检索结果-内蒙古大学图书馆

28th SIBGRAPI Conference on graphics, Patterns and images SIBGRAPI

作者： Bastos, Igor L. O. Angelo, Michele F. Loula, Angelo C. Univ Fed Bahia Math Inst Salvador BA Brazil State Univ Feira Santana UEFS Dept Exact Sci Dept Technol Feira De Santana Brazil

ISBN: (纸本)9781467379625

this paper aims at describing an approach developed for the recognition of gestures on digital images. In this way, two shape descriptors were used: the histogram of oriented gradients (HOG) and Zernike invariant moments (ZIM). A feature vector composed by the information acquired with both descriptors was used to train and test a two stage Neural Network, which is responsible for performing the recognition. In order to evaluate the approach in a practical context, a dataset containing 9600 images representing 40 different gestures (signs) from brazilian Sign Language (Libras) was composed. this approach showed high recognition rates (hit rates), reaching a final average of 96.77%.

关键词： Histogram of Oriented Gradients Zernike Invariant Moments Neural Networks Gesture Recognition Libras

来源：评论

学校读者我要写书评

暂无评论

Everything you wanted to know about Deep Learning for computer Vision but were afraid to ask 30

Everything you wanted to know about Deep Learning for Comput...

引用

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

作者： Ponti, Moacir A. Ribeiro, Leonardo S. F. Nazare, Tiago S. Bui, Tu Collomosse, John Univ Sao Paulo ICMC BR-13566590 Sao Carlos SP Brazil Univ Surrey CVSSP Guildford GU2 7XH Surrey England

ISBN: (纸本)9781538606193

Deep Learning methods are currently the state-of-the-art in many computer Vision and image processing problems, in particular image classification. After years of intensive investigation, a few models matured and became important tools, including Convolutional Neural Networks (CNNs), Siamese and Triplet Networks, Auto-Encoders (AEs) and Generative Adversarial Networks (GANs). the field is fast-paced and there is a lot of terminologies to catch up for those who want to adventure in Deep Learning waters. this paper has the objective to introduce the most fundamental concepts of Deep Learning for computer Vision in particular CNNs, AEs and GANs, including architectures, inner workings and optimization. We offer an updated description of the theoretical and practical knowledge of working with those models. After that, we describe Siamese and Triplet Networks, not often covered in tutorial papers, as well as review the literature on recent and exciting topics such as visual stylization, pixel-wise prediction and video processing. Finally, we discuss the limitations of Deep Learning for computer Vision.

关键词： computer Vision Deep Learning image processing Video processing

来源：评论

学校读者我要写书评

暂无评论

引用

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

作者： Nakanishi, Rafael Umino Ono, Jorge Piazentin Pagliosa, Paulo Nonato, Luis Gustavo Paiva, Afonso Univ Sao Paulo ICMC Sao Carlos SP Brazil NYU Sch Engn New York NY USA Univ Fed Mato Grosso do Sul FACOM Campo Grande Brazil

ISBN: (纸本)9781509035687

this paper presents a novel 3D partial shape retrieval algorithm based on time-series analysis. Given a piece of a 3D shape, the proposed method encodes the shape descriptor given by the Heat Kernel Signature (HKS) as a time-series, where the time is considered an ordered sequence of vertices provided by the Fiedler vector. Finally, a similarity metric is created using a well-known tool in time-series analysis called Cross Recurrence Plot (CRP). the good performance of our method is also attested in a large collection of shape models.

关键词： Partial Shape Retrieval Cross Recurrence Plot Heat Kernel Signature Fiedler Vector Time-Series Analysis Geometry processing

来源：评论

学校读者我要写书评

暂无评论

Quantized features for gesture recognition using high speed vision camera 16

Quantized features for gesture recognition using high speed ...

