检索结果-内蒙古大学图书馆

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

作者： Beltran, Lizeth A. C. dos Santos, Jorge Luiz Cruz, Carolina Uribe Freitas, Carla M. D. S. Fed Univ Rio Grande do Sul UFRGS Inst Informat Porto Alegre RS Brazil Univ Beira Interior Ctr Invest Ciencias Saude Covilha Portugal Lab Expt Hepatol & Gastroenterol Porto Alegre RS Brazil

ISBN: (纸本)9781509035687

Confocal microscopy is an important tool for visualizing 3D datasets of fluorescent specimens, and has been used to investigate the structure of biological specimens. However, such images are affected by the noise introduced during the specimen preparation and image acquisition processes. Anisotropic diffusion is a non-linear filter that can significantly improve image quality while removing noise without blurring edges. this study investigates the application of anisotropic diffusion in confocal microscopy images by exploring different models for parameters' estimation. Our data consists of several slices of extrahepatic bile ducts containing a network of small vessels named Peribiliary Vascular Plexus (PVP), which are affected by several sources of noise. Experimental results show that anisotropic diffusion improved the volumetric visualization of the PVP. We validated the results using MSE and PSNR quantitative approaches and qualitative description by an expert user.

关键词： Anisotropic diffusion image processing Confocal microscopic images Volumetric Visualization

来源：评论

学校读者我要写书评

暂无评论

Neural Networks for Implicit Representations of 3D Scenes 34

Neural Networks for Implicit Representations of 3D Scenes

引用

34th SIBGRAPI Conference on graphics, Patterns and images (SIBGRAPI)

作者： Schirmer, Luiz Schardong, Guilherme da Silva, Vinicius Lopes, Helio Novello, Tiago Yukimura, Daniel Magalhaes, thales Paz, Hallison Velho, Luiz Pontificia Univ Catolica Rio de Janeiro PUC Rio Rio De Janeiro RJ Brazil Inst Matemat Pura & Aplicada IMPA Rio De Janeiro RJ Brazil

ISBN: (纸本)9781665423540

this survey presents methods that use neural networks for implicit representations of 3D geometry - neural implicit functions. We explore the different aspects of neural implicit functions for shape modeling and synthesis. We aim to provide a theoretical analysis of 3D shape reconstruction using deep neural networks and introduce a discussion between researchers interested in this research field.

关键词： Geometry Deep learning three-dimensional displays Shape Neural networks image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Transmitting What Matters: Task-oriented video composition and compression 29

Transmitting What Matters: Task-oriented video composition a...

引用

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

作者： Andalo, Fernanda A. Penatti, Otavio A. B. Testoni, Vanessa Samsung Res Inst Campinas SP Brazil

ISBN: (纸本)9781509035687

We present a simple yet effective framework Transmitting What Matters (TWM) - to generate compressed videos containing only relevant objects targeted to specific computer vision tasks, such as faces for the task of face expression recognition, license plates for the task of optical character recognition, among others. TWM takes advantage of the final desired computer vision task to compose video frames only with the necessary data. the video frames are compressed and can be stored or transmitted to powerful servers where extensive and time-consuming tasks can be performed. We experimentally present the trade-offs between distortion and bitrate for a wide range of compression levels, and the impact generated by compression artifacts on the accuracy of the desired vision task. We show that, for one selected computer vision task, it is possible to dramatically reduce the amount of required data to be stored or transmitted, without compromising accuracy.

关键词： frame composition object detection and tracking video compression computer vision applications

来源：评论

学校读者我要写书评

暂无评论

Implementation of an image Stitching Algorithm to a Low-Cost Digital Microscope 30

Implementation of an Image Stitching Algorithm to a Low-Cost...

引用

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

作者： Botan, Renan Coco, Klaus Fabian Komati, Karin Satie Univ Fed Espirito Santo Inst Fed Espirito Santo Vitoria Espirito Santo Brazil Univ Fed Espirito Santo Vitoria Espirito Santo Brazil Inst Fed Espirito Santo Vitoria Espirito Santo Brazil

ISBN: (纸本)9781538622193

In this work we propose an implementation approach to a feature-based algorithm that stitch images which comes form MicroScanner, a low cost digital microscope created at Mogai Information Technology. this program solve the trade-off problem between field of view and resolution. these codes were developed in C++ language, with help of OpenCV library. the sequence of pictures taken is used by the program to reduce computing costs and increase reliability of the resulting mosaic. In addition, the results achieved maintain the quality from original images, and presents better quality and more effective results than previous related works.

