检索结果-内蒙古大学图书馆

A Local Feature Descriptor Based on Log-Gabor Filters for Keypoint Matching in Multispectral images

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2017年第10期14卷 1850-1854页

作者： Nunes, Cristiano F. G. Padua, Flavio L. C. Ctr Fed Educ Tecnol Minas Gerais BR-3042116 Belo Horizonte MG Brazil

this letter presents a new local feature descriptor for problems related to multispectral images. Most previous approaches are typically based on descriptors designed to work with images uniquely captured in the visible light spectrum. In contrast, this letter proposes a descriptor termed a multispectral feature descriptor (MFD) that is especially developed, such that it can be employed with image data acquired at different frequencies across the electromagnetic spectrum. the performance of the MFD is evaluated by using three data sets composed of images obtained in visible light and infrared spectra, and its performance is compared with those of state-of-the-art algorithms, such as edge-oriented histogram (EOH) and log-Gabor histogram descriptor (LGHD). the experimental results indicate that the computational efficiency of MFD exceeds those of EOH and LGHD, and that the precision and recall values of MFD are statistically comparable to the corresponding values of the forementioned algorithms.

关键词： Image matching local feature descriptor log-Gabor filters multispectral images

来源：评论

学校读者我要写书评

暂无评论

Contextual filtering of CT images using markovian wiener filters with a non local means approach for statistical estimation

Contextual filtering of CT images using markovian wiener fil...

引用

25th conference on graphics, patterns and images, sibgrapi 2012

作者： Salvadeo, Denis H.P. Mascarenhas, Nelson D.A. Levada, Alexandre L.M. São Carlos Brazil

ISBN: (纸本)9780769548296

Recently, investigations on medical imaging have been indicating a strong correlation between cases of cancers and the increasing number of Computed Tomography (CT) exams, mainly due to high radiation doses to which patients are exposed during the data acquisition process. thus, there is a need to reduce the radiation doses whereas still keeping satisfactory quality images for diagnosis. In this paper, we propose to filter noise in CT images using contextual versions of Wiener Filter such as Generalized Wiener Filter (GWF) and Non Local Means approach for parameter estimation. Experiments show that the proposed methods are promising, since they provide good results with no significant increase in the computational cost. © 2012 IEEE.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

Streamline-based topological graph construction with application to self-animated images

Streamline-based topological graph construction with applica...

引用

2013 26th conference on graphics, patterns and images, sibgrapi 2013

作者： Nascimento, Renata Lewiner, thomas Department of Mathematics Pontificia Universidade Catolica Do Rio de Janeiro Rio de Janeiro Brazil

ISBN: (纸本)9780769550992

Vector field analysis and visualization is a fundamental tool in science and engineering applications, raising the need for robust methods to capture and represent the global vector field behavior. One such representation, the topological graph, partitions the domain into regions where the flow of the vector field is homogeneous. this work introduces a topological graph construction based on streamlines. It is guaranteed to produce a coherent result even when some singularities are not detected. this work also details an application of topological graphs to improve the generation of self-animated images. In this application, the streamline-based approach carries almost no overhead, since self-animated images already rely on streamlines, but leads to a threefold speed-up of the core processing. © 2013 IEEE.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

Learning to classify seismic images with deep optimum-path forest 29

Learning to classify seismic images with deep optimum-path f...

引用

29th sibgrapi conference on graphics, patterns and images, sibgrapi 2016

作者： Afonso, Luis Vidal, Alexandre Kuroda, Michelle Falcao, Alexandre Xavier Papa, Joao P. Department of Computing Federal University of São Carlos São Carlos - SP Brazil Institute of Geology University of Campinas Campinas - SP Brazil Institute of Computing University of Campinas Campinas - SP Brazil Department of Computing São Paulo State University Bauru - SP Brazil

ISBN: (纸本)9781509035687

Due to the lack of labeled information, clustering techniques have been paramount in the last years once more. In this paper, inspired by the deep learning phenomenon, we presented a multi-scale approach to obtain more refined cluster representations of the Optimum-Path Forest (OPF) classifier, which has obtained promising results in a number of works in the literature. Here, we propose to fill a gap in OPF-based works by using a deep-driven representation of the feature space. Additionally, we validated the work in the context of high resolution seismic images aiming at petroleum exploration, as well as in general-purpose applications. Quantitative and qualitative analysis are conducted in order to assess the robustness of the proposed approach. © 2016 IEEE.