引用

16th brazilian symposium on computer graphics and image processing

作者： Perrin, S Ishikawa, M Univ Tokyo Ishikawa Hashimoto Lab Bunkyo Ku Tokyo 1138656 Japan

ISBN: (纸本)0769520324

In addition to speech, gestures have been considered as a means of interacting with a computer as naturally as possible. Like speech, gestures can be acquired and recognized using Hidden Markov Models (HMMs), but there are several problems that must be overcome. In this paper we propose solutions to two of these problems: the feature extraction and the HMMs training. First, the acquisition is done by means of a high speed vision camera which allows the position of a hand to be obtained every 1 ms. this simplifies the feature extraction task and also allows low-level fusion with speech to be considered, which is a future goal. Secondly, we introduce quantized features, after carefully selecting extracted features, in order to avoid drastically increasing the size of the gesture database needed for good training of the HMMs. We finally show results that demonstrate the ability of such quantized features to significantly improve the recognition rate despite a rather small database and to allow user-independent recognition of gestures.

关键词： Cameras computer vision Feature extraction Fuzzy logic Hidden Markov models Laboratories Spatial databases Speech recognition Stochastic processes Strontium

来源：评论

学校读者我要写书评

暂无评论

Differential representations for mesh processing

引用

computer graphics FORUM 2006年第4期25卷 789-807页

作者： Sorkine, Olga Tel Aviv Univ Sch Comp Sci IL-69978 Tel Aviv Israel

Surface representation and processing is one of the key topics in computer graphics and geometric modeling, since it greatly affects the range of possible applications. In this paper we will present recent advances in geometry processing that are related to the Laplacian processing framework and differential representations. this framework is based on linear operators defined oil polygonal meshes, and furnishes a variety of processing applications, such as shape approximation and compact representation, mesh editing, watermarking and morphing. the core of the framework is the definition of differential coordinates and new bases for efficient mesh geometry representation, based on the mesh Laplacian operator.

关键词： discrete Laplacian surface representation detail preservation geometry compression mesh editing

来源：评论

学校读者我要写书评

暂无评论

Does the input image spatial resolution generate different synthetic images? A Comparative Study of Facial Expression Synthesis Performance 36

Does the input image spatial resolution generate different s...

引用

36th SIBGRAPI Conference on graphics, Patterns and images (SIBGRAPI)

作者： Testa, Rafael Luiz Machado-Lima, Ariane Nunes, Fatima L. S. Univ Sao Paulo Sch Arts Sci & Humanities Sao Paulo Brazil

ISBN: (纸本)9798350338737;9798350338720

Facial expression synthesis has gained significant attention in the image synthesis field. Generative Adversarial Network (GAN) models have recently gained popularity due to the high-quality synthetic images they produce. However, these models require complex network architectures that can take days to train, even with high-performance graphics processing Units (GPUs). Many efforts have been made to accelerate and compress such models, but little attention has been paid to the resolution of the images. this study aims to assess the impact of input/output spatial resolution on the resources needed for training a facial expression synthesis model, as well as on the quality of the results. Our results indicate that the produced images and videos had similar quality results measured through objective measures for the spatial resolution of 128 x 128, 256 x 256, and 480 x 480. Furthermore, we found that lower-resolution images could significantly reduce the time required to generate new facial expressions without compromising quality, as measured by objective measures.

关键词： graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

image denoising with non-convex models: a comparison between BDCA and nmBDCA 37

Image denoising with non-convex models: a comparison between...

引用

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

作者： Ribeiro, Pedro Henrique Alves Souza, Joao Carlos de Oliveira Fed Inst Maranhao Imperatriz Maranhao Brazil Univ Fed Piaui Teresina Piaui Brazil

ISBN: (纸本)9798350376043;9798350376036

Data acquisition and analysis are important areas for science, directly related to image reconstruction. Much acquired data can be corrupted by various factors, such as external noise sources or those inherent to the application, but can be treated mathematically. this work aims to reconstruct images corrupted by Gaussian and Rician noise, using DC programming and a non-convex version of the total variation (TV) model. the tests are performed with a variation of BDCA (smoothing of the first DC component) and nmBDCA algorithms. the obtained results are evaluated both in quality (PSNR and SSIM) and in CPU time, covering medical computed tomography (CT) images and magnetic resonance images (MRI).

