检索结果-内蒙古大学图书馆

Proceedings - 10th IEEE International Conference on computer vision, ICCV 2005

作者： El-Melegy, Moumen T. Al-Ashwal, Nagi H. Farag, Aly A. Electrical Engineering Department Assiut University Assiut 71516 Egypt Computer Vision and Image Processing Lab. University of Louisville KY 40292

ISBN: (纸本)076952334X

In this paper, we propose a variational method to segment image objects, which have a given parametric shape based on a level-set formulation of the Mumford-Shah functional, and the shape parameters. We define an energy functional composed by two complementary terms. The first one detects object boundaries using a Chan-Vese-like method. The second term constrains the contour to find a shape compatible with the parametric shape. The segmentation of the object of interest is given by the minimum of our energy functional. This minimum is computed with the calculus of variation and the gradient descent method that provide a system of evolution equations solved with the well-known level set method. We focus in this paper on the parametric category of image linear objects. Applications of the proposed model are presented on synthetic and real images. © 2005 IEEE.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

A robust matching algorithm for active appearance models 1

引用

Workshops Bildverarbeitung fur die Medizin: Algorithmen - Systeme - Anwendungen, BVM 2005 - Workshop on image processing for Medicine: Algorithms - Systems - Applications, BVM 2005

作者： Beichel, Reinhard Bischof, Horst Langs, Georg Sonka, Milan Institute for Computer Graphics and Vision Graz University of Technology Inffeldgasse 16/2 A-8010 Graz Austria Pattern Recognition and Image Processing Group Vienna University of Technology Favoritenstr. 9 A-1040 Vienna Austria Department of Electrical and Computer Engineering University of Iowa Iowa City IA 52242 United States

ISBN: (数字)9783540264316

ISBN: (纸本)3540250522

This paper proposes a method for robustly matching active appearance models (AAMs) on images with gross disturbances (outliers). The method consists of two steps. First, an initial residual is calculated by comparing model and image appearance, and modes of the residual are analyzed. Second, all possible mode combinations are tested by evaluating an objective function. The objective function allows the selection of an outlier-free mode combination. Experiments demonstrate the ability of the robust matching method to successfully cope with outliers - compared to standard AAM matching, no degeneration of the model during matching occurs.

关键词： Statistics

来源：评论

学校读者我要写书评

暂无评论

Variational-based method to extract parametric shapes from images

Variational-based method to extract parametric shapes from i...

引用

International Conference on computer vision (ICCV)

作者： M.T. El-Melegy N.H. Al-Ashwal A.A. Farag Electrical Engineering Department Assiut University Asyut Egypt Computer Vision and Image Processing Laboratory University of Louisville KY USA

关键词： Shape image segmentation Level set computer vision Focusing image processing Object detection Calculus Application software Equations

来源：评论

学校读者我要写书评

暂无评论

Shape-based MRI data segmentation in the presence of intensity inhomogeneities using level sets

引用

International Congress Series 2004年第C期1268卷 213-218页

作者： Hassan, Hossam Farag, Aly A. Electrical and Computer Engineering Computer Vision and Image Processing Laboratory University of Louisville Louisville KY 40292 403 Lutz Hall Building Universit United States

Magnetic resonance imaging (MRI) intensity inhomogeneities can be attributed to imperfections in the RF coils or some problems associated with the acquisition sequences. The result is a slowly varying shading artifact over the image that can produce errors with conventional intensity-based classification. The removal of the spatial intensity inhomogeneities from MR images is difficult because the inhomogeneities could change with different MRI acquisition parameters from patient to patient and from slice to slice. We propose a shape-based classification technique to overcome this problem using the level set approach. A signed distance function is dedicated to describe the model of the tissue of interest. Then, a partial differential equation (PDE) is derived to describe the evolution of an observed structure. At each iteration, the observed structure is registered with the prior shape model. The algorithm is used at different levels of noise and intensity inhomogeneities showing a good accuracy. © 2004, Elsevier Inc. All rights reserved.

