检索结果-内蒙古大学图书馆

28th sibgrapi conference on graphics, patterns and images sibgrapi

作者： Leite, Tatiane Silvia De Martino, Jose Mario Univ Estadual Campinas Sch Elect & Comp Engn FEEC Campinas SP Brazil

ISBN: (纸本)9781467379625

Advertising images increasingly require attractive faces to attract the public's attention. Several studies have been conducted to enhance facial attractiveness in images. While some researchers suggest changes in geometrical shape, others advocate modifying the appearance of the facial skin;however, there have been few attempts to explore the possibility of combining both techniques. this paper sets out a novel method of doing this: facial geometry and skin texture modifications. Our method, which is based on supervised machine learning techniques, is able to improve the attractiveness of faces in images while preserving the original features of the picture. We also demonstrate the effectiveness of this combination by carrying out two different evaluations. Accordingly, we analyze the significance of each change that is designed to improve attractiveness by comparing the original image with a) the image in which only the facial geometry has been modified, b) the image in which only the texture skin has been modified and finally c) the image with both modifications. Our results reveal that the combination of geometric and skin texture modifications results in the most significant enhancement. It also demonstrates that modifications to the skin texture can be regarded as more important to obtain an attractive face than changes to the facial geometry. Additionally, evaluations are provided to quantify the gain in facial attractiveness and it should be pointed out that our method is the first to employ these, since there are no references to such tests in the literature.

关键词： facial attractiveness facial geometry skin texture machine learning

来源：评论

学校读者我要写书评

暂无评论

Improving Spatial Feature Representation from Aerial Scenes by Using Convolutional Networks 28

Improving Spatial Feature Representation from Aerial Scenes ...

引用

28th sibgrapi conference on graphics, patterns and images sibgrapi

作者： Nogueira, Keiller Miranda, Waner O. dos Santos, Jefersson A. Univ Fed Minas Gerais Dept Comp Sci Belo Horizonte MG Brazil

ISBN: (纸本)9781467379625

the performance of image classification is highly dependent on the quality of extracted features. Concerning high resolution remote image images, encoding the spatial features in an efficient and robust fashion is the key to generating discriminatory models to classify them. Even though many visual descriptors have been proposed or successfully used to encode spatial features of remote sensing images, some applications, using this sort of images, demand more specific description techniques. Deep Learning, an emergent machine learning approach based on neural networks, is capable of learning specific features and classifiers at the same time and adjust at each step, in real time, to better fit the need of each problem. For several task, such image classification, it has achieved very good results, mainly boosted by the feature learning performed which allows the method to extract specific and adaptable visual features depending on the data. In this paper, we propose a novel network capable of learning specific spatial features from remote sensing images, with any pre-processing step or descriptor evaluation, and classify them. Specifically, automatic feature learning task aims at discovering hierarchical structures from the raw data, leading to a more representative information. this task not only poses interesting challenges for existing vision and recognition algorithms, but also brings huge opportunities for urban planning, crop and forest management and climate modelling. the propose convolutional neural network has six layers: three convolutional, two fully-connected and one classifier layer. So, the five first layers are responsible to extract visual features while the last one is responsible to classify the images. We conducted a systematic evaluation of the proposed method using two datasets: (i) the popular aerial image dataset UCMerced Land-use and, (ii) a multispectral high-resolution scenes of the Brazilian Coffee Scenes. the experiments show that the pro

关键词： Deep Learning Remote Sensing Feature Learning Image Classification Machine Learning High-resolution images

来源：评论

学校读者我要写书评

暂无评论

Identification of the Radical Component from images of Chinese Characters 35

Identification of the Radical Component from Images of Chine...

引用

35th sibgrapi conference on graphics, patterns and images (sibgrapi)

作者： Wu, Yu Tzu Fujiwara, Eric Suzuki, Carlos K. Univ Estadual Campinas Sch Mech Engn BR-13083860 Campinas Brazil

ISBN: (数字)9781665453851

ISBN: (纸本)9781665453851

the Chinese writing system is made of pictographic symbols known as hanzi or Han characters which are combinations of single or multiple smaller units in varying degrees of complexity. For every hanzi, there is a fundamental block, namely the radical, which defines its meaning, usage, and how words are organized in the dictionary. Given its importance, this work proposes and demonstrates an automatic radical identifier and localizer of hanzi from images, reaching an average precision of similar to 78.0% and an average recall of similar to 74.3% for the 30 radicals with most entries in the dictionary and on a random excerpt of a historical novel.

