检索结果-内蒙古大学图书馆

Multiple testing correction in medical image analysis

JOURNAL OF MAthEMATICAL IMAGING AND VISION 2007年第2-3期29卷 107-117页

作者： Machado, Alexei Manso Correa Pontifical Catholic Univ Minas Gerias BR-30535610 Belo Horizonte MG Brazil

We present a novel method for correcting the significance level of hypothesis testing that requires multiple comparisons. It is based on the spectral graph theory, in which the variables are seen as the vertices of a complete undirected graph and the correlation matrix as the adjacency matrix that weights its edges. the method increases the statistical power of the analysis by refuting the assumption of independence among variables, while keeping the probability of false positives low. By computing the eigenvalues of the correlation matrix, it is possible to obtain valuable information about the dependence levels among the variables of the problem, so that the effective number of independent variables can be estimated. the method is compared to other available models and its effectiveness illustrated in case studies involving high-dimensional sets of variables.

关键词： hypothesis testing Bonferroni correction spectral graph theory

来源：评论

学校读者我要写书评

暂无评论

Tree-pruning: A new algorithm and its comparative analysis with the watershed transform for automatic image segmentation

Tree-pruning: A new algorithm and its comparative analysis w...

引用

SIBGRAPI 2006: 19th brazilian symposium on computer graphics and image processing

作者： Miranda, Paulo A. V. Rocha, Leonardo M. Bergo, Felipe P. G. Falcão, Alexandre X. LIV Institute of Computing UNICAMP C.P. 6176 13084-971 Campinas SP Brazil DECOM FEEC UNICAMP C.P. 6101 13083-970 Campinas SP Brazil

ISBN: (纸本)0769526861

image segmentation using tree pruning (TP) and watershed (WS) has been presented in the framework of the image forest transform (IFT)- a method to reduce image processing problems related to connectivity into an optimumpath forest problem in a graph. Given that both algorithms use the IFT with similar parameters, they usually produce similar segmentation results. However, they rely on different properties of the IFT which make TP more robust than WS for automatic segmentation tasks. We propose and demonstrate an important improvement in the TP algorithm, clarify the differences between TP and WS, and provide their comparative analysis from the theoretical and practical points of view. the experiments involve automatic segmentation of license plates in a database with 990 images. © 2006 IEEE.

关键词： Trees (mathematics)

来源：评论

学校读者我要写书评

暂无评论

Towards real-time image segmentation using polynomial functions 13

Towards real-time image segmentation using polynomial functi...

引用

13th brazilian symposium on computer graphics and image processing, SIBGRAPI 2000

作者： Sappa, Angel D. Garcia, Luiz M. Laboratoire d'Analyse et d'Architecture des Systèmes 7 Avenue du Colonel Roche Toulouse Cedex 0431077 France

ISBN: (纸本)0769508782

We present current development towards a real-time method for segmentation of images for robotics applications. Our algorithm follows a fast scan line procedure (rows and columns), thus breaking the 2D segmentation problem in two 1D processes. In this first phase we use polynomial functions to find possible ID boundaries in the image columns and rows separately. In a second step, a fusion method is applied, removing redundancies and false boundaries to find the regions of interest in the segmented images. We try to improve the algorithm by using a coarse to fine multi-resolution approach. Preliminary results demonstrate possible applicability in real-time. © 2000 IEEE.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Enhancing microscope biological images with DIP techniques 13

Enhancing microscope biological images with DIP techniques

引用

13th brazilian symposium on computer graphics and image processing, SIBGRAPI 2000

作者： De Araújo, Arnaldo A. De Faria, Bernardo M. Reis, Helton J. Silva, Marco Aurélio R. NPDI/DCC/UFMG Dept. de Ciência da Computação Caixa Postal 702 Belo Horizonte MG31270-010 Brazil ICB/UFMG Inst. de Ciências Biológicas Caixa Postal 486 Belo Horizonte MG31270-910 Brazil

ISBN: (纸本)0769508782

this work reports and illustrates the application of enhancement techniques to images of nervous system from a confocal microscope. these images are processed to enhance regions of interest, e.g. nucleus and nervous terminations. Hidden information due to non-ideal acquisition must be exposed after processing, and errors such as non-uniform brightness, noise and artifacts must be eliminated. © 2000 IEEE.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

A High-Spatial Resolution Dataset and Few-shot Deep Learning Benchmark for image Classification 35

A High-Spatial Resolution Dataset and Few-shot Deep Learning...