关键词： Seismology

来源：评论

学校读者我要写书评

暂无评论

Structural analysis of histological images to aid diagnosis of cervical cancer

Structural analysis of histological images to aid diagnosis ...

引用

25th conference on graphics, patterns and images, sibgrapi 2012

作者： Miranda, Gisele Helena Barboni Barrera, Junior Soares, Edson Garcia Felipe, Joaquim Cezar Department of Computing and Mathematics Faculty of Philosophy Sciences and Languages of Ribeirão Preto USP Brazil Department of Computer Science Institute of Mathematics and Statistics USP Brazil Department of Pathology Faculty of Medicine of Ribeirão Preto USP Brazil

ISBN: (纸本)9780769548296

the use of computational techniques in the processing of histopathological images allows the study of the structural organization of tissues and their pathological changes. the overall objective of this work includes the proposal, the implementation and the evaluation of a methodology for the analysis of cervical intraepithelial neoplasia (CIN) from histopathological images. For this pourpose, a pipeline of morphological operators were implemented for the segmentation of cell nuclei and the Delaunay Triangulation were used in order to represent the tissue architecture. Also, clustering algorithms and graph morphology were used to automatically obtain the boundary between the histological layers of the epithelial tissue. Similarity criteria and adjacency relations between the triangles of the network were explored. the proposed method was evaluated concerning the detection of the presence of lesions in the tissue as well as the their malignancy grading. © 2012 IEEE.

关键词： Tissue

来源：评论

学校读者我要写书评

暂无评论

Superpixel-based interactive classification of very high resolution images 27

Superpixel-based interactive classification of very high res...

引用

27th sibgrapi conference on graphics, patterns and images (sibgrapi)

作者： Vargas, John E. Saito, Priscila T. M. Falcao, Alexandre X. de Rezende, Pedro J. dos Santos, Jefersson A. Univ Estadual Campinas Inst Comp Campinas SP Brazil Fed Technol Univ Parana Dept Comp Engn Cornelio Procopio Brazil Univ Fed Minas Gerais Dept Comp Sci Belo Horizonte MG Brazil

ISBN: (纸本)9781479942602

Very high resolution (VHR) images are large datasets for pixel annotation - a process that has depended on the supervised training of an effective pixel classifier. Active learning techniques have mitigated this problem, but pixel descriptors are limited to local image information and the large number of pixels makes the response time to the user's actions impractical, during active learning. To circumvent the problem, we present an active learning strategy that relies on superpixel descriptors and a priori dataset reduction. Firstly, we compare VHR image annotation using superpixel- and pixel-based classifiers, as designed by the same state-of-the-art active learning technique - Multi-Class Level Uncertainty (MCLU). Even with the dataset reduction provided by the superpixel representation, MCLU remains unfeasible for user interaction. therefore, we propose a technique to considerably reduce the superpixel dataset for active learning. Moreover, we subdivide the reduced dataset into a list of subsets with random sample rearrangement to gain both speed and sample diversity during the active learning process.

关键词： Very high resolution image processing active learning superpixel representation dataset reduction supervised classification

来源：评论

学校读者我要写书评

暂无评论

Fast inverse halftoning algorithm for ordered dithered images

Fast inverse halftoning algorithm for ordered dithered image...

引用

24th sibgrapi conference on graphics, patterns and images

作者： Freitas, Pedro Garcia Farias, Mylène C.Q. De Araújo, Aletéia P. F. Brasília Brazil

ISBN: (纸本)9780769545486

In this paper, we present a simple and fast inverse halftoning algorithm, targeted at reconstructing halftoned images generated using dispersed-dot ordered dithering algorithms. the proposed algorithm uses a simple set of linear filters combined with a stochastic model in order to predict the best intensity values for the binary image pixels. the algorithm produces images with a better perceptual quality than the available algorithms in the literature, preserving most of the fine details of the original gray-level image. It has a high performance, which can be further improved with the use of parallelization techniques. © 2011 IEEE.

关键词： Binary images

来源：评论

学校读者我要写书评

暂无评论

Analysis of the statistical significance of 3D texture features in MRI images toward the detection of Tourette's Syndrome 35

Analysis of the statistical significance of 3D texture featu...

