检索结果-内蒙古大学图书馆

Automatic Location of Facial Feature Points and Synthesis of Facial Sketches Using Direct Combined Model

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS 2010年第4期40卷 1158-1169页

作者： Tu, Ching-Ting Lien, Jenn-Jier James Natl Cheng Kung Univ Dept Comp Sci & Informat Engn Tainan 70101 Taiwan

Automatically locating multiple feature points (i.e., the shape) in a facial image and then synthesizing the corresponding facial sketch are highly challenging since facial images typically exhibit a wide range of poses, expressions, and scales, and have differing degrees of illumination and/or occlusion. When the facial sketches are to be synthesized in the unique sketching style of a particular artist, the problem becomes even more complex. To resolve these problems, this paper develops an automatic facial sketch synthesis system based on a novel direct combined model (DCM) algorithm. The proposed system executes three cascaded procedures, namely, 1) synthesis of the facial shape from the input texture information (i.e., the facial image);2) synthesis of the exaggerated facial shape from the synthesized facial shape;and 3) synthesis of a sketch from the original input image and the synthesized exaggerated shape. Previous proposals for reconstructing facial shapes and synthesizing the corresponding facial sketches are heavily reliant on the quality of the texture reconstruction results, which, in turn, are highly sensitive to occlusion and lighting effects in the input image. However, the DCM approach proposed in this paper accurately reconstructs the facial shape and then produces lifelike synthesized facial sketches without the need to recover occluded feature points or to restore the texture information lost as a result of unfavorable lighting conditions. Moreover, the DCM approach is capable of synthesizing facial sketches from input images with a wide variety of facial poses, gaze directions, and facial expressions even when such images are not included within the original training data set.

关键词： Active appearance models eigenface face sketch synthesis image processing and computer vision statistical image models

来源：评论

学校读者我要写书评

暂无评论

Accurate and scalable surface representation and reconstruction from images

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2007年第1期29卷 141-158页

作者： Zeng, Gang Paris, Sylvain Quan, Long Sillion, Francois Hong Kong Univ Sci & Technol Dept Comp Sci Kowloon Hong Kong Peoples R China MIT Comp Sci & Artificial Intelligence Lab Cambridge MA 02139 USA INRIA Rhone Alpes ARTIS GRAVIR IMAG F-38330 Montbonnot St Martin France

We introduce a new surface representation method, called patchwork, to extend three-dimensional surface reconstruction capabilities from multiple images. A patchwork is the combination of several patches that are built one by one. This design potentially allows for the reconstruction of an object with arbitrarily large dimensions while preserving a fine level of detail. We formally demonstrate that this strategy leads to a spatial complexity independent of the dimensions of the reconstructed object and to a time complexity that is linear with respect to the object area. The former property ensures that we never run out of storage and the latter means that reconstructing an object can be done in a reasonable amount of time. In addition, we show that the patchwork representation handles equivalently open and closed surfaces, whereas most of the existing approaches are limited to a specific scenario, an open or closed surface, but not both. The patchwork concept is orthogonal to the method chosen for surface optimization. Most of the existing optimization techniques can be cast into this framework. To illustrate the possibilities offered by this approach, we propose two applications that demonstrate how our method dramatically extends a recent accurate graph technique based on minimal cuts. We first revisit the popular carving techniques. This results in a well-posed reconstruction problem that still enjoys the tractability of voxel space. We also show how we can advantageously combine several image-driven criteria to achieve a finely detailed geometry by surface propagation. These two examples demonstrate the versatility and flexibility of patchwork reconstruction. They underscore other properties inherited from patchwork representation: Although some min-cut methods have difficulty in handling complex shapes ( e. g., with complex topologies), they can naturally manipulate any geometry through the patchwork representation while preserving their intrinsic qualities. Th

关键词： computing methodologies image processing and computer vision reconstruction and applications patchwork representation and reconstruction space carving graph-cuts level-sets patch-wise carving patch-wise propagation

来源：评论

学校读者我要写书评

暂无评论

A statistics-based approach to binary image registration with uncertainty analysis

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2007年第1期29卷 112-125页

作者： Simonson, Katherine M. Drescher, Steven M., Jr. Tanner, Franklin R. Sandia Natl Labs Albuquerque NM 87185 USA

A new technique is described for the registration of edge-detected images. While an extensive literature exists on the problem of image registration, few of the current approaches include a well-defined measure of the statistical confidence associated with the solution. Such a measure is essential for many autonomous applications, where registration solutions that are dubious (involving poorly focused images or terrain that is obscured by clouds) must be distinguished from those that are reliable ( based on clear images of highly structured scenes). The technique developed herein utilizes straightforward edge pixel matching to determine the "best" among a class of candidate translations. A well-established statistical procedure, the McNemar test, is then applied to identify which other candidate solutions are not significantly worse than the best solution. This allows for the construction of confidence regions in the space of the registration parameters. The approach is validated through a simulation study and examples are provided of its application in numerous challenging scenarios. While the algorithm is limited to solving for two-dimensional translations, its use in validating solutions to higher-order (rigid body, affine) transformation problems is demonstrated.

