检索结果-内蒙古大学图书馆

6th International Conference on Document Analysis and recognition, ICDAR 2001

作者： Koerich, Alessandro L. Sabourin, Robert Suen, Ching Y. Lab. d'Imagerie de Vision et d'Intelligence Artificielle École de Technologie Supérieure MontréalH3C 1K3 Canada Centre for Pattern Recognition and Machine Intelligence Concordia University MontréalH3G 1M8 Canada

ISBN: (纸本)0769512631

Many off-line handwritten word recognition systems have been proposed since the early nineties. Most systems reported high recognition rates, however, they overlooked a very important factor in the process;speed factor. In this paper we explore the potential for speeding up an off-line handwritten word recognition system via concurrency. The goal of the system is to achieve both full accuracy and high speed when taking into account large vocabularies. This has been accomplished by integrating the recognition process with multiprocessing and distributed computing concepts. Experimental results showed that the multiprocessing environment is very promising in enhancing a sequential off - line handwritten word recognition system performance. © 2001 IEEE.

关键词： Distributed computer systems

来源：评论

学校读者我要写书评

暂无评论

THE HIDDEN MARKOV MODEL OF CO-ARTICULATION AND ITS APPLICATION TO THE CONTINUOUS SPEECH recognition

引用

Journal of Electronics(China) 2000年第3期17卷 242-247页

作者： Lee Tranzai Zheng Fang Wu Wenhu Chen Daowen(Speech lab., Dept. of computer Sciences and Technology, Tsinghua University, Beijing 100084) (National lab. of pattern recognition, Inst. of Automation, Chinese Academy of Sci., Beijing 100080) Speech Lab. Dept. of Computer Sciences and Technology Tsinghua University Beijing National Lab. of Pattern Recognition Inst. of Automation Chinese Academy of Sci. Beijing

The co-articulation is one of the main reasons that makes the speech recognition difficult. However, the traditional Hidden Markov Models(HMM) can not model the co-articulation, because they depend on the first-order assumption. In this paper, for modeling the co-articulation, a more perfect HMM than traditional first order HMM is proposed on the basis of the authors’ previous works(1997, 1998) and they give a method in that this HMM is used in continuous speech recognition by means of multilayer perceptrons(MLP), i.e. the hybrid HMM/MLP method with triple MLP structure. The experimental result shows that this new hybrid HMM/MLP method decreases error rate in comparison with authors’ previous works.

关键词： Speech recognition High-order HMM Hybrid HMM/MLP

来源：评论

学校读者我要写书评

暂无评论

Application of a genetic algorithm in triangulation of a 3-D object surface

引用

International Journal of computers and Applications 2000年第2期22卷 73-77页

作者： Zhenyu, Chen Mbede, J.B. Yan, Zhou Dehua, Li Hanping, Hu State Commn. Res. Open Lab. Image P. Inst. Pattern Recog. Artif. Intell. Huazhong Univ. of Sci. and Technol. 430074 Wuhan China Intelligent Contr. and Robotics Lab. Dept. of Contr. Sci. and Engineering Huazhong Univ. of Sci. and Technol. 430074 Wuhan China Second Artillery Institute Huazhong Univ. of Sci. and Technol. Inst. Pattern Recog. Artif. Intell. Huazhong Univ. of Sci. and Technol. Second Artillery Institute China Wuhan University China Artificial Intelligence Department University of Edinburgh Inst. of AI and Pattern Recognition Huazhong Univ. of Sci. and Technol. China Cogn. Sci. Natl. Key Found. Res. P. Douala University Cameroon Tübingen University Germany Automatic Control Laboratory Darmstadt University Department of Service Cameroon Min. of National Education Robotics Laboratory Huazhong Univ. of Sci. and Technol. Wuhan China Assoc. Connectionnistes These-ACTH Rennes France IEEE Soc. of Robotics and Automation IEEE Society of Control Systems IASTED Assoc. Jeunes Chercheurs Robotique France Navy University of Engineering China Huazhong Univ. of Sci. and Technol. China Department of Computer Science Airforce Radar Acad. of Engineering China Inst. of P.R and AI Huazhong Univ. of Sci. and Technol.

This paper proposes a genetic-based algorithm for surface reconstruction of three-dimension (3-D) objects from a group of contours representing its section plane lines. The algorithm can optimize the triangulation of the surface of 3-D objects with a multi-objective optimization function to meet the needs of a wide range of applications. Further, a new crossover operator for triangulation and a new 3-D quadrilateral mutation operator are also introduced.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Towards a description for video indexation

Towards a description for video indexation

引用

International Conference on pattern recognition

作者： F. Lebourgeois J.-M. Jolion P.Ch. Awart Pattern Recognition & Vision Lab. Inst. Nat. des Sci. Appliquees Villeurbanne France

This paper presents the overall scheme of an indexation system for broadcast video designed for very large databases. We discuss features which can possibly be extracted from a video sequence so as to be used for "queries by example". We present examples of semantic features (query by content) like text reading, face localisation and classification. As this study is still at its infancy, we point out the key features and temporary achievements and present some temporary results.

