检索结果-内蒙古大学图书馆

21st brazilian symposium on computer Games and Digital Entertainment (SBGames)

作者： Coutinho, Flavio Chaimowicz, Luiz Univ Fed Minas Gerais Dept Ciencia Comp Belo Horizonte MG Brazil Ctr Fed Educ Tecnol Minas Gerais Dept Comp Belo Horizonte MG Brazil

ISBN: (数字)9781665461566

ISBN: (纸本)9781665461566

Iterating on creating pixel art character sprite sheets is essential to the game development process. However, it can take a lot of effort until the final versions containing different poses and animation clips are achieved. This paper reports an investigation on the use of conditional generative adversarial networks to aid the designers in creating such sprite sheets. We propose an architecture based on Pix2Pix to generate images of characters facing a target side (e.g., right) given sprites of them in a source pose (e.g., front). Experiments with small pixel art datasets yielded promising results, producing models with varying degrees of generalization, sometimes capable of generating images very close to the ground truth. We analyzed the results through visual inspection and quantitatively with FID.

关键词： generative adversarial networks pixel art image-to-image translation procedural content generation

来源：评论

学校读者我要写书评

暂无评论

Asynchronous stroboscopic structured lighting image processing using low-cost cameras 31

Asynchronous stroboscopic structured lighting image processi...

引用

31st Conference on graphics, Patterns and images (SIBGRAPI)

作者： Borsato, Frank H. Morimoto, Carlos H. Univ Tecnol Fed Parana Curitiba Parana Brazil Univ Sao Paulo Sao Paulo Brazil

ISBN: (纸本)9781538692646

structured lighting (SL) image processing relies on the generation of known illumination patterns synchronized with the camera frame rate and is commonly implemented using syncing capable cameras. In general, such cameras employ global shutters, that exposes the whole frame at once. However, most modern digital cameras use rolling shutters, which expose each line at different intervals, impairing most structured lighting applications. In this paper we introduce an asynchronous SL technique that can be used by any rolling shutter digital camera. While the use of stroboscopic illumination partially solves for the line exposure shift, the phase difference between the camera and lighting clocks results in stripe artifacts that move vertically in the video stream. These stripes are detected and tracked using a Kalman filter. Two asynchronous stroboscopic SL methods are proposed. The first method, image differencing, minimizes the stripe artifacts. The second method, image compositing, completely removes the artifacts. We demonstrate the use of the asynchronous differential lighting technique in a pupil detector using a low-cost high-speed camera with no synchronization means, with the lighting running independently at a higher, unknown frequency to the application.

关键词： Lighting Synchronization Frequency synchronization Clocks Software Digital cameras

来源：评论

学校读者我要写书评

暂无评论

A Divide-and-Conquer Clustering Approach based on Optimum-Path Forest 31

A Divide-and-Conquer Clustering Approach based on Optimum-Pa...

引用

31st Conference on graphics, Patterns and images (SIBGRAPI)

作者： Montero, Adan Echemendia Falcao, Alexandre Xavier Univ Estadual Campinas Inst Comp Lab Image Data Sci Campinas SP Brazil

ISBN: (纸本)9781538692646

Data clustering is one of the main challenges when solving Data Science problems. Despite its progress over almost one century of research, clustering algorithms still fail in identifying groups naturally related to the semantics of the problem. Moreover, the technological advances add crucial challenges with a considerable data increase, which are not handled by most techniques. We address these issues by proposing a divide-and-conquer approach to a clustering technique, which is unique in finding one group per dome of the probability density function of the data - the Optimum-Path Forest (OPF) clustering algorithm. Our approach can use all samples, or at least many samples, in the unsupervised learning process without affecting the grouping performance and, therefore, being less likely to lose relevant grouping information. We show that it can obtain satisfactory results when segmenting natural images into superpixels.

关键词： Clustering algorithms Training Forestry Partitioning algorithms Probability density function Vegetation Prototypes

来源：评论

学校读者我要写书评

暂无评论

An egg image noise model for digital visual counting processing 34

An egg image noise model for digital visual counting process...