关键词： Microscopy Optical microscopy Biomedical optical imaging Optical imaging Robustness Mathematical model image resolution

来源：评论

学校读者我要写书评

暂无评论

Accessing CUDA features in the OpenGL rendering pipeline: A case study using N-Body simulation 30

Accessing CUDA features in the OpenGL rendering pipeline: A ...

引用

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

作者： Camillo, Mario Santos Wu Shin-Ting Univ Estadual Campinas Sch Elect & Comp Engn Campinas SP Brazil

ISBN: (纸本)9781538622193

the advances of the graphics programing unit (GPU) architecture and its rapidly evolving towards general purpose GPU make a series of applications adopt a general purpose (GPGPU) and a graphics computing interoperability approach in which the first is used for heavy calculations and the second for 3D graphics rendering. Because GPGPU exposes several hardware features, such as shared memory and thread synchronization mechanism, it allows a developer to write more efficient code. Nevertheless, we conjecture that such hardware features are also available in the graphics computing interface OpenGL 4.5 or later through the graphics concepts: blending, transform feedback, tessellation and instancing. In this paper we assess our conjecture by implementing an N-body simulation with both approaches. We indeed devise a novel non-graphics application to the tessellation hardware and the instanced rendering circuit. Instead of refining a mesh, we use the abstract patch for gaining direct accesses to shared memory. In the place of drawing multiple objects, we apply the instanced rendering technology for improving sequential data accesses. Comparative timing analysis is provided. We believe that these results provide better understanding of the graphics features that are useful for closing the performance gap between OpenGL and a GPGPU architecture, and open a new perspective on implementing solely with the OpenGL graphics applications that require both intense, but pre-specified, memory accesses and 3D graphics rendering.

关键词： graphics processing units Rendering (computer graphics) Pipelines Computational modeling computer architecture Programming

来源：评论

学校读者我要写书评

暂无评论

Multiview range image registration using the surface interpenetration measure

引用

image AND VISION COMPUTING 2007年第1期25卷 114-125页

作者： Silva, L. Bellon, O. R. P. Boyer, K. L. Univ Fed Parana Ctr Politecn Dept Informat BR-81531 Curitiba Parana Brazil Ohio State Univ Dept Elect & Comp Engn Columbus OH 43210 USA

this paper presents a new method for the precise registration of multiple range images with low pairwise overlap. the method is based in enhanced genetic algorithms (GAs). the proposed technique minimizes the alignment error within the common overlap area among a set of views, which is computed by a novel robust figure of merit called the surface interpenetration measure (SIM). the key idea behind this measure is the observation that mean squared error alone is insufficient to evaluate the quality of a registration solution because it fails to account for the spatial distribution of the error. the new measure explicitly forces the solution to distribute the errors across the overlap area, producing more stable, reliable solutions that limit propagation and amplification of error in the multiview problem. Our approach is not dependent on GAs as the search mechanism, but because they search in a space of transformations, GAs are capable of registering surfaces with no need for prealignment. the need for prealignment is a major weakness of methods based on the iterative closest point (ICP) algorithm, the most popular family of methods to date. the experimental results confirm that the new method ensures more precise global alignments than combined sequential pairwise alignments for registration. (c) 2006 Elsevier B.V. All rights reserved.

关键词： range images multiview registration simulated annealing genetic algorithms robust methods surface interpenetration measure

来源：评论

学校读者我要写书评

暂无评论

Fast Spatial-Temporal Transformer Network 34

Fast Spatial-Temporal Transformer Network

引用

34th SIBGRAPI Conference on graphics, Patterns and images (SIBGRAPI)

作者： Escher, Rafael Molossi de Bem, Rodrigo Andrade Jorge Drews Jr, Paulo Lilles Fed Univ Rio Grande Rio Grande Brazil

ISBN: (纸本)9781665423540

In computer vision, the restoration of missing regions in an image can be tackled with image inpainting techniques. Neural networks that perform inpainting in videos require the extraction of information from neighboring frames to obtain a temporally coherent result. the state-of-the-art methods for video inpainting are mainly based on Transformer Networks, which rely on attention mechanisms to handle temporal input data. However, such networks are highly costly, requiring considerable computational power for training and testing, which hinders its use on modest computing platforms. In this context, our goal is to reduce the computational complexity of state-of-the-art video inpainting methods, improving performance and facilitating its use in low-end GPUs. therefore, we introduce the Fast Spatio-Temporal Transformer Network (FastSTTN), an extension of the Spatio-Temporal Transformer Network (STTN) in which the adoption of Reversible Layers reduces memory usage up to 7 times and execution time by approximately 2.2 times, while maintaining state-of-the-art video inpainting accuracy.