关键词： Training Location awareness Dictionaries Text categorization Symbols Memory Information retrieval

来源：评论

学校读者我要写书评

暂无评论

An approach based on image processing techniques to segment lung region in chest X-ray images 34

An approach based on image processing techniques to segment ...

引用

34th sibgrapi conference on graphics, patterns and images (sibgrapi)

作者： de Menezes, Luiza C. de Araujo, Augusto R. V. F. Conci, Aura Univ Fed Fluminense Inst Comp BR-24210346 Niteroi RJ Brazil

ISBN: (纸本)9781665423540

Chest X-ray (CXR) images help specialists worldwide to diagnose lung diseases, such as tuberculosis and COVID-19. A primary step in an image-based diagnostic tool is to segment the region of interest. that facilitates the disease classification problem by reducing the amount of information to be processed. However, due to the noisy nature of CXRs, identifying the lung region can be a challenging task. this paper addresses the lung segmentation problem using a less costable computational process based on image analysis and mathematical morphology techniques. the proposed method achieved a specificity of 92.92%, a Jaccard index of 77.77%, and a Dice index of 87.37% on average.

关键词： graphics Image segmentation Image analysis Pulmonary diseases Lung Morphology Noise measurement

来源：评论

学校读者我要写书评

暂无评论

Information theory-based Detection of Noisy Bit Planes in Medical images 29

Information Theory-based Detection of Noisy Bit Planes in Me...

引用

29th sibgrapi conference on graphics, patterns and images (sibgrapi)

作者： de Oliveira, Hugo N. dos Santos, Jefersson A. de Melo, Matheus C. do Rego, thais G. Batista, Leonardo V. Univ Fed Minas Gerais Dept Ciencia Computacao Belo Horizonte MG Brazil Univ Fed Paraiba UFPB Ctr Informat Joao Pessoa Paraiba Brazil

ISBN: (纸本)9781509035687

Mammographic Computer-Aided Diagnosis systems are applications designed to assist radiologists in diagnosis of malignancy in mammographic findings. Most methods described in the literature do not perform a proper preprocessing step in mammographic images prior to classification, which can generate inconsistent results due to the potentially large amount of noise in medical images. this paper proposes a new method based on Information theory and Data Compression for detection of random noise in image bit planes. In order to validate the efficiency of the proposed noise removal method, we used Machine Learning algorithms to classify mammographic findings from the Digital Database for Screening Mammography. Results using texture features indicate that a reduction in the radiometric resolution of 4 or 5 bit planes in digitized screen film mammographic images result in a better classification performance.

关键词： noise detection mammogram classification information theory data compression

来源：评论

学校读者我要写书评

暂无评论

BRCars: a Dataset for Fine-Grained Classification of Car images 34

BRCars: a Dataset for Fine-Grained Classification of Car Ima...

引用

34th sibgrapi conference on graphics, patterns and images (sibgrapi)

作者： Kuhn, Daniel M. Moreira, Viviane P. Univ Fed Rio Grande do Sul Porto Alegre RS Brazil

ISBN: (纸本)9781665423540

Fine-grained computer vision tasks refer to the ability of distinguishing objects that belong to the same parent class, differentiating themselves by subtle visual elements. Image classification in car models is considered a fine-grained classification task. In this work, we introduce BRCars, a dataset that seeks to replicate the main challenges inherent to the task of classifying car images in many practical applications. BRCars contains around 300K images collected from a Brazilian car advertising website. the images correspond to 52K car instances and are distributed among 427 different models. the images are both from the exterior and the interior of the cars and present an unbalanced distribution across the different models. In addition, they are characterized by a lack of standardization in terms of perspective. We adopted a semi-automated annotation pipeline with the help of the new CLIP neural network, which enabled distinguishing thousands of images among different perspectives using textual queries. Experiments with standard deep learning classifiers were performed to serve as baseline results for future work on this topic.