引用

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

作者： de Barros, Murilo Costa Duarte, Kaue T. N. Lee, Wang-Tso Hsu, Chia-Jui de Carvalho, Marco Antonio G. Univ Estadual Campinas Sch Technol UNICAMP Comp Visual Lab R Paschoal Marmo 1888 Limeira Brazil Univ Calgary Vasc Imaging Lab 2500 Univ Dr NW Calgary AB T2N IN4 Canada Natl Taiwan Univ Childrens Hosp Dept Pediat Taipei Taiwan Natl Taiwan Univ Hosp Dept Pediat Hsinchu Branch Taipei Taiwan

ISBN: (数字)9781665453851

ISBN: (纸本)9781665453851

Tourette Syndrome (TS) is a genetically induced disorder that is believed to be caused by morphological alterations in brain structure, resulting in involuntary movements known as tics. the current clinical standard for diagnosing TS is by clinical assessments performed by physicians. Mild stages of TS, however, commonly go underdiagnosed as tics are infrequent or often suppressed. Brain imaging has been suggested to be a reliable tool to detect brain alterations and possible biomarkers that correspond to neurological disorders. In Magnetic Resonance Imaging (MRI), anatomical brain changes can be identified in the scan by variation in texture patterns of certain regions. the main goal of this work is to identify the statistical significance of texture features in specific brain regions to distinguish TS from control subjects. the proposed approach consists of four main steps: (i) image acquisition, where the data is also organized using demographic information;(ii) brain segmentation, where the structural MRI is parcellated into anatomical regions;(iii) registration, where functional MRI is aligned to structural MRI;(iv) obtaining texture features and statistical analysis, where texture features are extracted from the anatomical brain regions. We adopted 68 subjects aged between 6 to 14 years, divided equally into TS and Normal Control groups. We evaluated the texture features in a statistical manner, where our main findings are: (i) After False Discovery Rate (FDR) correction, only one texture feature was significant (p-value < 0.08) in structural MRI;(ii) Following FDR correction, eight texture features in functional MRI for three anatomical regions were considered significant;(iii) the right amygdala presented significance in distinct texture features, matching its importance in the literature. Texture features aligned with the literature can serve as a reliable tool to identify imaging changes, which can lead to future work applied to clinical studies.

关键词： Brain Image segmentation Visualization three-dimensional displays Statistical analysis Functional magnetic resonance imaging Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Ranking methods for tensor components analysis and their application to face images

Ranking methods for tensor components analysis and their app...

引用

2013 26th conference on graphics, patterns and images, sibgrapi 2013

作者： Filisbino, Tiene A. Giraldi, Gilson A. thomaz, Carlos Eduardo National Laboratory for Scientific Computing LNCC Petropolis Brazil Department of Electrical Engineering FEI Sao Bernardo do Campo Brazil

ISBN: (纸本)9780769550992

Higher order tensors have been applied to model multidimensional image databases for subsequent tensor decomposition and dimensionality reduction. In this paper we address the problem of ranking tensor components in the context of the concurrent subspace analysis (CSA) technique following two distinct approaches: (a) Estimating the covariance structure of the database, (b) Computing discriminant weights through separating hyper planes, to select the most discriminant CSA tensor components. the former follows a ranking method based on the covariance structure of each subspace in the CSA framework while the latter addresses the problem through the discriminant principal component analysis methodology. Both approaches are applied and compared in a gender classification task performed using the FEI face database. Our experimental results highlight the low dimensional data representation of both approaches, while allowing robust discriminant reconstruction and interpretation of the sample groups and high recognition rates. © 2013 IEEE.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Segmentation of large images with complex networks

Segmentation of large images with complex networks

引用

25th conference on graphics, patterns and images, sibgrapi 2012

作者： Cuadros, Oscar Botelho, Glenda Rodrigues, Francisco Neto, João Batista São Carlos Brazil

ISBN: (纸本)9780769548296

Image segmentation is still a challenging issue in pattern recognition. Among the various segmentation approaches are those based on graph partitioning, which present some drawbacks, one being high processing times. With the recent developments on complex networks theory, pattern recognition techniques based on graphs have improved considerably. the identification of cluster of vertices can be considered a process of community identification according to complex networks theory. Since data clustering is related with image segmentation, image segmentation can also be approached via complex networks. However, image segmentation based on complex networks poses a fundamental limitation which is the excessive numbers of nodes in the network. this paper presents a complex network approach for large image segmentation that is both accurate and fast. To that, we incorporate the concept of super pixels, to reduce the number of nodes in the network. We evaluate our method for both synthetic and real images. Results show that our method can outperform other graph-based methods both in accuracy and processing times. © 2012 IEEE.

关键词： Image segmentation

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：