引用

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

作者： Ramirez Behaine, Carlos Alberto Ide, Jaime S. Univ Passo Fundo UPF Dept Elect Engn BR 285 BR-99052900 Passo Fundo RS Brazil Yale Univ Sch Med 34 Pk St New Haven CT 06519 USA

ISBN: (纸本)9781665423540

Contactless counting is a suitable technique for the measurement of fragile commodities, acting as a successful tool for industrial production control. Visual counting processing is one of the most common contactless methods for non-invasive measurements. However, the creation of accurate models for processing images in realistic scenarios is still challenging due to the existence of noise in optical sensors. This paper proposes an egg image noise model for digital visual counting processing that incorporates particular aspects of real images in such acquisition systems. The matching function is defined in hue saturation value (HSV) color space, and a classical nearest neighbor cluster classification is utilized for the counting. Validation experiments are executed with low and high diversity test images, and the performance of the proposed model is compared to existing methods. The matching function results suggest that the introduced egg image noise model is able to represent more accurately complex aspects of egg images in an industrial environment. The comparative results show that the proposed model significantly improves digital visual counting, in terms of egg counting errors, and outperforms in 9% the second best method.

关键词： Visualization image color analysis Production control Optical sensors Colored noise

来源：评论

学校读者我要写书评

暂无评论

A Novel Fingerprint Quality Assessment Based on Gabor Filters 31

A Novel Fingerprint Quality Assessment Based on Gabor Filter...

引用

31st Conference on graphics, Patterns and images (SIBGRAPI)

作者： Andrezza, Igor Borges, Erick Gualberto, Arnaldo Brasileiro, Joao Gomes, Herman Batista, Leonardo Vsoft Tecnol Joao Pessoa PB Brazil Univ Fed Campina Grande Campina Grande PB Brazil Univ Fed Paraiba Joao Pessoa PB Brazil

ISBN: (纸本)9781538692646

Fingerprints are the most widely deployed biometric characteristics. However, the recognition of a fingerprint may be influenced by a lot of factors (e.g., skin conditions, sensor conditions) and a matching algorithm is highly affected by the quality of the images involved. This work proposes a novel method for Fingerprint Quality Assessment (FQA) based on the analysis of the Gabor filters response on a fingerprint image. The correlation between the worst quality templates and the matching score has also been analyzed. The method is validated on FVC2000DB3, FVC2004DB2, FVC2004DB3, and FVC2006DB3 databases. This work was compared to other FQAs in order to evaluate performance and with different matching algorithms for fair comparison. The results found pointed that the proposed method is able to identify the images which most affect the error rates of an AFIS, better than the other methods presented in the literature.

关键词： Fingerprint recognition Quality assessment Databases standards Histograms Forensics image recognition

来源：评论

学校读者我要写书评

暂无评论

image-based Visualization of Classifier Decision Boundaries 31

Image-based Visualization of Classifier Decision Boundaries

引用

31st Conference on graphics, Patterns and images (SIBGRAPI)

作者： Rodrigues, Francisco Caio M. Hirata, R., Jr. Telea, A. C. Univ Sao Paulo Inst Math & Stat Sao Paulo Brazil Univ Groningen Johann Bernoulli Inst Groningen Netherlands

ISBN: (纸本)9781538692646

Understanding how a classifier partitions a high-dimensional input space and assigns labels to the parts is an important task in machine learning. Current methods for this task mainly use color-coded sample scatterplots, which do not explicitly show the actual decision boundaries or confusion zones. We propose an image-based technique to improve such visualizations. The method samples the 2D space of a dimensionality-reduction projection and color-code relevant classifier outputs, such as the majority class label, the confusion, and the sample density, to render a dense depiction of the high-dimensional decision boundaries. Our technique is simple to implement, handles any classifier, and has only two simple-to-control free parameters. We demonstrate our proposal on several real-world high-dimensional datasets, classifiers, and two different dimensionality reduction methods.

关键词： Two dimensional displays Visualization Training Dimensionality reduction Color Brightness Task analysis

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Dialogue Act Classification with Optimum-Path Forest 31

Unsupervised Dialogue Act Classification with Optimum-Path F...

引用

31st Conference on graphics, Patterns and images (SIBGRAPI)

作者： Felix Ribeiro, Luiz Carlos Papa, Joao Paulo Sao Paulo State Univ UNESP Dept Comp Bauru SP Brazil

ISBN: (纸本)9781538692646

Dialogue Act classification is a relevant problem for the Natural Language processing field either as a standalone task or when used as input for downstream applications. Despite its importance, most of the existing approaches rely on supervised techniques, which depend on annotated samples, making it difficult to take advantage of the increasing amount of data available in different domains. In this paper, we briefly review the most commonly used datasets to evaluate Dialogue Act classification approaches and introduce the Optimum-Path Forest (OPF) classifier to this task. Instead of using its original strategy to determine the corresponding class for each cluster, we use a modified version based on majority voting, named M-OPF, which yields good results when compared to k-means and Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN), according to accuracy and V-measure. We also show that M-OPF, and consequently OPF, are less sensitive to hyper-parameter tuning when compared to HDBSCAN.

