), ensuring the generation of connected objects, but such that the connection between its internal seeds is guaranteed to have a user-controllable minimum width. In other frameworks, such as the min-cut/max-flow algorithm, the connectivity constraint is known to lead to NP-hard problems. In contrast, our method conserves the low complexity of the OIFT algorithm. In the experiments, we show improved results for the segmentation of thin and elongated objects, for the same amount of user interaction. Our dataset of natural images with true segmentation is publicly available to the community.

关键词： image segmentation connectivity constraints boundary polarity image foresting transform

来源：评论

学校读者我要写书评

暂无评论

Ray-Traced Reflections in Real-Time Using Heuristic Based Hybrid Rendering 13

Ray-Traced Reflections in Real-Time Using Heuristic Based Hy...

引用

13th brazilian symposium on computer Games and Digital Entertainment (SBGAMES)

作者： Andrade, Paulo Sabino, thales Clua, Esteban Pagliosa, Paulo Univ Fed Fluminense Inst Comp Medialab Niteroi RJ Brazil Pontificia Univ Catolica Estado Rio De Janeiro Tecgraf Rio De Janeiro Brazil Univ Fed Mato Grosso do Sul FACOM Campo Grande Brazil

ISBN: (纸本)9781479980659

Game engines typically use cube maps or screen space local reflections for simulating reflections effects at the real-time renderer pipeline. While these techniques work in many situations, they cannot deal well with reflections of reflections, reflections from covered spaces, reflections from elements outside the screen space or reflections from elements that change its shape or position in real-time. In this paper, we present a method capable of creating true real-time ray-traced reflections by using a heuristic based method and a hybrid renderer. Our solution maintain real-time frame rates by selecting, for each frame, the best reflexive surfaces to ray trace, based on the users point of view.

关键词： computer graphics ray-tracing parallel processing image generation

来源：评论

学校读者我要写书评

暂无评论

Graph-based object tracking using structural pattern recognition

Graph-based object tracking using structural pattern recogni...

引用

20th brazilian symposium on computer graphics and image processing, sibgrapi 2007

作者： Graciano, Ana B. V. Cesar Jr., Roberto M. Bloch, Isabelle Institute of Mathematics and Statistics - USP Department of Computer Science Rua do Matão 1010 São Paulo SP 05508-900 Brazil Dept. TSI GET-ENST CNRS - UMR 5141 LTCI 46 Rue Barrault F-75634 Cedex 13 Paris France

ISBN: (纸本)0769529968

this paper proposes a model-based methodology for recognizing and tracking objects in digital image sequences. Objects are represented by attributed relational graphs (or ARGs), which carry both local and relational information about them. the recognition is performed by inexact graph matching, which consists in finding an approximate homomorphism between ARGs derived from an input video and a model image. Searching for a suitable homomorphism is achieved through a tree-search optimization algorithm and the minimization of a pre-defined cost function. Motion smoothness between successive frames is exploited to achieve the recognition over the whole sequence, with improved spatio-temporal coherence. © 2007 IEEE.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

AFRIGRAPH: computer graphics in Africa

AFRIGRAPH: Computer graphics in Africa

引用

18th brazilian symposium on computer graphics and image processing (sibgrapi 2005)

作者： Gain, J. E. Strasser, W. Univ Cape Town Collaborat Visual Comp Lab ZA-7925 Cape Town South Africa Univ Tubingen Wilhelm Schickard Inst Informat Graph Interakt Sy D-7400 Tubingen Germany

Afrigraph is an organization whose purpose is to help consolidate and promote the practice of relevant computer graphics in Africa in academia, the arts and industry. It was formed as a result of ACM SIGGRAPH initiatives beginning in 2000 and culminating in it being constituted as a professional body complete with a constitution modeled on that of ACM SIGGRAPH. the mandate of the organization also includes local issues such as the digital divide, curriculum design and intellectual property affecting growth and development of computer graphics in Africa. the papers and tutorials of the conferences have been wide-ranging including digital reconstruction of African art works, relighting of archaeological sites and automated sign language translation. Topics in Virtual Reality, computer graphics, Visualization and Interaction have also been well represented.

