检索结果-内蒙古大学图书馆

5th international conference on scale space and PDE methods in computer vision, scale-space 2005

作者： Platel, B. Demirci, M. Fatih Shokoufandeh, A. Florack, L.M.J. Kanters, F.M.W. Ter Haar Romeny, B.M. Dickinson, S.J. Eindhoven University of Technology P.O. Box 513 5600 MB Eindhoven Netherlands Drexel University 3141 Chestnut Street Philadelphia PA 19104 United States University of Toronto 6 King's College Rd. Toronto Ont. M5S 3G4 Canada

In previous work, singular points (or top points) in the scale space representation of generic images have proven valuable for image matching. In this paper, we propose a construction that encodes the scale space description of top points in the form of a directed acyclic graph. This representation allows us to utilize graph matching algorithms for comparing images represented in terms of top point configurations instead of using solely the top points and their features in a point matching algorithm, as was done previously. The nodes of the graph represent the critical paths together with their top points. The edge set will capture the neighborhood distribution of vertices in scale space, and is constructed through a Delaunay triangulation scheme. We also will present a many-to-many matching algorithm for comparing such graph-based representations. This algorithm is based on a metric-tree representation of labelled graphs and their low-distortion embeddings into normed vector spaces via spherical encoding. This is a two-step transformation that reduces the matching problem to that of computing a distribution-based distance measure between two such embeddings. To evaluate the quality of our representation, two sets of experiments are considered. First, the stability of this representation under Gaussian noise of increasing magnitude is examined. In the second set of experiments, a series of recognition experiments is run on a small face database. © Springer-Verlag Berlin Heidelberg 2005.

关键词： Image processing

来源：评论

学校读者我要写书评

暂无评论

Feature-based image analysis

引用

international JOURNAL OF computer vision 2003年第2-3期52卷 73-95页

作者： Lillholm, M Nielsen, M Griffin, LD IT Univ Copenhagen Copenhagen NV Denmark Kings Coll London London WC2R 2LS England

According to Marr's paradigm of computational vision the first process is an extraction of relevant features. The goal of this paper is to quantify and characterize the information carried by features using image-structure measured at feature-points to reconstruct images. In this way, we indirectly evaluate the concept of feature-based image analysis. The main conclusions are that (i) a reasonably low number of features characterize the image to such a high degree, that visually appealing reconstructions are possible, (ii) different feature-types complement each other and all carry important information. The strategy is to define metamery classes of images and examine the information content of a canonical least informative representative of this class. Algorithms for identifying these are given. Finally, feature detectors localizing the most informative points relative to different complexity measures derived from models of natural image statistics, are given.

关键词： features stochastic complexity statistics of natural images least commitment scale-space image reconstruction variational methods

来源：评论

学校读者我要写书评

暂无评论

A distance measure and a feature likelihood map concept for scale-invariant model matching

引用

international JOURNAL OF computer vision 2003年第2-3期52卷 97-120页

作者： Laptev, I Lindeberg, T Royal Inst Technol Computat Vis & Act Percept Lab Dept Numer Anal & Comp Sci SE-10044 Stockholm Sweden

This paper presents two approaches for evaluating multi-scale feature-based object models. Within the first approach, a scale-invariant distance measure is proposed for comparing two image representations in terms of multi-scale features. Based on this measure, the maximisation of the likelihood of parameterised feature models allows for simultaneous model selection and parameter estimation. The idea of the second approach is to avoid an explicit feature extraction step and to evaluate models using a function defined directly from the image data. For this purpose, we propose the concept of a feature likelihood map, which is a function normalised to the interval [0, 1], and that approximates the likelihood of image features at all points in scale-space. To illustrate the applicability of both methods, we consider the area of hand gesture analysis and show how the proposed evaluation schemes can be integrated within a particle filtering approach for performing simultaneous tracking and recognition of hand models under variations in the position, orientation, size and posture of the hand. The experiments demonstrate the feasibility of the approach, and that real time performance can be obtained by pyramid implementations of the proposed concepts.

关键词： matching scale-space image features tracking recognition multi-scale representations

来源：评论

学校读者我要写书评

暂无评论

Selection of optimal stopping time for nonlinear diffusion filtering

引用

international JOURNAL OF computer vision 2003年第2-3期52卷 189-203页

作者： Mrázek, P Navara, M Czech Tech Univ Ctr Appl Cybernet Fac Elect Engn Prague 16627 6 Czech Republic Czech Tech Univ Ctr Machine Percept Dept Cybernet Fac Elect Engn Prague 16627 6 Czech Republic

We develop a novel time-selection strategy for iterative image restoration techniques: the stopping time is chosen so that the correlation of signal and noise in the filtered image is minimized. The new method is applicable to any images where the noise to be removed is uncorrelated with the signal, under the assumptions that the filter used is suitable for the given type of data, and that neither the additive noise nor the filtering procedure alter the average gray value;no other knowledge (e. g. the noise variance, training data etc.) is needed. We analyse the theoretical properties of the method, then test the performance of our time estimation procedure experimentally, and demonstrate that it yields near-optimal results for a wide range of noise levels and for various filtering methods.

关键词： nonlinear diffusion stopping time regularization parameter image restoration scale space

来源：评论

学校读者我要写书评

暂无评论

4th international conference on scale space methods in computer vision, scale space 2003

4th International Conference on Scale Space Methods in Compu...