关键词： Deep learning Visualization Computer vision Computational modeling Pipelines Neural networks Automobiles

来源：评论

学校读者我要写书评

暂无评论

Local Moebius transformations applied to omnidirectional images

引用

COMPUTERS & graphics-UK 2017年第Nov.期68卷 77-83页

作者： Ferreira, Leonardo Souto Sacht, Leonardo Velho, Luiz Univ Fed Santa Catarina Dept Matemat Campus Trindade BR-88040900 Florianopolis SC Brazil IMPA Estr Dona Castorina 110 BR-22460320 Rio De Janeiro Brazil

this work presents a new method to transform omnidirectional images based on a combination of Moebius transformations in the complex plane and weighting functions that restrict the action of these mappings to regions of interest. the transformations are calculated based. on the specification of the image of three points and the weighting functions are designed to achieve specific goals such as local zoom or straight line rectification. Since no optimization or numerical methods are involved, our implementation of the proposed method can be upgraded to reach real-time performance. We provide a user interface and present many results that illustrate the potential of the proposed technique. (C) 2017 Elsevier Ltd. All rights reserved.

关键词： Moebius transformations Omnidirectional images Panoramas Distortions

来源：评论

学校读者我要写书评

暂无评论

Enhancement of Underwater images in Low-to-High Turbidity Rivers 29

Enhancement of Underwater Images in Low-to-High Turbidity Ri...

引用

29th sibgrapi conference on graphics, patterns and images (sibgrapi)

作者： Rodrigues, Daily Daleno de O. de Barros, Wagner F. de Queiroz-Neto, Jose P. Fontoura, Anderson G. Carvalho, Jose Reginaldo H. Univ Fed Amazonas IComp BR-69067005 Manaus Amazonas Brazil Inst Fed Amazonas IFAM BR-69100003 Manaus Amazonas Brazil IFNMG Montes Claros MG Brazil

ISBN: (纸本)9781509035687

the demand for efficient enhancement methods of underwater images of the rivers in the Amazon region is increasing. However, most of those in the region present moderate turbidity and low luminosity. this work aims to improve these images by non-linear filtering techniques, which promote the minimization of light interaction characteristics with the environment, loss of the contrast and colors. the proposed method is compared with two others techniques that requires a unique image as input. the results of the proposed method is promising, with better visual quality considering a wide range of experiments with simulation data and real outdoor scenes.

关键词： Underwater images Image Enhancement Degraded images

来源：评论

学校读者我要写书评

暂无评论

sibgrapi-T 2012

SIBGRAPI-T 2012

引用

25th sibgrapi - conference on graphics, patterns and images Tutorials, sibgrapi-T 2012

作者： Walter, Marcelo Yin, Lijun

ISBN: (纸本)9780769548302

this book contains five survey papers written on the topics of the tutorials presented at the 25th sibgrapi - conference on graphics, patterns and images, held in Ouro Preto, Minas Gerais, Brazil from August 22-25, 2012. this is the fourth year that tutorial papers from sibgrapi are published by IEEE CPS. the authors of accepted tutorials are invited to write survey papers about the topics and concepts presented during the tutorial sessions. this selection includes survey papers on exciting topics in computer graphics, image processing and computer vision. We hope this material will inspire new exciting research in our fields. © 2012 IEEE.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

Visual Computing in 360°: Foundations, Challenges, and Applications 35

Visual Computing in 360°: Foundations, Challenges, and Appl...

引用

35th sibgrapi conference on graphics, patterns and images (sibgrapi)

作者： da Silveira, thiago L. T. Jung, Claudio R. Univ Fed Rio Grande do Sul Inst Informat Porto Alegre Brazil

ISBN: (数字)9781665453851

ISBN: (纸本)9781665453851

Omnidirectional media are becoming widespread with the increasing popularization of devices for capture and visualization. Unlike traditional pinhole-based images, omnidirectional images are defined on the surface of a sphere, present a full field of view, and store light intensities from a whole scene. In particular, applications exploring immersive augmented, mixed, and virtual reality experiences can strongly benefit from omnidirectional vision. though omnidirectional images are defined on the spherical domain, they are commonly mapped to one or multiple planes. those sphere-to-plane mappings generate distorted images, and, if directly applied, most traditional visual computing algorithms tend to present some quality degradation. this tutorial paper revises the spherical imaging model, common capture device types, and prominent representation formats. It also discusses the significant challenges of spherical visual computing and showcases the advances in three selected applications.

关键词： 360 degrees images spherical images omnidirectional images panoramas

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：