检索结果-内蒙古大学图书馆

28th SIBGRAPI Conference on graphics, Patterns and images SIBGRAPI

作者： Lopes, Andre Teixeira de Aguiar, Edilson Oliveira-Santos, Thiago Univ Fed Espirito Santo Vitoria ES Spain

ISBN: (纸本)9781467379625

Facial expression recognition has been an active research area in the past ten years, with a growing application area like avatar animation and neuromarketing. The recognition of facial expressions is not an easy problem for machine learning methods, since different people can vary in the way that they show their expressions. And even an image of the same person in one expression can vary in brightness, background and position. Therefore, facial expression recognition is still a challenging problem in computer vision. In this work, we propose a simple solution for facial expression recognition that uses a combination of standard methods, like Convolutional Network and specific image pre-processing steps. Convolutional networks, and the most machine learning methods, achieve better accuracy depending on a given feature set. Therefore, a study of some image pre-processing operations that extract only expression specific features of a face image is also presented. The experiments were carried out using a largely used public database for this problem. A study of the impact of each image pre-processing operation in the accuracy rate is presented. To the best of our knowledge, our method achieves the best result in the literature, 97.81% of accuracy, and takes less time to train than state-of-the-art methods.

关键词： Facial Expression Convolutional Networks computer Vision Machine Learning Expression Specific Features

来源：评论

学校读者我要写书评

暂无评论

A Boosting-Based Approach for Remote Sensing Multimodal image Classification

A Boosting-Based Approach for Remote Sensing Multimodal Imag...

引用

brazilian symposium on computer graphics and image processing (SIBGRAPI)

作者： Edemir Ferreira Arnaldo de Albuquerque Araújo Jefersson Alex Dos Santos Universidade Federal de Minas Gerais (UFMG) MG Brazil Universidade Federal de Minas Gerais Belo Horizonte MG BR

ISBN: (纸本)9781509035694;9781509035687

Remote Sensing images (RSI) have been used as a major source of data, particularly with respect to the creation of thematic maps. This process is usually modeled as a supervised learning task where the system needs to learn the patterns of interest provided by the user and assign a class to the rest of the image regions. Thus, it is common to have images obtained from different sensors, which could improve the quality of thematic maps. However, this requires the creation of techniques to properly encode and combine the different properties of the images. So, this paper proposes a boosting-based technique for classification of regions in RSI that manages to encode features extracted from different sources of data, spectral and spatial domains. The approach is evaluated in an urban and a coffee crop recognition scenarios, achieving statistically better results in comparison with the baselines in urban classification and better results at some baselines for the coffee crop recognition.

关键词： Remote sensing Sensors Spatial resolution Feature extraction Data integration image sensors

来源：评论

学校读者我要写书评

暂无评论

A New Approach for Dynamic Gesture Recognition Using Skeleton Trajectory Representation and Histograms of Cumulative Magnitudes

A New Approach for Dynamic Gesture Recognition Using Skeleto...

引用

brazilian symposium on computer graphics and image processing (SIBGRAPI)

作者： Edwin Escobedo Guillermo Camara Department of Computer Science (DECOM) Federal University of Ouro Preto Ouro Preto MG Brazil

ISBN: (纸本)9781509035694;9781509035687

In this paper, we present a new approach for dynamic hand gesture recognition that uses intensity, depth, and skeleton joint data captured by Kinect sensor. This method integrates global and local information of a dynamic gesture. First, we represent the skeleton 3D trajectory in spherical coordinates. Then, we select the most relevant points in the hand trajectory with our proposed method for keyframe detection. After, we represent the joint movements by spatial, temporal and hand position changes information. Next, we use the direction cosines definition to describe the body positions by generating histograms of cumulative magnitudes from the depth data which were converted in a point-cloud. We evaluate our approach with different public gesture datasets and a sign language dataset created by us. Our results outperformed state-of-the-art methods and highlight the smooth and fast processing for feature extraction being able to be implemented in real time.

关键词： Trajectory Feature extraction Gesture recognition Skeleton Histograms Robot sensing systems Elbow

来源：评论

学校读者我要写书评

暂无评论

Efficient Object Recognition Using Sampling of Keypoint Triples and Keygraph Structure

Efficient Object Recognition Using Sampling of Keypoint Trip...

