检索结果-内蒙古大学图书馆

2nd International Conference on Video, Vision and Graphics, VVG 2005

作者： Atsalakis, A. Papamarkos, N. Image Processing and Multimedia Laboratory Department of Electrical and Computer Engineering Democritus University of Thrace 67100 Xanthi Greece

ISBN: (纸本)9783905673579

A new method for the reduction of the number of colors in a digital image is proposed. The new method is based on the developed of a new neural network classifier that combines the advantages of the Growing Neural Gas (GNG) and the Kohonen Self-Organized Feature Map (SOFM) neural networks. We call the new neural network: Self-Growing and Self-Organized Neural Gas (SGONG). Its main advantage is that it defines the number of the created neurons and their topology in an automatic way. As a consecutive, isolated color classes, which may correspond to significant image details, can be obtained. The SGONG is fed by the color components and additional spatial features. To speed up the entire algorithm and to reduce memory requirements, a fractal scanning sub-sampling technique is used. The method is applicable to any type of color images and it can accommodate any type of color space. © The Eurographics Association 2005.

关键词： Color

来源：评论

学校读者我要写书评

暂无评论

Using a free-parts representation for visual speech recognition

Using a free-parts representation for visual speech recognit...

引用

Digital Imaging Computing: Techniques and Applications, DICTA 2005

作者： Lucey, Patrick Lucey, Simon Sridharan, Sridha Speech Audio Image and Video Research Laboratory Queensland University of Technology GPO Box 2424 Brisbane 4001 Australia Advanced Multimedia Processing Laboratory Department of Electrical and Computer Engineering Carnegie Mellon University Pittsburgh PA 15213 United States

ISBN: (纸本)0769524672

Motivated by the success of free-parts based representations in face recognition, we have attempted to address some of the problems associated with applying such a philosophy to the task of speaker-independent visual speech recognition. A major problem with canonical area-based approaches in automatic visual speech recognition is the dependence these approaches have on locating and tracking the speaker's region of interest (ROI) correctly. By employing a free-parts representation, we assume that the position/structure of patches within the mouth image can be relaxed so they can "freely" move to varying extents, hence reducing the influence of the front-end effect. In this paper, we show that by using a free-parts representation we gain some robustness against the problem of ROI localisation and tracking compared to current area-based feature extraction techniques such as the discrete cosine transform (DCT). Also in this paper, we expose the importance of representation for the task of visual speech recognition highlighted by the poor results current representations yield. © 2005 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

IMPROVED SPEECH READING THROUGH A FREE-PARTS REPRESENTATION

IMPROVED SPEECH READING THROUGH A FREE-PARTS REPRESENTATION

引用

2005 International Conference on Auditory-Visual Speech processing, AVSP 2005

作者： Lucey, Simon Lucey, Patrick Advanced Multimedia Processing Laboratory Department of Electrical and Computer Engineering Carnegie Mellon University PittsburghPA15213 United States Speech Audio Image and Video Research Laboratory Queensland University of Technology GPO Box 2424 Brisbane4001 Australia

Motivated by the success of free-parts based representations in face recognition [1] we have attempted to address some of the problems associated with applying such a philosophy to the task of speaker-independent automatic speech reading. Hitherto, a major problem with canonical area-based approaches in automatic speech reading is the intrinsic lack of training observations due to the visual speech modality’s low sample rate and large variability in appearance. We believe a free-parts representation can overcome many of these limitations due to its natural ability to generalize by producing many observations from a single mouth image, whilst still preserving the ability to discriminate between various visual-speech units. This approach additionally requires a modification to traditional techniques employed for the estimation of hidden Markov Models (HMMs), whose resultant models we currently refer to as free-parts HMMs (FP-HMMs). Results will be presented on the CUAVE audiovisual speech database. © AVSP 2005. All rights reserved.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Optical flow-based tracking of deformable objects using a non-prior training active feature model 5th

Optical flow-based tracking of deformable objects using a no...