关键词： registration edge and feature detection nonparametric statistics uncertainty "fuzzy," and probabilistic reasoning image processing and computer vision

来源：评论

学校读者我要写书评

暂无评论

Collocation for Diffeomorphic Deformations in Medical image Registration

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2018年第7期40卷 1570-1583页

作者： Darkner, Sune Pai, Akshay Liptrot, Matthew G. Sporring, Jon Univ Copenhagen Dept Comp Sci DK-1165 Copenhagen Denmark

Diffeomorphic deformation is a popular choice in medical image registration. A fundamental property of diffeomorphisms is invertibility, implying that once the relation between two points A to B is found, then the relation B to A is given per definition. Consistency is a measure of a numerical algorithm's ability to mimic this invertibility, and achieving consistency has proven to be a challenge for many state-of-the-art algorithms. We present CDD (Collocation for Diffeomorphic Deformations), a numerical solution to diffeomorphic image registration, which solves for the Stationary Velocity Field (SVF) using an implicit A-stable collocation method. CDD guarantees the preservation of the diffeomorphic properties at all discrete points and is thereby consistent to machine precision. We compared CDD's collocation method with the following standard methods: Scaling and Squaring, Forward Euler, and Runge-Kutta 4, and found that CDD is up to 9 orders of magnitude more consistent. Finally, we evaluated CDD on a number of standard bench-mark data sets and compared the results with current state-of-the-art methods: SPM-DARTEL, Diffeomorphic Demons and SyN. We found that CDD outperforms state-of-the-art methods in consistency and delivers comparable or superior registration precision.

关键词： Registration ordinary differential equation convergence and stability model validation and analysis image processing and computer vision

来源：评论

学校读者我要写书评

暂无评论

Fast Keypoint Recognition Using Random Ferns

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2010年第3期32卷 448-461页

作者： Oezuysal, Mustafa Calonder, Michael Lepetit, Vincent Fua, Pascal Ecole Polytech Fed Lausanne IC ISIM CVLab CH-1015 Lausanne Switzerland

While feature point recognition is a key component of modern approaches to object detection, existing approaches require computationally expensive patch preprocessing to handle perspective distortion. In this paper, we show that formulating the problem in a naive Bayesian classification framework makes such preprocessing unnecessary and produces an algorithm that is simple, efficient, and robust. Furthermore, it scales well as the number of classes grows. To recognize the patches surrounding keypoints, our classifier uses hundreds of simple binary features and models class posterior probabilities. We make the problem computationally tractable by assuming independence between arbitrary sets of features. Even though this is not strictly true, we demonstrate that our classifier nevertheless performs remarkably well on image data sets containing very significant perspective changes.

关键词： image processing and computer vision object recognition tracking image registration feature matching naive Bayesian

来源：评论

学校读者我要写书评

暂无评论

General neighborhood sequences in Zⁿ

引用

DISCRETE APPLIED MATHEMATICS 2007年第18期155卷 2507-2522页

作者： Hajdu, Andras Hajdu, Lajos Tijdeman, Robert Univ Debrecen Fac Informat H-4010 Debrecen Hungary Univ Debrecen Hungarian Acad Sci Math Inst Num Theory Res Grp H-4010 Debrecen Hungary Leiden Univ Inst Math NL-2300 RA Leiden Netherlands

Neighborhoods and neighborhood sequences play important roles in several branches of pattern analysis. In earlier papers in Z(n) only certain special (e.g. periodic or octagonal) sequences were investigated. In this paper we study neighborhood sequences which are either ultimately periodic or allow at every neighborhood to do nothing at no cost. We give finite procedures and descriptive theoretical criteria for certain important (e.g. metrical) properties of the sequences. Our results are valid for several types of classical neighborhood sequences and for generated distance functions (e.g. octagonal and chamfer distances) which are widely applied in digital image processing. We conclude the paper by showing how our results contribute to the theory of distance transformations. (D 2007 Elsevier B.V. All rights reserved.