引用

brazilian symposium on computer graphics and image processing (SIBGRAPI)

作者： Estephan Dazzi Teofilo De Campos Adrian Hilton Roberto Cesar Instituto de Matemática e Estatística-IME Universidade de São Paulo-USP São Paulo SP Brasil Fac. Gama Univ. de Brasilia Brasilia DF BR Speech and Signal Processing-CVSSP University of Surrey Guildford UK

ISBN: (纸本)9781509035694;9781509035687

We present an object matching method that employs matches of local graphs of keypoints, called keygraphs, instead of simple keypoint matches. For a keygraph match to be valid, vertex (keypoint) descriptors must be similar and both keygraphs must satisfy structural properties concerning keypoints orientation, scale, relative position and cyclic ordering; as a result, the large majority of initial incorrect keypoint matches is correctly filtered out. We introduce a novel approach to sample keypoint triples (i.e. keygraphs) in a query image, based on complementary Delaunay triangulations; this generates a linear number of triples with relation to the number of keypoints. Query keygraphs are then matched against the indexed model keypoints; each established keygraph match is used to evaluate a candidate pose (an affine transformation). The proposed method has been evaluated for object recognition and pose estimation, achieving a better performance in comparison to state-of-the-art methods.

关键词： Training Object recognition Three-dimensional displays Solid modeling Pose estimation image edge detection Electronic mail

来源：评论

学校读者我要写书评

暂无评论

A New Descriptor for Retrieving 3D Objects Applied in Congestive Heart Failure Diagnosis

A New Descriptor for Retrieving 3D Objects Applied in Conges...

引用

brazilian symposium on computer graphics and image processing (SIBGRAPI)

作者： Helton H. Bíscaro Hellyan Oliveira Leila C. C. Bergamasco Fátima L. S. Nunes Laboratory of Computer Applications for HealthCare University of Sâo Paulo São Paulo Brazil

ISBN: (纸本)9781509035694;9781509035687

Content-Based image Retrieval (CBIR) aims to retrieve similar graphical objects from large databases based on their contents. CBIR requires definition of descriptors, algorithms that condense information from the object in order to represent it usually as a real number or a vector in Rn. This article presents the Spectral Descriptor, a new descriptor designed for retrieving three-dimensional geometric objects applied to aid the diagnosis of Congestive Heart Failure (CHF). Our descriptor is based on techniques of compressive sensing and rewrites the coordinates of 3D objects vertices on a basis on which they have a sparse representation. Tests with surfaces reconstructed from heart MRI images, specifically from left ventricle, show that the descriptor has presented a good performance, reaching an average precision of approximately 85% for CHF and 71% for non-CHF cases, maintaining high levels of precision. Results also showed that the Spectral Descriptor can decrease the high dimensionality of features vectors in CBIR systems.

关键词： Three-dimensional displays Feature extraction Heart Sparse matrices image reconstruction Matrix decomposition Databases

来源：评论

学校读者我要写书评

暂无评论

Exploded View Diagrams of 3D Grids 28

Exploded View Diagrams of 3D Grids

引用

28th SIBGRAPI Conference on graphics, Patterns and images SIBGRAPI

作者： Martins Filho, Zamir Brazil, Emilio Vital Sousa, Mario Costa Univ Calgary Calgary AB Canada

ISBN: (纸本)9781467379625

We present a system for creating interactive exploded view diagrams in generalized 3D grids. The primary difference between our approach and existing ones is that our technique neither requires geometrical information of the whole model nor any information regarding the relationship among model parts;instead our implementation depends on which grid cells are considered as object of interest, and which view angle to use. To achieve this, we introduce the Explosion Tree, a data structure closely related to a BSP tree, which supports the explosion view diagrams technique based on the relationship between disjoint convex polygons. In this paper we discuss the application of this technique to Corner-Point Grid which has been extensively used for geological modeling and flow simulation. All the data presented in this work consists of real data currently used in the industry.

关键词： Computational Geometry computer graphics

来源：评论

学校读者我要写书评

暂无评论

Retinal Vessel Segmentation Using Parallel Grayscale Skeletonization Algorithm and Mathematical Morphology

Retinal Vessel Segmentation Using Parallel Grayscale Skeleto...

引用

brazilian symposium on computer graphics and image processing (SIBGRAPI)

作者： Jardel Rodrigues Nivando Bezerra Departamento da Telemática Ciência e Tecnologia do Ceará Fortaleza Brasil

ISBN: (纸本)9781509035694;9781509035687

Retinal vessel segmentation is an important step for the detection of numerous system diseases, such as glaucoma, diabetic retinopathy, and others. Thus, the retinal blood vessel analysis can be used to diagnose and to monitor the progress of these diseases. Manual segmentation of fundus images is a long and tedious task that requires a specialist. Therefore, many algorithms have been developed for this purpose. This paper demonstrates an automated method for retinal blood vessel segmentation based on the combination of topological and morphological vessel extractors. Each of these extractors is based on different blood vessel features to increase the detection robustness. The final segmentation is obtained intersecting the two resulting images, smoothing the vessel borders and removing spurious objects remaining. Our proposed method is tested on DRIVE and STARE databases, achieving an average accuracy of 0.9565 and 0.9568, respectively, with good values of sensitivity and specificity.