关键词： Training graphics computer vision Neural networks Transformers image restoration Data mining

来源：评论

学校读者我要写书评

暂无评论

Pap-smear image classification by using a fusion of texture features 35

Pap-smear image classification by using a fusion of texture ...

引用

35th SIBGRAPI Conference on graphics, Patterns and images (SIBGRAPI)

作者： Backes, Andre Ricardo Univ Fed Uberlandia Sch Comp Sci Ave Joao Naves Avila 2121 BR-38408100 Uberlandia MG Brazil

ISBN: (数字)9781665453851

ISBN: (纸本)9781665453851

In this paper we address the problem of pap-smear image classification. these images have great medical importance to diagnose and prevent uterine cervix cancer and have been intensively studied in computer vision research. We evaluated 19 texture features on their ability to discriminate between two classes (normal and abnormal) of pap-smear images. We performed the classification of these feature using three different approaches: K-Nearest Neighbors (KNN), Support Vector Machine (SVM) and Linear Discriminant Data (LDA). We conducted this evaluation considering each texture method independently and their concatenation with others. Results show combining methods improves the accuracy, surpassing most of the compared methods, including some deep learning approaches.

关键词： Support vector machines Deep learning graphics computer vision Task analysis Medical diagnostic imaging image classification

来源：评论

学校读者我要写书评

暂无评论

kNarrator: A Model For Authors To Simplify Authoring Process Using Natural Language processing To Portuguese 16

kNarrator: A Model For Authors To Simplify Authoring Process...

引用

16th brazilian symposium on computer Games and Digital Entertainment (SBGames)

作者： Kerber, Adriano Camozzato, Daniel Queiroz, Rossana Cassol, Vinicius Univ Vale Rio Sinos Unisinos Escola Politecn Sao Leopoldo Brazil

ISBN: (纸本)9781538648469

In this paper, we propose a model to help writers to produce narratives or text fragments using only few words as input. the proposed model uses pseudo-text as input and returns full fluid text as output. the facts described in the pseudo-text can be transcribed with a different level of detail set by the user, from a simple sentence to an expanded description, adding details according to a user-defined semantic dictionary. this allows authors to visualize ideas and concepts of narratives. Our model can also be used in games as a tool to generate narratives and descriptions in natural language text. In order to evaluate our approach, we performed a comparative study with some authoring models and results are further discussed.

关键词： Natural Language processing Natural Language Generation Authoring Model Portuguese Storytelling

来源：评论

学校读者我要写书评

暂无评论

Assessing Texture Descriptors for Seismic image Retrieval 30

Assessing Texture Descriptors for Seismic Image Retrieval

引用

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

作者： Mattos, Andrea Britto Ferreira, Rodrigo S. da Gama e Silva, Reinaldo M. Riva, Mateus Brazil, Emilio Vital IBM Res Rio De Janeiro Brazil Univ Sao Paulo IME Sao Paulo Brazil

ISBN: (纸本)9781538622193

Much work has been done on the assessment of texture descriptors for image retrieval in many domains. In this work, we evaluate the accuracy and performance of three well-known texture descriptors - Gabor Filters, GLCM, and LBP - for seismic image retrieval. these subsurface images pose challenges yet not thoroughly investigated in previous works, which are addressed and evaluated in our experiments. We asked for domain experts to annotate two seismic cubes, Penobscot 3D and Netherlands F3, and used them to evaluate texture descriptors, corresponding parameters, and similarity metrics with the potential to retrieve visually similar regions of the considered datasets. While GLCM is used in the vast majority of works in this area, our findings indicate that LBP has the potential to produce satisfying results with lower computational cost.

关键词： image retrieval three-dimensional displays Gabor filters Entropy Feature extraction Visualization

来源：评论

学校读者我要写书评

暂无评论

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：

请选择收藏分类：

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

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：