引用

35th SIBGRAPI Conference on graphics, Patterns and images (SIBGRAPI)

作者： de Souza Miranda, Mateus Alvarenga e Silva, Lucas Fernando dos Santos, Samuel Felipe de Santiago Junior, Valdivino Alexandre Korting, thales Sehn Almeida, Jurandy Inst Nacl Pesquisas Espaciais INPE Sao Jose Dos Campos SP Brazil Univ Fed Sao Paulo UNIFESP Sao Jose Dos Campos SP Brazil Univ Fed Sao Carlos UFSCar Sorocaba SP Brazil

ISBN: (数字)9781665453851

ISBN: (纸本)9781665453851

this paper presents a high-spatial-resolution dataset with remote sensing images of the brazilian Cerrado for land use and land cover classification. the Biome Cerrado Dataset (Cerra-Data) is a large database created from 150 scenes of the CBERS-4A satellite. images were created by merging the near-infrared, green, and blue bands. Moreover, pan-sharpening was performed between all the scenes and their respective panchromatic bands, resulting in a final spatial resolution of two meters. A total of 2.5 million tiles of 256x256 pixels were derived from these scenes. From this total, 50 thousand tiles were labeled. We also conducted a few-shot learning experiment considering a training set with only 100 samples, 11 deep neural networks (DNNs), and two traditional machine learning (ML) algorithms, i.e., support vector machine (SVM) and random forest (RF). Results show that the DNN DenseNet-161 was the best model but its performance can be improved if it is used only as a feature extractor, leaving the classification task for the traditional ML algorithms. However, by decreasing the size of the training set, smarter approaches are needed. the labeled subset of CerraData as well as the source code we developed to support this study are available on-line: https://***/ai4luc/CerraData-code-data.

关键词： Support vector machines Training Radio frequency Deep learning Satellites Machine learning algorithms Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Recognition of characters in plates of private brazilian vehicles using neural networks 13

Recognition of characters in plates of private Brazilian veh...

引用

13th brazilian symposium on computer graphics and image processing, SIBGRAPI 2000

作者： Da Rocha Gesualdi, Aline De Albuquerque, Marcelo Portes Seixas, José Manoel Calôba, Luiz Pereira De Albuquerque, Marcio Portes Laboratório de Processamento de Sinais Depto. de Eng. Eletrônica e de Computaçào EE Programa de Engenharia Elétrica-COPPE UFRJ C.P. 68504 Rio de Janeiro RJ21945-970 Brazil CBPF/CNPq - Centro Brasileiro de Pesquisas Fisicas Coordenação de Atividades Técnicas Rua Dr. Xavier Sigaud no 150 Urca Rio de Janeiro RJ22290-180 Brazil

ISBN: (纸本)0769508782

this work aims the recognition of characters in plates of private brazilian vehicles using neural networks. Initially we define a standard for the image as prerequisite for the pre-processing. Afterward, the reduction of the dimensionality is made in order to make possible the use of the network. For this we establish a figure of merit-Q-characterizing, amongst some algorithms of characters splitting, the best one. Q is based on normalized cross correlation of the desired character image and the gotten one. the pre-processing allowed us the improvement of the image, reducing the background noise and increasing the contrast by applying a non-linear function. In the last stage, the neural network recognizes each character of the plate. Preliminary results are shown. © 2000 IEEE.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

STN PLAD: A Dataset for Multi-Size Power Line Assets Detection in High-Resolution UAV images 34

STN PLAD: A Dataset for Multi-Size Power Line Assets Detecti...

引用

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

作者： Buarque Vieira-e-Silva, Andre Luiz Felix, Heitor de Castro Chaves, thiago de Menezes Magalhaes Simoes, Francisco Paulo Teichrieb, Veronica dos Santos, Michel Mozinho Santiago, Hemir da Cunha Cordeiro Sgotti, Virginia Adelia Teixeira Lott Neto, Henrique Baptista Duffles Univ Fed Pernambuco Ctr Informat Voxar Labs Recife PE Brazil Univ Fed Rural Pernambuco Dept Comp Recife PE Brazil In Forma Software Recife PE Brazil Sistema Transmissao Nordeste STN Recife PE Brazil