关键词： computer graphics

来源：评论

学校读者我要写书评

暂无评论

Reduction of interband correlation for landsat image compression

Reduction of interband correlation for landsat image compres...

引用

sibgrapi 2005: 18th brazilian symposium on computer graphics and image processing - Conference Proceedings

作者： Acevedo, Daniel G. Ruedin, Ana M. C. Departamento de Computatión Facultad de Ciencias Exactas y Naturales Universidad de Buenos Aires

ISBN: (纸本)0769523897

We present a lossless compressor for multispectral images that exploits interband correlations. Each band is divided into blocks, to which a wavelet transform is applied. the wavelet coefficients are predicted by means of a linear combination of coefficients belonging to the same orientation and spatial location. the prediction errors are then encoded with an entropy - based coder. Our original contributions are i) the inclusion, among the candidates for prediction, of coefficients of the same location from other spectral bands, ii) the calculation of weights tuned to the landscape being processed, iii) a fast block classification and a different band-ordering for each landscape. Our compressor reduces the size of an image to about a fourth of its original size. Our method is equivalent to LOCO-I, on 3 of the images tested it was superior. It is superior to other lossless compressors: WinZip, JPEG2000 and PNG. © 2005 IEEE.

关键词： image compression

来源：评论

学校读者我要写书评

暂无评论

Reconfigurable designs for radiosity

Reconfigurable designs for radiosity

引用

Annual IEEE symposium on Field-Programmable Custom Computing Machines (FCCM)

作者： P. Baker T. Todman H. Styles W. Luk Department of Computing Imperial College London London UK

We develop reconfigurable designs to support radiosity, a computer graphics algorithm for producing highly realistic images of artificial scenes, but which is computationally expensive. We implement radiosity using stochastic raytracing, which affords both instruction-level and data parallelism. Our designs are parameterisable by bitwidth, allowing trade-offs between image quality and computation speed. We measure the speed of our designs for a Xilinx XC2V6000 device in the Celoxica RC2000 platform: at 53 MHz it can run up to five times faster than a software implementation on an Athlon MP 2600+ processor at 2.1 GHz. We estimate that retargeting our design for a Virtex-4 XCVSX55 device can result in over 160 times software speed, while a Spartan-3 XC3S5000 device can run more than 40 times faster than the software implementation.

关键词： Lighting computer graphics Layout Hardware Acceleration Bismuth Educational institutions Algorithm design and analysis Stochastic processes Parallel processing

来源：评论

学校读者我要写书评

暂无评论

Level lines continuation based digital inpainting

Level lines continuation based digital inpainting

引用

brazilian symposium on computer graphics and image processing (sibgrapi)

作者： C.A.Z. Barcelos M.A. Batista A.M. Martins A.C. Nogueira Universidade Federal de Uberlândia Brazil Universidade Federal de Uberlândia Uberlandia Minas Gerais Brazil

Inpainting digital models have been since the late 1990s a powerful image reconstruction tool for missing data. After the original work of Bertalmio et al. (2000) several different approaches have been used to tackle the problem. Some are based on partial differential equations to model a transport process and a diffusion process, others are based on the Euler elastica functional. this paper presents a model using the level lines continuation to perform the filling-in of the inpainting domain D. the model is proposed in a way as to satisfy the "connectivity principle". the image u(x,y) is represented by a family of level lines and the missing part of the image is filled-in by the propagation of the available surrounding information, from outside to inside of the inpainting domain D along the level lines of the image. After defining the domain D the restoration process becomes automatic and the final result u(x,y,t/sub n/) is carried out by the evolutionary process starting with the initial degraded image u(x,y,0). Examples on real and textured images show the performance of this proposed model.

关键词： image restoration image reconstruction image processing Partial differential equations Degradation Humans Diffusion processes Digital images Bridges Layout

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10页 << < 1 2 3 4 5 6 7 8 9 10 > >>

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：