检索结果-内蒙古大学图书馆

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

作者： Gomes, Rafael Beserra Aroca, Rafael Vidal De Carvalho, Bruno Motta Goncalves, Luiz Marcos Garcia Department of Computing Engineering and Automation UFRN Natal Brazil Department of Informatics and Applied Mathematics UFRN Natal Brazil

ISBN: (纸本)9780769548296

We propose a novel and fast interactive segmentation methodology for computer vision applications. Basically, the proposed system performs the tracking of seeds so that multiple seeds can be acquired over time, substantially improving the segmentation results. Moreover, instead of image coordinates, the user indicates points in the real-world that become seeds in the image. these seeds can be indicated, for example using a laser pointer or a smart-phone. the seeds can then be tracked and used by a segmentation algorithm. Experiments using the Lucas-Kanade Optical Flow and the Fast Multi-Object Fuzzy Segmentation (Fast-MOFS) algorithm demonstrate that the proposed technique successfully segments images in real-time and improves the user ability to directly segment an object in the real world. the proposed system has a high performance, allowing it to be used with high frame rates in devices with low processing capability and/or with restricted power requirements. © 2012 IEEE.

关键词： computer vision

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

Analysis of the impact of visual attacks on the characteristics of neural networks in image recognition 14

Analysis of the impact of visual attacks on the characterist...

引用

14th International symposium on Intelligent Systems

作者： Andriyanov, N. A. Dementiev, V. E. Kargashin, Yu D. Financial Univ Govt Russian Federat Leningradsky AveH 49 Moscow 125993 Russia Ulyanovsk State Tech Univ Severny Venets StH 32 Ulyanovsk 432027 Russia JSC RPC Istok Vokzalnaya StH 2 Fryazino 141190 Moscow Region Russia

the article discusses various methods of visual attacks on neural networks such as the introducing of additive white Gaussian noise, pixel maximization and minimization of brightness, maximization and minimization of brightness in the area. For well-known datasets (MNIST, Kaggle dataset called as Dogs_vs_Cats), the dependence of the proportion of correct recognitions on the proportion of distorted images in the test sample is studied. Networks such as VGG-16, Inception_v3, networks without training transfer are analyzed. the characteristics of the accuracy of such networks from the noise level in the image, from the size of the attack areas are obtained. the probabilities of belonging to a given class for various images in various attacks are analyzed. As a method for combating visual attacks, it is proposed to single out a new class during training: "poor image". By selecting valid images by dumping "bad images" by the neural network, accuracy is improved even in the case of a large volume of distorted images in the test sample. the accuracy of such a network is compared for N classes and for (N + 1) classes of images. Ways of further research and ideas of alternative methods of combating visual attacks on neural networks are formulated. (C) 2021 the Authors. Published by Elsevier B.V.

关键词： Convolutional neural networks pattern recognition visual attacks VGG-16 Inception_v3 image processing

来源：评论

学校读者我要写书评

暂无评论

Object Distance Estimation with Machine Learning Algorithms for Stereo Vision 14

Object Distance Estimation with Machine Learning Algorithms ...

引用

14th International Joint symposium on Artificial Intelligence and Natural Language processing, iSAI-NLP 2019

作者： Akepitaktam, Pawarit Hnoohom, Narit Mahidol University Department of Computer Engineering Image Nakorn Pathom Thailand

ISBN: (纸本)9781728156316

this paper presents a novel distance estimation to calculate distances from the stereo camera to the object accurately. this study collected stereo camera images as a dataset, each object determined at two different lighting environments and five different distances between the stereo camera and the object. To estimate the distance, researchers applied supervised learning methods to approach this task. there were performed with two machine learning algorithms: Linear Regression, and Artificial Neuron Network Regression. In the experimental results, the efficiency of the proposed method was examined by using the evaluation metrics to calculate the distance estimation errors. the results showed the model of convolutional neuron networks operated with densely connected neuron networks has the lowest errors rate in comparison with other models. the model eliminates the error rate of distance estimation at 0.000531, 0.014490, and 0.000048 meters, measured by mean square error, mean absolute error and mean logarithmic error respectively. © 2019 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Evaluation of a feature tracking vision application on a heterogeneous chip 26

Evaluation of a feature tracking vision application on a het...

