检索结果-内蒙古大学图书馆

Animated Talking Head with Personalized 3D Head Model

Journal of VLSI signal processing Systems for signal, image, and Video Technology 1998年第1-2期20卷 97-105页

作者： Ostermann, Jörn Chen, Lawrence S. Huang, Thomas S. AT and T Labs.-Research Red Bank NJ 07701 100 Schultz Dr. United States Beckman Institute CSL University of Urbana IL 61801 United States University of Hannover Imperical College London United States University of Hannover Germany Inst. F. Theor. Nachrichtentechnik United States Vis. Commun. Research Department Bell Labs. United States Image Proc. and Technology Research AT and T Labs.-Research United States University of Illinois Urbana-Champaign IL United States University of Illinois United States Beckman Inst. Adv. Sci. and Technol. University of Illinois United States AT and T Labs. United States ATR Media Intgn. and Commun. Labs. Kyoto Japan National Taiwan University Taipei Taiwan Massachusetts Inst. of Technology Cambridge MA United States Department of Electrical Engineering MIT United States School of Electrical Engineering United States Lab. for Info. and Signal Processing Purdue University United States Coordinated Science Laboratory United States Dept. the Image Form. and Proc. Grp. Beckman Inst. Adv. Sci. and Technol. United States MIT Lincoln Laboratory IBM Thomas J. Watson Research Center Rheinishes Landes Museum Bonn Germany Swiss Institutes of Technology Zurich Switzerland Swiss Institutes of Technology Lausanne Switzerland University of Hannover Germany INRS-Telecommunications University of Quebec Montreal Que. Canada University of Tokyo Japan

Natural Human-computer Interface requires integration of realistic audio and visual information for perception and display. An example of such an interface is an animated talking head displayed on the computer screen in the form of a human-like computer agent. This system converts text to acoustic speech with synchronized animation of mouth movements. The talking head is based on a generic 3D human head model, but to improve realism, natural looking personalized models are necessary. In this paper, we report a semi-automatic method for adapting a generic head model to 3D range data of a human head obtained from a 3D-laser range scanner. This personalized model is incorporated into the talking head system. With texture mapping, the personalized model offers a more natural and realistic look than the generic model. The model created with the proposed method compares favorable to generic models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Content-based colour image filters

引用

ELECTRONICS LETTERS 1997年第3期33卷 202-203页

作者： Plataniotis, KN Androutsos, D Venetsanopoulos, AN Department of Electrical and Computer Engineering Digital Signal/Image Processing Laboratory University of Toronto Toronto Canada

A nonlinear ranked-order filter based on a content model of similarity is proposed for colour image processing. Simulation results indicate that the new filter suppresses impulsive as well as Gaussian noise and preser... 详细信息

关键词： image processing colour

来源：评论

学校读者我要写书评

暂无评论

Convergence rates for decentralized consistent location parameter estimation in the presence of Gaussian outliers

引用

signal processing 1997年第3期60卷 281-288页

作者： Delic, H Signal and Image Processing Laboratory Department of Electrical and Electronics Engineering Boǧaziçi University Bebek 80815 Istanbul Turkey

We consider a distributed system where sensors make location parameter estimates using their observations. A central processor collects the local estimates and declares a final estimate based on them. We present a simple study of the convergence properties of three structures where empirical mean and M-estimates are used in various combinations. It is shown that when occasional outliers exist, decentralized estimators that provide robustness at stages where data corruption occurs perform superiorly. (C) 1997 Elsevier Science B.V.

