检索结果-内蒙古大学图书馆

Detection and classification of road signs for automatic inventory systems using computer vision

INTEGRATED computer-AIDED ENGINEERING 2012年第3期19卷 285-298页

作者： Pelaez Coronado, Gustavo A. Romero Munoz, Maria Maria Armingol, Jose de la Escalera, Arturo Jesus Munoz, Juan van Bijsterveld, Wouter Antonio Bolano, Juan Univ Carlos III Madrid Syst Engn & Automat Dept Intelligent Syst Lab Leganes Spain Geotecnia & Cimientos SA Coslada Madrid Spain

This article describes an intelligent system that enables the automatic recognition of road signs from image sequences in road environments. The main difficulties the system has to deal with are related to changes in lighting conditions, obstacles blocking the view, the presence of objects with geometric and chromatic similarities and the absence of previous knowledge about their position and orientation. The application of different techniques allows the system to overcome this variety of problems. Therefore, the road sign recognition system is based on a first pre-processing of images, making use of information about road geometry to isolate those areas of the image where road signs may appear. The detection step uses colour and shape analysis to determine the regions of the image where potential road signs may be located. A third step focuses on recognition and classification using pattern matching and edge feature analysis. The proposed algorithm has been tested in different weather and lighting conditions and roads (one and two-lane roads and motorways), overall, a total of 1200 kilometres with a very high success rate of detection and classification as the experimental results show.

关键词： Road sign recognition road sign inventory searching space reduction colour segmentation pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Face recognition under variable illumination by weighted-subband edge enhancement

Face recognition under variable illumination by weighted-sub...

引用

2012 5th Chinese Conference on pattern recognition, CCPR 2012

作者： Lai, Zhao-Rong Dai, Dao-Qing Ren, Chuan-Xian Center for Computer Vision Department of Mathematics Sun Yat-Sen University Xin Gang Xi Road No.135 Guangzhou China

ISBN: (纸本)9783642335051

This article presents a novel weighted-subband method based on wavelet decomposition for face recognition under variable illumination. Different levels of subbands contain different features of the edge of a human face image. Through assigning a weight to each subband, we can strengthen the features beneficial to recognition, and weaken the features detrimental to recognition. To make the edge of human face stand out, a new histogram equalization and border smoothing method is implemented before weighted-subband edge enhancement. Experiments on the Extended YaleB Database show promising performance. © 2012 Springer-Verlag.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Face recognition Using Nonlinear Partial Least Squares in Reproducing Kernel Hilbert Space

Face Recognition Using Nonlinear Partial Least Squares in Re...

引用

Chinese Conference on pattern recognition

作者： Hu, Ye-Gang Ren, Chuan-Xian Yao, Yun-Fei Li, Wan-Yi Feng-Wang Fuyang Normal Coll Dept Math Fuyang 236037 Peoples R China Sun Yat Sen Univ Ctr Comp Vision Dept Math Guangzhou 510275 Guangdong Peoples R China Chinese Acad Sci Inst Automat Beijing 100190 Peoples R China Fuyang Normal Coll Dept Comp & Informat Fuyang 236037 Peoples R China

ISBN: (纸本)9783642335051

Dimensionality reduction is an important step for face recognition. A novel feature extraction method using nonlinear partial least squares discrimination (NPLSD) for facial images is proposed in this paper. The method is constituted by two consecutive steps, in which the original facial features are projected onto the reproducing kernel Hilbert space to solve the linear inseparable problem, then the iterative and supervised partial least squares method is used for calculating subsequent discriminant components, wherein an approach for modeling a relationship between a set of input variables and response variables, while maintaining most of the variance in the input variables, and then extract the discrimination features from different classes, until convergence of latent vectors by more iterations. This will result in a dramatic reduction for the computational time since the calculation for the covariance matrix is not required. The experiment results using the ORL data demonstrates the effectiveness of the proposed method.

关键词： Face recognition nonlinear mapping kernel learning partial least squares iterative process

来源：评论

学校读者我要写书评

暂无评论

A systematic gradient-based method for the computation of fingerprint's orientation field

引用

computerS & ELECTRICAL ENGINEERING 2012年第5期38卷 1035-1046页

作者： Mei, Yuan Cao, Guo Sun, Huaijiang Hou, Rongtao Nanjing Univ Informat Sci & Technol Jiangsu Engn Ctr Network Monitoring Nanjing 210044 Jiangsu Peoples R China Nanjing Univ Informat Sci & Technol Sch Comp & Software Nanjing 210044 Jiangsu Peoples R China Nanjing Univ Aeronaut & Astronaut Dept Comp Sci & Engn Nanjing 210016 Jiangsu Peoples R China Nanjing Univ Sci & Technol Sch Comp Sci & Technol Nanjing 210094 Jiangsu Peoples R China