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Detecting computer Generated images with Deep Convolutional Neural Networks 30

Detecting Computer Generated Images with Deep Convolutional ...

引用

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

作者： de Rezende, Edmar R. S. Ruppert, Guilherme C. S. Carvalho, Tiago CTI Renato Archer BR-13069901 Campinas SP Brazil Fed Inst Sao Paulo IFSP BR-13069901 Campinas SP Brazil

ISBN: (纸本)9781538622193

computer graphics techniques for image generation are living an era where, day after day, the quality of produced content is impressing even the more skeptical viewer. Although it is a great advance for industries like games and movies, it can become a real problem when the application of such techniques is applied for the production of fake images. In this paper we propose a new approach for computer generated images detection using a deep convolutional neural network model based on ResNet-50 and transfer learning concepts. Unlike the state-of-the-art approaches, the proposed method is able to classify images between computer generated or photo generated directly from the raw image data with no need for any pre-processing or hand-crafted feature extraction whatsoever. Experiments on a public dataset comprising 9700 images show an accuracy higher than 94%, which is comparable to the literature reported results, without the drawback of laborious and manual step of specialized features extraction and selection.

关键词： Feature extraction Training Neural networks Law Industries Games

来源：评论

学校读者我要写书评

暂无评论

DeepDive: An End-to-End Dehazing Method Using Deep Learning 30

DeepDive: An End-to-End Dehazing Method Using Deep Learning

引用

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

作者： Goncalves, Lucas T. Gaya, Joel O. Drews, Paulo, Jr. Botelho, Silvia S. C. Univ Fed Rio Grande FURG Ctr Computat Sci C3 Intelligent Robot & Automat Grp NAUTEC Rio Grande Brazil

ISBN: (纸本)9781538622193

image dehazing can be described as the problem of mapping from a hazy image to a haze-free image. Most approaches to this problem use physical models based on simplifications and priors. In this work we demonstrate that a convolutional neural network with a deep architecture and a large image database is able to learn the entire process of dehazing, without the need to adjust parameters, resulting in a much more generic method. We evaluate our approach applying it to real scenes corrupted by haze. the results show that even though our network is trained with simulated indoor images, it is capable of dehazing real outdoor scenes, learning to treat the degradation effect itself, not to reconstruct the scene behind it.

关键词： image restoration Neural networks Degradation Training Machine learning Atmospheric modeling computer architecture

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Effects of Dimensionality Reduction for Unsupervised Domain Adaptation 34

Analyzing the Effects of Dimensionality Reduction for Unsupe...

引用

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

作者： Lopes Junior, Renato Sergio Schwartz, William Robson Fed Univ Minas Gerais UFMG Dept Comp Sci Smart Sense Lab Belo Horizonte MG Brazil

ISBN: (纸本)9781665423540

Deep neural networks are extensively used for solving a variety of computer vision problems. However, in order for these networks to obtain good results, a large amount of data is necessary for training. In image classification, this training data consists of images and labels that indicate the class portrayed by each image. Obtaining this large labeled dataset is very time and resource consuming. therefore, domain adaptation methods allow different, but semantic-related, datasets that are already labeled to be used during training, thus eliminating the labeling cost. In this work, the effects of embedding dimensionality reduction in a state-of-the-art domain adaptation method are analyzed. Furthermore, we experiment with a different approach that use the available data from all domains to compute the confidence of pseudo-labeled samples. We show through experiments in commonly used datasets that, in fact, the proposed modifications led to better results in the target domain in some scenarios.

关键词： Training Dimensionality reduction graphics Deep learning computer vision Costs Training data

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：