关键词： Bias field image segmentation Level set segmentation MR imaging PDE

来源：评论

学校读者我要写书评

暂无评论

Intensity and region-of-interest-based finite-element modeling of brain deformation

引用

International Congress Series 2004年第C期1268卷 373-377页

作者： Shi, Hongjian Farag, Aly Computer Vision Image Processing Laboratory Electrical Computer Engineering University of Louisville Louisville KY 40292 403 Lutz Hall Building United States

This paper proposes intensity and region-of-interest-based finite-element modeling of brain deformation. The modeling is based on the intensities of voxels within each element and motion analysis of region of interest (ROI) for image-guided minimally invasive surgery (MIS) applications. It is proposed to configure an ROI at the tip of surgical tools instead of the whole brain, so that the FEM is applied only on the ROI, and the maximum nodal displacement outside the ROI is small and in control. The deformed MR image using the proposed finite-element modeling shows better proportion to its original structures. © 2004, Elsevier Science B.V. All rights reserved.

关键词： Brain deformation Finite-element modeling Minimal invasive surgery

来源：评论

学校读者我要写书评

暂无评论

Real-time vision-based approach for probe tracking in operating room

引用

International Congress Series 2004年 1268卷 467-472页

作者： Aly A. Farag M.Sabry Hassouna Ayman El-Baz S. Hushek Computer Vision and Image Processing Laboratory Electrical and Computer Engineering University of Louisville 403 Lutz Hall Bldg. Louisville KY 40292 USA Department of Neurological Surgery University of Louisville USA

A hand-held surgical probe is an essential component of any image-guided neurosurgery (IGNS). During the surgical procedure, the IGNS tracks the probe position and displays the anatomy beneath it as three orthogonal image slices on a workstation-based 3D imaging system. Existing IGNS systems use different tracking techniques including mechanical, optical, ultrasonic, and electromagnetic systems. In this paper, we present a new computational vision-based probe tracking technique, which provides both position and orientation. We also propose another new computational vision-based technique to track the patient head and thus compensate for its movement during probing procedure. The proposed system is completely passive, its stereo cameras detect the presence of the probe using available visible light, and reports on their exact location and orientation in patient physical space in real time. We have validated the system using a skull phantom and a hand made probe.

关键词： image-guided neurosurgery Head motion tracking Probe tracking vision tracking

来源：评论

学校读者我要写书评

暂无评论

Enhancement of stents using interference of low-frequency ultrasonic echo signals

引用

Journal of Medical Ultrasonics 2004年第2期31卷 67-73页

作者： Ohashi, Gosuke Ohya, Akihisa Tobise, Kazimobu Akiyama, Iwaki Faculty of Engineering Shizuoka University Hamamatsu Japan Institute of Information Sciences and Electronics University of Tsukuba Tsukuba Japan Shoryo Electronic Corporation Kamakura Japan Faculty of Engineering Shonan Institute of Technology Fujisawa Japan Image Processing and Vision Research Laboratory Department of Electrical and Computer Engineering University of California at Santa Barbara Santa Barbara CA 93106-9560 United States

Purpose. We set out to enhance the imaging of stents used for coronary coarctation surgery without imaging the reticulation of the stent. Because the stent is a reticulated structure, there is a relation between ultrasound wavelength and the interstice reticulation that produces the echo. Methods. First we performed computer simulation by ultrasound frequency of transmitted signals to analyze this relation. Then, instead of controlling the transmitted wave, we processed the returned signals through a band-pass filter because of the difficulty of controlling the transmitted waves of diagnostic ultrasound equipment. Following this, we conducted experiments on an agar gel phantom containing a stent to verify the effectiveness of this method. Results. The simulation confirmed that the stent was apparent when the ultrasonic wavelength equaled the product of an integer and twice the interval of the reticulation of the stent. Application of a band-pass filter of 0.8 to 1.5MHz to the waveform returned from the agar gel phantom containing the stent. Conclusions. The effectiveness of this method in depicting the stent was confirmed. © The Japan Society of Ultrasonics in Medicine 2004.