引用

5th Pacific Rim Conference on multimedia, PCM 2004

作者： Kim, Sangjin Kang, Jinyoung Shin, Jeongho Lee, Seongwon Paik, Joonki Kang, Sangkyu Abidi, Besma Abidi, Mongi Image Processing and Intelligent Systems Laboratory Department of Image Engineering Graduate School of Advanced Imaging Science Multimedia and Film Chung-Ang University 221 Huksuk-Dong Tongjak-Ku Seoul156-756 Korea Republic of Imaging Robotics and Intelligent Systems Laboratory Department of Electrical and Computer Engineering The University of Tennessee KnoxvilleTN37996-2100 United States

ISBN: (纸本)9783540239857

This paper presents a feature point tracking algorithm using optical flow under the non-prior training active feature model (NPT-AFM) framework. The proposed algorithm mainly focuses on analysis of deformable objects, and provides real-time, robust tracking. The proposed object tracking procedure can be divided into two steps: (i) optical flow-based tracking of feature points and (ii) NPT-AFM for robust tracking. In order to handle occlusion problems in object tracking, feature points inside an object are estimated instead of its shape boundary of the conventional active contour model (ACM) or active shape model (ASM), and are updated as an element of the training set for the AFM. The proposed NPT-AFM framework enables the tracking of occluded objects in complicated background. Experimental results show that the proposed NPT-AFM-based algorithm can track deformable objects in real-time. © Springer-Verlag Berlin Heidelberg 2004.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Clustering by principal curve with tree structure

Clustering by principal curve with tree structure

引用

International Symposium on Signals, Circuits and Systems (ISSCS)

作者： I. Cleju P. Franti Xiaolin Wu Multimedia Signal Processing Group Department of Computer and Information Science University of Karlsruhe Konstanz Germany Speech and Image Processing Research Group Department of Computer Science University of Joensuu Joensuu Finland Multimedia Computing and Comucations Laboratory Department of Etectrical and Computer Engineering McMaster University Hamilton ONT Canada

Data clustering is intensively used in signal processing in tasks such as multimedia compression, segmentation and pattern matching. In this work we extend the use of principal curves in clustering to complex multidimensional datasets. The use of principal curve in clustering is limited for high complexity data. Automatic parameterization of the principal curve to assure good results for different datasets is a difficult task. We propose to use the tree structure to capture the general settlement of the data. Using this topology, regions of the dataset can be extracted, individually clustered using the principal curve and then optimally recombined. The experiments show the improvement of the new method over the principal curve based clustering and the good performance compared to other clustering methods.

关键词： Tree data structures Clustering algorithms Partitioning algorithms multimedia computing Quantization computer science Pattern matching Data mining Application software Information science

来源：评论

学校读者我要写书评

暂无评论

Using a Free-Parts Representation for Visual Speech Recognition

Using a Free-Parts Representation for Visual Speech Recognit...

引用

Proceedings of the Digital image Computing: Technqiues and Applications (DICTA)

作者： P. Lucey S. Lucey S. Sridharan Queensland University of Technology Speech Audio Image and Video Research Laboratory Brisbane Australia Advanced Multimedia Processing Laboratory Department of Electrical and Computer Engineering Carnegie Mellon University Pittsburgh PA USA

Motivated by the success of free-parts based representations in face recognition, we have attempted to address some of the problems associated with applying such a philosophy to the task of speaker-independent visual speech recognition. A major problem with canonical area-based approaches in automatic visual speech recognition is the dependence these approaches have on locating and tracking the speaker’s region of interest (ROI) correctly. By employing a free-parts representation,we assume that the position/structure of patches within the mouth image can be relaxed so they can "freely" move to varying extents, hence reducing the influence of the front-end effect. In this paper, we show that by using a free-parts representation we gain some robustness against the problem of ROI localisation and tracking compared to current area-based feature extraction techniques such as the discrete cosine transform (DCT). Also in this paper, we expose the importance of representation for the task of visual speech recognition highlighted by the poor results current representations yield.