关键词： Video sequences lab.ratories Multimedia communication Broadcasting Indexing Image storage Image color analysis pattern recognition Design automation Tellurium

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

On integration of vision modules

On integration of vision modules

引用

IEEE computer Society Conference on computer vision and pattern recognition Workshops (CVPRW)

作者： Pankanti Jain Tuceryan Pattern Recognition and Image Proc. Lab. Michigan State University East Lansing MI USA European Computer-Industry Research Centre Munchen Germany

Individual cues from visual modules are fallible and often ambiguous. As a result, only integrated vision systems can be expected to give a reliable performance in practice. The design of such systems is challenging since each vision module works under different and possibly conflicting sets of assumptions. We have proposed and implemented a multiresolution system which integrates perceptual grouping, segmentation, stereo, shape from shading, and line lab.lling modules. The output of the integrated system is shown to be relatively insensitive to the constraints imposed by the individual modules.< >

关键词： Machine vision Image segmentation Stereo vision

来源：评论

学校读者我要写书评

暂无评论

Texture analysis in the presence of speckle noise 12

Texture analysis in the presence of speckle noise

引用

12th Annual International Geoscience and Remote Sensing Symposium, IGARSS 1992

作者： Schistad, Anne H. Jain, Anil K. Norwegian Computing Center P.O. Box 114 Blindern Oslo 3N-0314 Norway Pattern Recognition and Image Processing Lab. Computer Science Department Michigan State University East LansingMI48824 United States

ISBN: (纸本)0780301382

We investigate the performance of selected texture models for the purpose of land use classification. The texture models are evaluated based on the resulting classification error rates. Three classes of texture models are evaluated: fractal models, lognormal random fields and grey level co-occurrence matrices. The effect of filtering and noise transformation is investigated. The lognormal random field model gives the best performance. © IEEE 1992.

关键词： Land use

来源：评论

学校读者我要写书评

暂无评论

Occlusion Boundary Prediction and Transformer Based Depth-Map Refinement From Single Image

引用

ACM Transactions on Multimedia Computing, Communications, and Applications 1000年

作者： Praful Hambarde Gourav Wadhwa Santosh Kumar Vipparthi Subrahmanyam Murala Abhinav Dhall Computer Vision and Pattern Recognition Lab Indian Institute of Technology Ropar India ByteDance Singapore School of Computer Science and Statistics Trinity College Dublin Ireland Flinders University Adelaide Australia

Due to the numerous applications of boundary maps and occlusion orientation maps (ORI-maps) in high-level vision problems, accurate estimation of these maps is a crucial task. The existing deep networks employ a single-stream network to estimate the relation between boundary map and ORI-map estimation. However, these networks fail to explore significant individual information separately. To resolve this problem, in this paper, we propose a novel two-stream generative adversarial network (GAN) for boundary map and ORI-map estimation, named OBP-GAN. The proposed OBP-GAN consists of two streams known as BP-GAN and OR-GAN. The BP-GAN estimates the boundary map, and the OR-GAN predicts the ORI-map. The boundary and ORI-map can also be useful cues for the task of depth-map refinement from single images. Therefore, in this work, we propose a transformer-based depth-map refinement network (TRANSDMR-GAN) for refining the depth estimated from monocular images using boundary and ORI-map. We conducted extensive analyses on indoor and outdoor datasets to validate our proposed OBP-GAN and TRANSDMR-GAN. The extensive experimental analysis and ablation study demonstrate the ability of the proposed OBP-GAN to generate state-of-the-art occlusion boundary maps. Furthermore, we show that the proposed network, TRANSDMR-GAN, can generate an edge-enhanced depth map without degrading the accuracy of the initial depth map.

关键词： Depth-map Refinement Occlusion Boundary Map Occlusion Orientation Map Self-attention and Generative Adversarial Networks

来源：评论

学校读者我要写书评

暂无评论

Multimedia Content Representation, Classification and Security 1

引用

丛书名： Lecture Notes in computer Science

1000年

作者： Bilge Gunsel Anil K. Jain A. Murat Tekalp Bülent Sankur

ISBN: (数字)9783540393931

ISBN: (纸本)9783540393924

We would like to welcome you to the proceedings of MRCS 2006, Workshop on Multimedia Content Representation, Classi?cation and Security, held Sept- ber 11–13, 2006, in Istanbul, Turkey. The goal of MRCS 2006 was to provide an erudite but friendly forum where academic and industrial researchers could interact, discuss emerging multimedia techniques and assess the signi?cance of content representation and security techniques within their problem domains. We received more than 190 submissions from 30 countries. All papers were subjected to thorough peer review. The ?nal decisions were based on the cri- cisms and recommendations of the reviewers and the relevance of papers to the goals of the conference. Only 52% of the papers submitted were accepted for inclusion in the program. In addition to the contributed papers, four distinguished researchers agreed to deliver keynote speeches, namely: – Ed Delp on multimedia security – Pierre Moulin on data hiding – John Smith on multimedia content-based indexing and search – Mar´ ?o A. T. Figueiredo on semi-supervised learning.

关键词： computer Applications Multimedia Information Systems Information Storage and Retrieval computer Communication Networks Information Systems Applications (incl. Internet) Image Processing and computer vision

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：