关键词： multiple sensor estimation Gaussian outlier M-estimate asymptotics

来源：评论

学校读者我要写书评

暂无评论

View generation for three-dimensional scenes from video sequences

引用

IEEE TRANSACTIONS ON image processing 1997年第4期6卷 584-598页

作者： Chang, NL Zakhor, A Video and Image Processing Laboratory Department of Electrical Engineering and Computer Sciences University of California Berkeley CA USA

This paper focuses on the representation and view generation of three-dimensional (3-D) scenes. In contrast to existing methods that construct a full 3-D model or those that exploit geometric invariants, our representation consists of dense depth maps at several preselected viewpoints from an image sequence, Furthermore, instead of using multiple calibrated stationary cameras or range scanners, we derive our depth maps from image sequences captured by an uncalibrated camera with only approximately known motion, We propose an adaptive matching algorithm that assigns various confidence levels to different regions in the depth maps, Nonuniform bicubic spline interpolation is then used to fill in low confidence regions in the depth maps. Once the depth maps are computed at preselected viewpoints, the intensity and depth at these locations are used to reconstruct arbitrary views of the 3-D scene, Specifically, the depth maps are regarded as vertices of a deformable 2-D mesh, which are transformed in 3-D, projected to 2-D, and rendered to generate the desired view. Experimental results are presented to verify our approach.

关键词： Layout Video sequences Cameras image sequences image reconstruction Geometry Solid modeling Spline Interpolation Mesh generation

来源：评论

学校读者我要写书评

暂无评论

1.5V resistive fuse for image smoothing and segmentation

引用

ELECTRONICS LETTERS 1997年第10期33卷 851-852页

作者： Athreya, JKV Gregson, PH Department of Electrical Engineering Computer Vision and Image Processing Laboratory Technical University of Nova Scotia Halifax Canada

A 1.5V resistive fuse for image smoothing and segmentation using bulk-driven MOSFETs is presented. The circuit switches on only if the differential voltage applied across its input terminals is less than a set voltage;it switches off if the differential voltage is higher than the set value. The useful operation range of the circuit is 0.4V with a supply voltage of 1.5V and threshold voltages of V-Tn = 0.828V and V-Tp = -0.56V for n and g channel MOSFETs, respectively.

关键词： image processing segmentation (image processing)

来源：评论

学校读者我要写书评

暂无评论

ML parameter estimation and minimum distance classifier for texture analysis using wavelet transform

引用

computerS & INDUSTRIAL engineering 1997年第1-2期33卷 449-452页

作者： Singh, R Singh, R Vasquez, R Laboratory for Applied Remote Sensing and Image Processing Department of Electrical and Computer Engineering University of Puerto Rico Mayaguez Campus PR 06681-5000 Puerto Rico

This work concentrates on comparing the performance of the minimum distance classifier and maximum-likelihood classifier for texture analysis. A tree-structured wavelet transform has been used for extracting the features and the comparison is based on the correct classification percentage. The results indicate that the maximum-likelihood classifier performs marginally better than the mahalanobis distance for some feature sets. The Euclidean distance did not prove to be powerful in distinguishing the textures. The performance of various orthogonal wavelet transforms have also been compared in order to find out the best wavelet for each of the classifiers considered. (C) 1997 Elsevier Science Ltd.

关键词： texture analysis ML parameter estimation minimum distance wavelet transform

来源：评论

学校读者我要写书评

暂无评论

Two-stage neural network for volume segmentation of medical images

Two-stage neural network for volume segmentation of medical ...

引用

1997 IEEE International Conference on Neural Networks (ICNN 97)

作者： Ahmed, MN Farag, AA Computer Vision and Image Processing Laboratory University of Louisville Department of Electrical Engineering Louisville KY 40292 United States

ISBN: (纸本)0780341236

In this paper, we present a new system to segment and label CT/MRI Brain slices using feature extraction and unsupervised clustering. In this technique, each voxel is assigned a feature pattern consisting of a scaled family of differential geometrical invariant features. The invariant feature pattern is then assigned to a specific region using a two-stage neural network system. The first stage is a self-organizing principal components analysis (SOPCA) network that is used to project the feature vector onto its leading principal axes found by using principal components analysis. This step provides an effective basis for feature extraction. The second stage consists of a self-organizing feature map (SOFM) which will automatically cluster the input vector into different regions. The optimum number of regions (clusters) is obtained by a model fitting approach. Finally, a 3D connected component labeling algorithm is applied to ensure region connectivity. Implementation and performance of this technique are presented. Compared to other approaches, the new system is more accurate in extracting 3D anatomical structures of the brain, and can be apdated to real-time imaging scenarios.