关键词： image segmentation Blood vessels Biomedical imaging Retina Feature extraction Skeleton Gray-scale

来源：评论

学校读者我要写书评

暂无评论

Interactive Visualization of the Cranio-Cerebral Correspondences for 10/20, 10/10 and 10/5 Systems

Interactive Visualization of the Cranio-Cerebral Corresponde...

引用

brazilian symposium on computer graphics and image processing (SIBGRAPI)

作者： José Angel Iván Rubianes Silva Fabio Enrique Suarez Burgos Shin-Ting Wu Sch. of Elec. & Comput. Eng. Universidade Estadual de Campinas Campinas SP BR Sch. of Med. Sci. Universidade Estadual de Campinas Campinas SP BR Sch. of Elec. and Computer Engineering University of Campinas Campinas Brazil

Electroencephalogram (EEG) is a method that records electrical activities of the brain. Reliable interpretation of its measurements rely on accurate correspondence of the scalp electrodes and the underlying cortical surface. To standardize comparative studies international 10/20, 10/10 and 10/5 systems for the placement of electrodes have been proposed to specify the locations of scalp EEG sensors under the assumption that there is a consistent correlation between these sites and the structure of the cerebral cortex. However, several studies have demonstrated that the cranio-cerebral correlations vary greatly. For enhancing the electrophysiological analyses, an algorithm is presented in this paper, allowing the multimodal visualization of EEG and magnetic resonance scan in the patient's native space. The key to our solution is twofold: an interactive image-based electrode placement algorithm and an extended GPU-based multimodal ray-casting algorithm. Experimental results show that with the present tool one can easily assess the cranio-cerebral correspondences even when the brain tissue is displaced by structural lesions.

关键词： Electrodes Scalp Electroencephalography Rendering (computer graphics) Magnetic resonance imaging Correlation Surface reconstruction

来源：评论

学校读者我要写书评

暂无评论

Efficient Ray Tracing Through Aspheric Lenses and Imperfect Bokeh Synthesis

引用

computer graphics FORUM 2016年第4期35卷 99-105页

作者： Joo, Hyuntae Kwon, Soonhyeon Lee, Sangmin Eisemann, Elmar Lee, Sungkil Sungkyunkwan Univ Seoul South Korea Delft Univ Technol NL-2600 AA Delft Netherlands

We present an efficient ray-tracing technique to render bokeh effects produced by parametric aspheric lenses. Contrary to conventional spherical lenses, aspheric lenses do generally not permit a simple closed-form solution of ray-surface intersections. We propose a numerical root-finding approach, which uses tight proxy surfaces to ensure a good initialization and convergence behavior. Additionally, we simulate mechanical imperfections resulting from the lens fabrication via a texture-based approach. Fractional Fourier transform and spectral dispersion add additional realism to the synthesized bokeh effect. Our approach is well-suited for execution on graphics processing units (GPUs) and we demonstrate complex defocus-blur and lens-flare effects.

关键词： Categories and Subject Descriptors (according to ACM CCS) I.3.3 [computer graphics]: Picture/image Generation—Display Algorithms

来源：评论

学校读者我要写书评

暂无评论

An Efficient Global Point Cloud Descriptor for Object Recognition and Pose Estimation

An Efficient Global Point Cloud Descriptor for Object Recogn...

引用

brazilian symposium on computer graphics and image processing (SIBGRAPI)

作者： João Paulo Silva do Monte Lima Veronica Teichrieb Universidade Federal Rural de Pernambuco Recife PE BR Centro de Inf. Universidade Federal de Pernambuco (UFPE) Recife Brazil

This paper presents a global point cloud descriptor to be used for efficient object recognition and pose estimation. The proposed method is based on the estimation of a reference frame for the whole point cloud that represents an object instance, which is used for aligning it with the canonical coordinate system. After that, a descriptor is computed for the aligned point cloud based on how its 3D points are spatially distributed. Such descriptor is also extended with color distribution throughout the aligned point cloud. The global alignment transforms of matched point clouds are used for computing object pose. The proposed approach was evaluated with a publicly available dataset, showing that it outperforms major state of the art global descriptors regarding recognition rate and performance and that it allows precise pose estimation.

关键词： Three-dimensional displays Shape Histograms Object recognition Pose estimation Color image color analysis

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：