引用

26th International symposium on computer Architecture and High Performance Computing, SBAC-PAD 2014

作者： Gran, Rubén Shi, August Totoni, Ehsan Garzarán, María J. University of Zaragoza C/ María de Luna 3 Zaragoza50018 Spain University of Illinois at Urbana-Champaign 201 N. Goodwin UrbanaIL61801 United States

ISBN: (纸本)9781479969043

Consumers of personal devices such as desktops, tablets, or smart phones run applications based on image or video processing, as they enable a natural computer-user interaction. the challenge with these computationally demanding applications is to execute them efficiently. One way to address this problem is to use on-chip heterogeneous systems, where tasks can execute in the device where they run more efficiently. In this paper, we discuss the optimization of a feature tracking application, written in OpenCL, when running on an on-chip heterogeneous platform. Our results show that OpenCL can facilitate programming of these heterogeneous systems because it provides a unified programming paradigm and at the same time can deliver significant performance improvements. We show that, after optimization, our feature tracking application runs 3.2, 2.6, and 4.3 times faster and consumes 2.2, 3.1, and 2.7 times less energy when running on the multicore, the GPU, or both the CPU and the GPU of an Intel i7, respectively. © 2014 IEEE.

关键词： graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

MODULAR SYSTOLIC ARCHITECTURE FOR image CONVOLUTIONS.

引用

14th Annual International symposium on computer Architecture - Conference Proceedings.

作者： Doshi, Kshitij Varman, Peter Rice Univ Houston TX USA Rice Univ Houston TX USA

ISBN: (纸本)0818607769

A modular, systolic design is described for two-dimensional convolution, which is a frequent and computationally intensive operation in low-level image processing. the design consists of a one-dimensional array of homogeneous cells, each with a fixed amount of storage. Schema are presented by which a design consisting of a limited number of cells can be used to implement convolutions of varying kernel sizes, with optimal throughput. the design is simple and hence a good candidate for VLSI integration. Its one-dimensional organization and unidirectional data-flow characteristics result in good fault tolerance for the array.

关键词： computer ARCHITECTURE

来源：评论

学校读者我要写书评

暂无评论

A Unified Approach to the processing of Hyperspectral images 14th

A Unified Approach to the Processing of Hyperspectral Images

引用

14th International symposium on Mathematical Morphology (ISMM)

作者： Burgeth, Bernhard Didas, Stephan Kleefeld, Andreas Saarland Univ D-66123 Saarbrucken Germany Trier Univ Appl Sci Environm Campus Birkenfeld D-55761 Birkenfeld Germany Forschungszentrum Julich Julich Supercomp Ctr D-52425 Julich Germany

ISBN: (纸本)9783030208677;9783030208660

Since vector fields, such as RGB-color, multispectral or hyperspectral images, possess only limited algebraic and ordering structures they do not lend themselves easily to image processing methods. However, for fields of symmetric matrices a sufficiently elaborate calculus, that includes, for example, suitable notions of multiplication, supremum/infimum and concatenation with real functions, is available. In this article a vector field is coded as a matrix field, which is then processed by means of the matrix valued counterparts of image processing methods. An approximate decoding step transforms a processed matrix field back into a vector field. Here we focus on proposing suitable notions of a pseudo-supremum/infimum of two vectors/colors and a PDE-based dilation/erosion process of color images as a proof-of-concept. In principle there is no restriction on the dimension of the vectors considered. Experiments, mainly on RGB-images for presentation reasons, will reveal the merits and the shortcomings of the proposed methods.

关键词： Multispectral image Hyperspectral image Matrix field Mathematical morphology

来源：评论

学校读者我要写书评

暂无评论

image processing assessment of femoral osteopenia

引用

JOURNAL OF DIGITAL IMAGING 1997年第3期10卷 218-221页

作者： Lee, RL Dacre, JE James, MF 1. Centre for Health Informatics & Multiprofessional Education UCL Medical School Whittington Hospital 4th Floor Archway Wing N19 5NE London UK 2. SmithKline Beecham Pharmaceuticals Essex UK