关键词： segmentation pattern analysis learning in vision

来源：评论

学校读者我要写书评

暂无评论

Temporal prediction of video sequences using an image warping technique based on color segmentation 9th

Temporal prediction of video sequences using an image warpin...

引用

9th International Conference on image Analysis and processing, ICIAP 1997

作者： Herodotou, N. Venetsanopoulos, A.N. Digital Signal and Image Processing Laboratory Department of Electrical and Computer Engineering University of Toronto 10 King's College Road TorontoONM5S 3G4 Canada

ISBN: (纸本)3540635076

An image warping technique based on segmented regions is introduced for the temporal prediction of videophone-type sequences. At the encoder, a set of control points are determined from the previous frame and their corresponding best matched points are determined from the current frame. The selection process of these points is achieved by segmenting the previous frame into different regions using a color segmentation technique based on a recursive histogramming approach and the control points are subsequently chosen along the region boundaries. The spatial offset of these points between the previous and current frame are represented as motion vectors. The facial area is intraframe encoded to avoid distortions of the facial features which convey critical information. At the decoder, the same segmentation and control point selection algorithm is used along with the motion vectors in order to find the region boundaries of the predicted frame. The facial area is decoded and an affine transformation is finally used to determine the remaining regions and form the predicted frame. This technique produces results that are free from blocking artifacts as in the conventional block matching method, with only a moderate increase in computational complexity. © Springer-Verlag Berlin Heidelberg 1997.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Autoregressive modeling of lung sounds using higher-order statistics: estimation of source and transmission

Autoregressive modeling of lung sounds using higher-order st...

引用

IEEE signal processing Workshop on Higher-Order Statistics

作者： L.J. Hadjileontiadis S.M. Panas Department of Electrical & Computer Engineering Division of Medical Signal and Image Processing Aristotle University of Thessaloniki Thessaloniki Greece

The use of higher-order statistics in an autoregressive modeling of lung sounds is presented resulting in a characterization of their source and transmission. The lung sound source in the airway is estimated using the prediction error of an all-pole filter based on higher-order statistics (AR-HOS), while the acoustic transmission through the lung parenchyma and chest wall is modeled by the transfer function of the same AR-HOS filter. The parametric bispectrum, using the estimated a/sub i/ coefficients of the AR-HOS model, is also calculated to elucidate the frequency characteristics of the modeled system. The implementation of this approach on pre-classified lung sound segments in known disease conditions, selected from teaching tapes, was examined. Experiments have shown that a reliable and consistent with current knowledge estimation of lung sound characteristics can be achieved using this method, even in the presence of additive Gaussian noise.

关键词： Lungs Higher order statistics Filters Frequency estimation Predictive models Transfer functions Diseases Education Additive noise Gaussian noise

来源：评论

学校读者我要写书评

暂无评论

A least-squares-based 2-D filtering for disparity estimation

A least-squares-based 2-D filtering for disparity estimation

引用

IEEE International Conference on image processing

作者： Sang-Woon Seo M.R. Azimi-Sadjadi Bin Tian Signal/Image Processing Laboratory Department of Electrical Engineering Colorado State University Fort Collins CO USA

A block-matching method is generally used for the disparity estimation as well as motion estimation applications. However, this method suffers from limitations such as blocking artifacts on the reconstructed images and a lack of compensation ability for the mismatching areas. A new disparity estimation scheme using 2-D filtering is proposed to provide more accurate estimates of the disparity vector and better compensation ability. This is accomplished by applying the left image to the reference input of the filter while using the right image as the desired output. The goal is to provide the best matching for the right image using the filter output instead of the left image directly as used in the block-matching method. A reduced order filtering scheme is also introduced to minimize the number of filter coefficients for the reconstruction. The reconstructed images generated based upon the estimated disparity vectors and some principal filter coefficients exhibited excellent quality.

关键词： Filtering Motion estimation image coding image sequences image reconstruction Matched filters Videoconference Stereo image processing image resolution signal processing

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：