关键词： combinatorial algorithms path and circuit problems geometric algorithms languages and systems image processing and computer vision

来源：评论

学校读者我要写书评

暂无评论

Advanced very low bit rate video coding using preferential pattern selection algorithms

引用

JOURNAL OF RESEARCH AND PRACTICE IN INFORMATION TECHNOLOGY 2005年第3期37卷 285-295页

作者： Paul, M Murshed, M Monash Univ Gippsland Sch Comp & IT Churchill Vic Australia

In the context of very low bit-rate video coding, pre-defined fixed pattern representations of moving regions in blocked-based motion estimation and compensation has become increasingly attractive over H.264 as the former represents an MB by a smaller size moving region covered by the best available pattern that approximates the shape of the region more closely and hence, requiring no extra motion vector, which is not the case with the latter. But fixed set patterns sometimes fail to code efficiently for all video sequences. In this paper a novel idea of selecting a subset of best-matched patterns through preferential selection technique is developed by presenting two algorithms, Variable Pattern Selection (VPS) and Extended VPS (EVPS) for an initial pattern codebook size of 32 using a new parametric macroblock classification definition and a new similarity metric. The complexity analysis confirmed that EVPS guaranteed to be nearly six times faster than VPS, with the peak performance providing an improvement factor of nine times. The overall performance of EVPS is identical to VPS for certain parameters but on average, 0.2dB and 0.8dB better than the contemporary algorithm using fixed set patterns and Advanced Video coding standard (H.264) respectively, for the same. number of bits per frame. ACM Classification: 1.4.2 (Computing methodologies - image processing and computer vision - compression (coding)).

关键词： Computing methodologies image processing and computer vision Compression (coding) Video coding peak performance algorithms Computing Methodologies improvement factor motion vector Complexity Analysis computer-Assisted image processing

来源：评论

学校读者我要写书评

暂无评论

Fast and efficient recursive algorithm of Meixner polynomials

引用

JOURNAL OF REAL-TIME image processing 2021年第6期18卷 2225-2237页

作者： Abdulhussain, Sadiq H. Mahmmod, Basheera M. Univ Baghdad Dept Comp Engn Baghdad Iraq

Meixner polynomials (MNPs) and their moments are considered significant feature extraction tools because of their salient representation in signal processing and computer vision. However, the existing recurrence algorithm of MNPs exhibits numerical instabilities of coefficients for high-order polynomials. This paper proposed a new recurrence algorithm to compute the coefficients of MNPs for high-order polynomials. The proposed algorithm is based on a derived identity for MNPs that reduces the number of the utilized recurrence times and the computed number of MNPs coefficients. To minimize the numerical errors, a new form of the recurrence algorithm is presented. The proposed algorithm computes similar to 50% of the MNP coefficients. A comparison with different state-of-the-art algorithms is performed to evaluate the performance of the proposed recurrence algorithm in terms of computational cost and reconstruction error. In addition, an investigation is performed to find the maximum generated size. The results show that the proposed algorithm remarkably reduces the computational cost and increases the generated size of the MNPs. The proposed algorithm shows an average improvement of similar to 77% in terms of computation cost. In addition, the proposed algorithm exhibits an improvement of similar to 1269% in terms of generated size.

关键词： image processing and computer vision Multimedia Information Systems computer Graphics Pattern Recognition Signal image and Speech processing

来源：评论

学校读者我要写书评

暂无评论

3D Face Discriminant Analysis Using Gauss-Markov Posterior Marginals

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2013年第3期35卷 728-739页

作者： Ocegueda, Omar Fang, Tianhong Shah, Shishir K. Kakadiaris, Ioannis A. Univ Houston Dept Comp Sci Computat Biomed Lab CBL Houston TX 77204 USA

We present a Markov Random Field model for the analysis of lattices (e.g., images or 3D meshes) in terms of the discriminative information of their vertices. The proposed method provides a measure field that estimates the probability of each vertex being "discriminative" or "nondiscriminative" for a given classification task. To illustrate the applicability and generality of our framework;we use the estimated probabilities as feature scoring to define compact signatures for three different classification tasks: 1) 3D Face Recognition, 2) 3D Facial Expression Recognition, and 3) Ethnicity-based Subject Retrieval, obtaining very competitive results. The main contribution of this work lies in the development of a novel framework for feature selection in scenaria in which the most discriminative information is smoothly distributed along a lattice.

关键词： Feature evaluation and selection object recognition Markov random fields segmentation image processing and computer vision pattern recognition face and gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Multifocal projection: A multiprojector technique for increasing focal depth

引用

IEEE TRANSACTIONS ON VISUALIZATION AND computer GRAPHICS 2006年第4期12卷 658-667页

作者： Bimber, O Emmerling, A Bauhaus Univ Weimar D-99423 Weimar Germany

In this paper, we describe a novel multifocal projection concept that applies conventional video projectors and camera feedback. Multiple projectors with differently adjusted focal planes, but overlapping image areas are used. They can be either differently positioned in the environment or can be integrated into a single projection unit. The defocus created on an arbitrary surface is estimated automatically for each projector pixel. If this is known, a final image with minimal defocus can be composed in real-time from individual pixel contributions of all projectors. Our technique is independent of the surfaces' geometry, color and texture, the environment light, as well as of the projectors' position, orientation, luminance, and chrominance.

关键词： computing methodologies computer graphics picture/image generation digitizing and scanning display algorithms image processing and computer vision digitization and image capture radiometry reflectance sampling scanning enhancement sharpening and deblurring scene analysis color shape

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：