关键词： Interference Received waveform Signal processing Stent Ultrasonic echography

来源：评论

学校读者我要写书评

暂无评论

Features extraction based on fuzzy clustering and segmentation onto the motion region for medium field surveillance application

Features extraction based on fuzzy clustering and segmentati...

引用

International Conference on computer Graphics, Imaging and Visualization, CGIV

作者： M.N. Maliki S.A.R.A.B. Al-Attas Computer Vision Video and Image Processing (CVVIP) Research Group Department of Microelectronic and Computer Engineering (MiCE) Faculty of Electrical Engineering Universiti Teknologi Malaysia Skudai Johor Malaysia Computer Vision Universiti Teknologi Malaysia Skudai Johor Malaysia Universiti Teknologi Malaysia Skudai Johor MY Dept. of Microelectron. & Comput. Eng. Univ. Teknologi Malaysia Johor Malaysia

Fuzzy-based clustering algorithm is becoming popular in image processing, especially in image segmentation. Based on the degree of the membership function, each pixel can be grouped into "natural group" of pixels according to the spatial coordinate using their values. In this work we present features extraction based on fuzzy clustering and segmentation onto the motion region for medium field surveillance application. Instead of using blob analysis, we believe that fuzzy based clustering algorithm, can also be used to generate different clusters. Incorporating the motion-based segmentation the complexity of the fuzzy clustering is also reduced because only the motion region is processed to the clustering algorithm.

关键词： Feature extraction Surveillance Clustering algorithms image segmentation Equations Prototypes Application software computer vision image processing Data mining

来源：评论

学校读者我要写书评

暂无评论

Multimodality image registration and fusion using neural network

引用

Journal of Harbin Institute of Technology(New Series) 2003年第3期10卷 235-240页

作者： Mostafa G Mostafa Aly A Farag Edward Essock Computer Vision and Image Processing Laboratory Dept. of Electrical and Computer Engineering University of Louisville Louisville KY 40292 USAComputer Vision and Image Processing Laboratory Dept. of Electrical and Computer Engineering University of Louisville Louisville KY 40292 USADept. of Psychology University of Louisville Louisville kY 40292 USA

Multimodality image registration and fusion are essential steps in building 3-D models from remotesensing data. We present in this paper a neural network technique for the registration and fusion of multimodali-ty remote sensing data for the reconstruction of 3-D models of terrain regions. A FeedForward neural network isused to fuse the intensity data sets with the spatial data set after learning its geometry. Results on real data arepresented. Human performance evaluation is assessed on several perceptual tests in order to evaluate the fusionresults.

关键词： data fusion image registration image interpolation neural network, 3-D model building

来源：评论

学校读者我要写书评

暂无评论

Statistically Robust Approach to Lens Distortion Calibration with Model Selection

Statistically Robust Approach to Lens Distortion Calibration...

引用

Conference on computer vision and Pattern Recognition Workshop, CVPRW 2003

作者： Taha El-Melegy, Moumen Farag, Aly A. Electrical Engineering Dept. Assiut University Assiut Egypt Computer Vision and Image Processing Lab. University of Louisville LouisvilleKY40292 United States

ISBN: (纸本)0769519008

This paper addresses the problem of calibrating camera lens distortion, which can be significant in medium to wide angle lenses. While almost all existing nonmetric distortion calibration methods need user involvement in one form or another,we present an approach to distortion calibration based on the robust the-least-median-of-squares (LMedS) estimator. Our approach is thus able to proceed in a ful ly-automatic manner while being less sensitive to erroneous input data such as image curves that are mistakenly considered as projections of 3D linear segments. Our approach uniquely uses fast, closed-form solutions to the distortion coefficients, which serve as an initial point for a non-linear optimization algorithm to straighten imaged lines. Moreover we propose a method for distortion model selection based on geometrical *** experiments to evaluate the performance of this approach on synthetic and real data are reported. © 2003 IEEE.

关键词： Least squares approximations

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：