ISBN: (纸本)9781665423540

Many power line companies are using UAVs to perform their inspection processes instead of putting their workers at risk by making them climb high voltage power line towers, for instance. A crucial task for the inspection is to detect and classify assets in the power transmission lines. However, public data related to power line assets are scarce, preventing a faster evolution of this area. this work proposes the STN Power Line Assets Dataset, containing high-resolution and real-world images of multiple high-voltage power line components. It has 2,409 annotated objects divided into five classes: transmission tower, insulator, spacer, tower plate, and Stockbridge damper, which vary in size (resolution), orientation, illumination, angulation, and background. this work also presents an evaluation with popular deep object detection methods and MS-PAD, a new pipeline for detecting power line assets in hi-res UAV images. the latter outperforms the other methods achieving 89.2% mAP, showing considerable room for improvement.

关键词： Power transmission lines image resolution Poles and towers Pipelines Lighting Object detection Inspection

来源：评论

学校读者我要写书评

暂无评论

Histogram uniformization for digital image encryption

Histogram uniformization for digital image encryption

引用

25th Conference on graphics, Patterns and images, SIBGRAPI 2012

作者： Lima, Juliano B. De Souza, Ricardo M. Campello Department of Mathematics Federal University of Pernambuco Recife Brazil Department of Electronics and Systems Federal University of Pernambuco Recife Brazil

ISBN: (纸本)9780769548296

In this paper, histogram uniformization of digital images by means of the finite field cosine transform (FFCT) is examined. the approach consists in dividing the image into blocks and applying the FFCT, in a recursive manner, to each block. Simulations of the procedure show that the histogram of the transformed image exhibits a uniform shape and its pixels have low correlation with their neighbors. this result is achieved due to the modular arithmetic used in the application of the FFCT to the image blocks. the suitability of the proposed technique in the context of image encryption is discussed. © 2012 IEEE.

关键词： Cosine transforms

来源：评论

学校读者我要写书评

暂无评论

Realistic modeling of self-adapted spider orb-webs in real-time

Realistic modeling of self-adapted spider orb-webs in real-t...

引用

2013 26th Conference on graphics, Patterns and images, SIBGRAPI 2013

作者： Schmitt, Wagner Walter, Marcelo Comba, Joao Luiz Dihl Instituto de Informatica UFRGS Porto Alegre Brazil

ISBN: (纸本)9780769550992

Modeling organic objects and natural phenomena is a very time consuming task, and usually requires a certain level of expertise. this happens due to the lack of suitable geometric primitives available in most modeling tools. In addition, with the great advance in real-time rendering power, there is a growing demand for more complex models. Hence, this paper proposes a method to automatically build visually convincing spider orb-webs that are self-adapted to the environment. We show results of mesh-based spider orb-webs built in real-time that are visually pleasing and realistically looking. © 2013 IEEE.

关键词： Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

Measuring Hierarchiness of image Segmentations 37

Measuring Hierarchiness of Image Segmentations

引用

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

作者： Belem, Felipe Kochem, Fabio Patrocinio, Zenilton, Jr. Perret, Benjamin Cousty, Jean Falcao, Alexandre Guimaraes, Silvio Jamil F. Pontificia Univ Catolica Minas Gerais IMSci BR-30535901 Belo Horizonte MG Brazil Univ Estadual Campinas LIDS BR-13083970 Sao Paulo Brazil Univ Gustave Eiffel CNRS LIGM F-77454 Marne La Valee France

ISBN: (纸本)9798350376043;9798350376036

Numerous segmentation methods are able to produce several partitions of the same image by tuning a scale parameter. In such a series of multilevel segmentations, if every region at a given level is included in a single region of the segmentation at the next level, then the series is called a hierarchy. Hierarchies are often desired for multiscale image representation and analysis due to their mathematical properties, leading to accurate and efficient solutions. Although certain effective strategies may not produce a hierarchy, it is uncertain whether their multiscale output is close to be one. this work explores several cases when analyzing two consecutive segmentations, as full inflation and full merge, for instance. From those, we provide three measures for evaluating the hierarchiness between two subsequent partitions: (i) nestedness;(ii) refinement error;and (iii) inflation ration. Using our proposals in a in-sequence pairwise comparison, as shown by the experimental results, it is possible to verify whether a multiscale segmentation is a hierarchy and, if not, to analyze the nature and extent of the hierarchical errors that prevent it from becoming hierarchical.

关键词： Inflation

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：