Visual assessment of femoral osteopenia (the radiographic presentation of osteoporosis) is unreliable. Many of the short-comings of observer grading can be overcome by digital image analysis. Our group has developed algorithms to make automatic assessment of osteopenia from clinical radiographs. Texture Analysis Models (TA) commonly used in image analysis were investigated as measures of osteopenia. Unlike densitometric methods, TA characterizes properties of the structure of the image lie, trabecular patterns). A group of women were analyzed whose subjects ranged from those at risk of osteoporosis (n = 24) to normal (n = 40). Using an IBM PC, frame-grabber, camera, and light-box, we appraised five statistical TA algorithms for assessment of the femoral neck in standard pelvic radiographs: (1) Fractal Signature (FS) describes the image's fractal nature. (2) Auto-Correlation of unaltered and Sobel Edge Transformed images (ACSE) measures image spatial self-similarity. (3) Go-occurrence Matrices (CM) gives the joint probability of greylevels with distance/direction and describes statistical relationships of image variation. (4) Textural Spectrum (TS) neighborhood pixel relationships measure regional directional and pixel-inversion properties. (5) Eular Numbers (EN) describe texture by properties (such as connectivity) of binary images. Good reproducibility from repeated analysis of radiographs was shown using both paired t-tests and Altman-Bland's methods. We have shown a correlation between femoral neck bone mineral density (BMD-the ''gold standard'' of osteoporosis assessment) and textural measures for all five algorithms. Significant measures of osteopenia were: ACSE (r = 0.6, P < .001), CM (r = -0.69, P < .001), FS (r = 0.35, P < .01), TS (r = 0.52, P < .001) and EN (r = -0.39, P < .01). Relationships were also found between textural characteristics and age/weight. TA techniques characterize the radiographic changes of bone in osteoporosis. Technology based on thes

关键词： osteoporosis femoral radiographs digital image processing texture analysis

来源：评论

学校读者我要写书评

暂无评论

3D Face Reconstruction from Video Using 3D Morphable Model and Silhouette 27

3D Face Reconstruction from Video Using 3D Morphable Model a...

引用

27th SIBGRAPI Conference on graphics, Patterns and images (SIBGRAPI)

作者： Baumberger, Christian Reyes, Mauricio Constantinescu, Mihai Olariu, Radu de Aguiar, Edilson Oliveira-Santos, thiago Univ Bern CH-3012 Bern Switzerland Inselspital Bern Bern Switzerland Univ Fed Espirito Santo Vitoria ES Brazil

ISBN: (纸本)9781479942602

Capitalizing on the advances of 3D face reconstruction from computer graphics and computer vision, this work presents a system to enable precise and robust 3D facial reconstruction from video in order to improve current approaches for doctor-patient communication tools. the reconstructed face can be used for emulation of aesthetic procedures in 3D. the proposed 3D face reconstruction algorithm uses a statistical shape model as well as information from facial landmarks and silhouette to iteratively model the face of a subject moving the face from front to left. the presented 3D active shape model approach enables the spatio-temporal tracking of facial landmarks and pose estimation based on a few initial facial landmarks defined in the first frame. Silhouette information extracted from key frames allows for better face reconstruction. the proposed methods were rigorously evaluated with experiments using real and artificial data. Results showed that the proposed method can detect facial landmarks with an approximate median error of 5% intraocular distance, can estimate pose with a median error below 5 degrees, and that silhouette information can improve reconstruction accuracy in all facial regions, specially on the cheeks.

关键词： morphable model face reconstruction computer graphics

来源：评论

学校读者我要写书评

暂无评论

Generalized rigid and generalized affine image registration and interpolation by geometric multigrid

Generalized rigid and generalized affine image registration ...

引用

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

作者： Keeling, Stephen L. Karl Franzens Univ Graz Inst Math & Wissenschaftliches Rechmen A-8010 Graz Austria

Generalized rigid and generalized affine registration and interpolation obtained by finite displacements and by optical flow are here developed variationally and numerically as well as with respect to a geometric multigrid solution process. For high order optimality systems under natural boundary conditions, it is shown that the convergence criteria of Hackbusch (Iterative Solution of Large Sparse Systems of Equations. Springer, Berlin, 1993) are met. Specifically, the Galerkin formalism is used together with a multi-colored ordering of unknowns to permit vectorization of a symmetric successive over-relaxation on image processing systems. the geometric multigrid procedure is situated as an inner iteration within an outer Newton or lagged diffusivity iteration, which in turn is embedded within a pyramidal scheme that initializes each outer iteration from predictions obtained on coarser levels. Differences between results obtainable by finite displacements and by optical flows are elucidated. Specifically, independence of image order can be shown for optical flow but in general not for finite displacements. Also, while autonomous optical flows are used in practice, it is shown explicitly that finite displacements generate a broader class of registrations. this work is motivated by applications in histological reconstruction and in dynamic medical imaging, and results are shown for such realistic examples.

关键词： generalized rigid generalized affine image registration image interpolation geometric multigrid

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：