关键词： Task analysis Prototypes Forestry Vegetation Switches Hidden Markov models Natural language processing

来源：评论

学校读者我要写书评

暂无评论

Proactive service migration for long-running Byzantine fault-tolerant systems

引用

IET SOFTWARE 2009年第2期3卷 154-164页

作者： Zhao, W. Zhang, H. Cleveland State Univ Dept Elect & Comp Engn Cleveland OH 44115 USA

A proactive recovery scheme based on service migration for long-running Byzantine fault-tolerant systems is described. Proactive recovery is an essential method for ensuring the long-term reliability of fault-tolerant systems that are under continuous threats from malicious adversaries. The primary benefit of our proactive recovery scheme is a reduced vulnerability window under normal operation. This is achieved in two ways. First, the time-consuming reboot step is removed from the critical path of proactive recovery. Second, the response time and the service migration latency are continuously profiled and an optimal service migration interval is dynamically determined during runtime based on the observed system load and the user-specified availability requirement.

关键词： FAULT-tolerant computing INTERNET ALGORITHMS ELECTRONIC data processing computer networks

来源：评论

学校读者我要写书评

暂无评论

Robust feature spaces from pre-trained deep network layers for skin lesion classification 31

Robust feature spaces from pre-trained deep network layers f...

引用

31st Conference on graphics, Patterns and images (SIBGRAPI)

作者： dos Santos, Fernando Pereira Ponti, Moacir A. Univ Sao Paulo Inst Math & Comp Sci ICMC Sao Carlos SP Brazil

ISBN: (纸本)9781538692646

The incidence of skin cancer in the world population is a public health concern, and the first diagnosis takes into account the appearance of lesions on skin. In this context, automated methods to aid the screening for malign lesions can be an important tool. However, the efficiency of developed methods depends directly on the quality of the generated feature space which may vary when considering different image datasets and sources. We present a detailed study of feature spaces obtained from deep convolutional networks (CNNs), using the benchmark PH2 dataset, considering three CNN architectures, as well as investigating different layers, impact of dimensionality reduction, use of colour quantisation and noise addition. Our results show that, features have discriminative capability comparable to competing methods with balanced accuracy 94%, and 95% with noise injection. Additionally, we present a study of fine-tuning and generalisation across image quantisation and noise levels, contributing to the discussion of learning features from deep networks and offering a guideline for future works.

关键词： Feature extraction Lesions Skin image color analysis Skin cancer Radio frequency

来源：评论

学校读者我要写书评

暂无评论

image-Based state Recognition for Disconnect Switches in Electric Power Distribution Substations 31

Image-Based State Recognition for Disconnect Switches in Ele...

引用

31st Conference on graphics, Patterns and images (SIBGRAPI)

作者： Nassu, Bogdan T. Lippmann, Lourival, Jr. Marchesi, Bruno Canestraro, Amanda Wagner, Rafael Zarnicinski, Vanderlei Univ Tecnol Fed Parana Curitiba Parana Brazil Inst Lactec Curitiba Parana Brazil Co Paranaense Energia Curitiba Parana Brazil

ISBN: (纸本)9781538692646

Knowing the state of the disconnect switches in a power distribution substation is important to avoid accidents, damaged equipment, and service interruptions. This information is usually provided by human operators, who can commit errors because of the cluttered environment, bad weather or lighting conditions, or lack of attention. In this paper, we introduce an approach for determining the state of each switch in a substation, based on images captured by regular pan-tilt-zoom surveillance cameras. The proposed approach includes noise reduction, image registration using phase correlation, and classification using a convolutional neural network and a support vector machine fed with gradient-based descriptors. By combining information given in an initial labeling stage with image processing techniques to reduce variations in viewpoint, our approach achieved 100% accuracy on experiments performed at a real substation over multiple days. We also show how modifications to the standard phase correlation image registration algorithm can make it more robust to lighting variations, and how SIFT (Scale-Invariant Feature Transform) descriptors can be made more robust in scenarios where the relevant objects may be brighter or darker than the background.

关键词： Substations Cameras image registration Lighting Monitoring Labeling Correlation

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：