引用

4th international conference on scale space methods in computer vision, scale space 2003

ISBN: (纸本)354040368X

The proceedings contain 56 papers. The special focus in this conference is on Deep Structure Representation, scale space Mathematics, Equivalences, Implementing scale spaces and Other Evolution Equations. The topics include: Many-to-many matching of scale-space feature hierarchies using metric embedding;content based image retrieval using multiscale top points;feature coding with a statistically independent cortical representation;scale-space image analysis based on hermite polynomials theory;a complete system of measurement invariants for abelian lie transformation groups;equivalence results for TV diffusion and TV regularisation;correspondences between wavelet shrinkage and nonlinear diffusion;a generalized discrete scale-space formulation for 2-d and 3-d signals;real-time scale selection in hybrid multi-scale representations;a scale space for contour registration using minimal surfaces;the maximum principle for Beltrami color flow;the monogenic scale space on a bounded domain and its applications;least squares and robust estimation of local image structure;mode estimation using pessimistic scale space tracking;properties of Brownian image models in scale-space;image decomposition application to SAR images;basic morphological operations, band-limited images and sampling;an explanation for the logarithmic connection between linear and morphological systems;interest point detection and scale selection in space-time;towards recognition-based variational segmentation using shape priors and dynamic labeling;a Markov random field approach to multi-scale shape analysis and regularizing a set of unstructured 3d points from a sequence of stereo images.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Using the complex Ginzburg-Landau equation for digital inpainting in 2D and 3D

Using the complex Ginzburg-Landau equation for digital inpai...

引用

4th international conference on scale space methods in computer vision

作者： Grossauer, H Scherzer, O Univ Innsbruck Dept Comp Sci A-6020 Innsbruck Austria

ISBN: (纸本)354040368X

Recently, several different approaches for digital inpainting have been proposed in the literature. We give a review and introduce a novel approach based on the complex Ginzburg-Landau equation. The use of this equation is motivated by some of its remarkable analytical properties. While common inpainting technology is especially designed for restorations of two dimensional image data, the Ginzburg-Landau equation can straight forwardly be applied to restore higher dimensional data, which has applications in frame interpolation, improving sparsely sampled volumetric data and to fill in fragmentary surfaces. The latter application is of importance in architectural heritage preservation. We discuss a stable and efficient scheme for the numerical solution of the Ginzburg-Landau equation and present some numerical experiments. We compare the performance of our algorithm with other well established methods for inpainting.

关键词： Ginzburg-Landau equation inpainting diffusion filtering non-linear partial differential equations variational problems

来源：评论

学校读者我要写书评

暂无评论

3rd international conference on scale-space and Morphology in computer vision, scale-space 2001

引用

3rd international conference on scale-space and Morphology in computer vision, scale-space 2001

ISBN: (纸本)9783540423171

The proceedings contain 41 papers. The special focus in this conference is on scale-space and Morphology in computer vision. The topics include: Using the vector distance functions to evolve manifolds of arbitrary codimension;computing optic flow by scale space integration of normal flow;image registration, optical flow, and local rigidity;tracking of multi-state hand models using particle filtering and a hierarchy of multi-scale image features;a note on two classical shock filters and their asymptotics;Bayesian object detection through level curves selection;a multi-scale feature likelihood map for direct evaluation of object hypotheses;total variation based oversampling of noisy images;down scaling for better transform compression;algebraic and PDE approaches for multiscale image operators with global constraints;adjunctions in pyramids and curve evolution;hierarchies of partitions and morphological segmentation;scale-space theories for scalar and vector images;generic multi-scale segmentation and curve approximation method;exploring non-linear diffusion;bilateral filtering and anisotropic diffusion;an accurate operator splitting scheme for nonlinear diffusion filtering;selection of optimal stopping time for nonlinear diffusion filtering;combing a porcupine via stereographic direction diffusion;indentation and protrusion detection and its applications;geodesic active contours applied to texture feature space;geometry motivated variational segmentation for color images;hierarchical segmentation using dynamics of multiscale color gradient watersheds;fast statistical level sets image segmentation for biomedical applications and morphological tools for robust key-region extraction and video shot modeling.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Geometry motivated variational segmentation for color images 3

引用

3rd international conference on scale-space and Morphology in computer vision, scale-space 2001

作者： Brook, Alexander Kimmel, Ron Sochen, Nir A. Dept. Of Mathematics Technion Israel Dept. Of Computer Science Technion Israel Dept. Of Applied Mathematics Tel-Aviv University Israel

We propose image enhancement, edge detection, and segmentation models for the multi-channel case, motivated by the philosophy of processing images as surfaces, and generalizing the Mumford-Shah functional. Refer to ht... 详细信息

ISBN: (纸本)9783540423171

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Inverse scale space theory for inverse problems

引用

3rd international conference on scale-space 2001

作者： Scherzer, O Groetsch, C Univ Bayreuth Angew Math D-95440 Bayreuth Germany Univ Cincinnati Dept Math Cincinnati OH 45221 USA

ISBN: (纸本)3540423176

In this paper we derive scale space methods for inverse problems which satisfy the fundamental axioms of fidelity and causality and we provide numerical illustrations of the use of such methods in deblurring. These scale space methods are asymptotic formulations of the Tikhonov-Morozov regularization method. The analysis and illustrations relate diffusion filtering methods in image processing to Tikhonov regularization methods in inverse theory.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Selection of optimal stopping time for nonlinear diffusion filtering 3

引用

3rd international conference on scale-space 2001

作者： Mrázek, P Czech Tech Univ Fac Elect Engn Ctr Machine Percept Prague 16627 6 Czech Republic

ISBN: (纸本)3540423176

We develop a novel time-selection strategy for iterative image restoration techniques: the stopping time is chosen so that the correlation of signal and noise in the filtered image is minimised. The new method is applicable to any images where the noise to be removed is uncorrelated with the signal, no other knowledge (e.g. the noise variance, training data etc.) is needed. We test the performance of our time estimation procedure experimentally, and demonstrate that it yields near-optimal results for a wide range of noise levels and for various filtering methods.

关键词： Iterative methods

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：