关键词： Speech recognition Mouth Hidden Markov models Laboratories Face recognition Feature extraction Discrete cosine transforms Robustness Automatic speech recognition Pixel

来源：评论

学校读者我要写书评

暂无评论

Automatic face region tracking for highly accurate face recognition in unconstrained environments

Automatic face region tracking for highly accurate face reco...

引用

IEEE Conference on Advanced Video and Signal Based Surveillance (AVSS)

作者： Y.-O. Kim J. Paik Jingu Heo A. Koschan B. Abidi M. Abidi Korea Electronics and Technology Institute Puchon Gyeonggi South Korea Image Processing Laboratory Department of Image Engineering Graduate School of Advanced Imaging Science Multimedia and Film Chung-Ang University Seoul South Korea Imaging Robotics and Intelligent Systems Laboratory Department of Electrical and Computer Engineering University of Tennessee Knoxville USA

We present a combined real-time face region tracking and highly accurate face recognition technique for an intelligent surveillance system. High-resolution face images are very important to achieving accurate identification of a human face. Conventional surveillance or security systems, however, usually provide poor image quality because they use only fixed cameras to record scenes passively. We have implemented a real-time surveillance system that tracks a moving face using four pan-tilt-zoom (PTZ) cameras. While tracking, the region-of-interest (ROI) can be obtained by using a low-pass filter and background subtraction with the PTZ. Color information in the ROI is updated to extract features for optimal tracking and zooming. FaceIt/sup /spl reg//, which is one of the most popular face recognition software packages, is evaluated and then used to recognize the faces from the video signal. Experimentation with real human faces showed highly acceptable results in the sense of both accuracy and computational efficiency.

关键词： Face recognition Surveillance Real time systems Humans Cameras Intelligent systems Security image quality Layout Low pass filters

来源：评论

学校读者我要写书评

暂无评论

A Region-Based Representation of images in MARS

引用

Journal of VLSI Signal processing Systems for Signal, image, and Video Technology 1998年第1-2期20卷 137-150页

作者： Servetto, Sergio D. Rui, Yong Ramchandran, Kannan Huang, Thomas S. Beckman Inst. Adv. Sci. and Technol. Univ. Illinois at Urbana-Champaign Urbana IL 61801 United States Universidad Nacional de La Plata Argentina Univ. Illinois at Urbana-Champaign United States Comp. Res. Adv. Applications Group IBM Argentina Argentina Image Formation and Processing Group Beckman Institute UIUC United States Department of Computer Science UNLP Argentina Dept. of Elec. and Comp. Engineering UIUC United States Multimedia Commun. Res. Department Bell Laboratories Murray Hill NJ United States Info. Sciences Research Department AT and T Labs. Florham Park NJ United States Department of Computer Science UIUC United States Southeast University China Tsinghua University China University of Illinois Urbana-Champaign IL United States Image Formation and Processing Group Beckman Inst. Advance Sci. Technol. UIUC United States Vis. Technol. Grp. of Microsoft Res. Redmond WA United States City College of New York United States Columbia University United States AT and T Bell Labs. United States Ctr. for Telecommunications Research Columbia University United States Elec. and Comp. Eng. Department United States Beckman Institute Coordinated Science Laboratory IL United States IEEE Signal Processing Society United States IEEE IMDSP Technical Committee United States IEEE Transactions on Image Proc. United States 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 Dept. of Elec. and Comp. Engineering United States Coordinated Science Laboratory United States Image Formation and Processing Group 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 S

We study the problem of representing images within a multimedia Database Management System (DBMS), in order to support fast retrieval operations without compromising storage efficiency. To achieve this goal, we propose new image coding techniques which combine a wavelet representation, embedded coding of the wavelet coefficients, and segmentation of image-domain regions in the wavelet domain. A bitstream is generated in which each image region is encoded independently of other regions, without having to explicitly store information describing the regions. Simulation results show that our proposed algorithms achieve coding performance which compares favorably, both perceptually and objectively, to that achieved using state-of-the-art image/video coding techniques while additionally providing region-based support.

关键词：

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：