Orientation field which describes the local direction of ridge-valley pattern, play a very important role in automatic fingerprint recognition. In this paper, a systematic gradient-based method for the computation of fingerprint's orientation field is proposed. This method mainly includes two procedures: the coarse level orientation computing, and the orientation predicting. In the first procedure, the effective point gradient vector and the composite block are proposed for overcoming the limitation caused by normalization, and the contradiction between accuracy and robustness respectively;in the second procedure, an iteration based predicting method is adopted for improving the robustness against noise. All experiments show that: compared with the previously proposed gradient-based approaches, our method does not only possess the advantage of high accuracy, but also be more robust against noise and be capable of predicting. (c) 2011 Elsevier Ltd. All rights reserved.

关键词： FINGERPRINTS computer vision pattern recognition systems PREDICTION theory VECTOR analysis ACCURACY ROBUST control AUTOMATION

来源：评论

学校读者我要写书评

暂无评论

A fast machine vision for automated packaging

A fast machine vision for automated packaging

引用

2011 International Conference on Electrical, Information Engineering and Mechatronics, EIEM 2011

作者： Liu, Yang Vo, Thanh Vinh Department of Information Technology Vaasa University of Applied Sciences Vaasa Finland School of Electrical and Electronic Engineering Hubei University of Technology Wuhan China

ISBN: (纸本)9781447124665

This paper introduces a fast, simple, cheap but accurate and reliable vision system designed for the automated packaging robot application, which is to replace manual product packaging. The objective is to develop a vision system and algorithm for such application and achieve pattern tracking in nearly real-time with a normal entry-level computer. This paper describes in detail the implementation of the proposed vision system including image processing and pattern recognition. The application uses only a simple gray scale image of product as sample pattern to track the product in the scene at real-time speed, which has come near to replace human eyes. The proposed machine vision has been implemented and equipped on a real ABB robot arm with other related hardware/software to achieve automated packaging. The performance has been evaluated as a success in both timing and precision. Its stability and reliability are also proved under laboratory testing environment. © 2012 Springer-Verlag London Limited.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

Image warping for face recognition: From local optimality towards global optimization

Image warping for face recognition: From local optimality to...

引用

作者： Pishchulin, Leonid Gass, Tobias Dreuw, Philippe Ney, Hermann MPI for Informatics - Computer Vision and Multimodal Computing Group Campus E1 4 D-66123 Saarbrücken Germany ETH Zurich Computer Vision Lab. Sternwartstrasse 7 CH-8092 Zurich Switzerland RWTH Aachen - Department 6 Ahornstr. 55 D-52056 Aachen Germany

This paper systematically analyzes the strengths and weaknesses of existing image warping algorithms on the tasks of face recognition. Image warping is used to cope with local and global image variability and in general is an NP-complete problem. Although many approximations have recently been proposed, neither thorough comparison, nor systematic analysis of methods in a common scheme has been done so far. We follow the bottom-up approach and analyze the methods with increasing degree of image structure preserved during optimization. We evaluate the presented warping approaches on four challenging face recognition tasks in highly variable domains. Our findings indicate that preserving maximum dependencies between neighboring pixels by imposing strong geometrical constraints leads to the best recognition results while making optimization efficient. © 2011 Elsevier Ltd. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Good match exploration using triangle constraint

Good match exploration using triangle constraint

引用

作者： Guo, Xiaojie Cao, Xiaochun School of Computer Science and Technology Tianjin University Tianjin 300072 China

This paper presents a novel method for addressing the problem of finding more good feature pairs between images, which is one of the most fundamental tasks in computer vision and pattern recognition. We first select matched features by Bi-matching as seed points, then organize these seed points by adopting the Delaunay triangulation algorithm. Finally, triangle constraint is used to explore good matches. The experimental evaluation shows that our method is robust to most geometric and photometric transformations including rotation, scale change, blur, viewpoint change, JPEG compression and illumination change, and significantly improves both the number of correct matches and the matching score. And the application on estimating the fundamental matrix for a pair of images is also shown. Both the experiments and the application demonstrate the robust performance of our method. © 2011 Elsevier B.V. All rights reserved.

关键词： pattern recognition

来源：评论

学校读者我要写书评

暂无评论

A Detection Method of Traffic Parameters Based on EPI

A Detection Method of Traffic Parameters Based on EPI

引用

International Workshop on Information and Electronics Engineering (IWIEE) / International Conference on Information, Computing and Telecommunications (ICICT)

作者： Deng, T. M. Li, B. Chongqing Jiaotong Univ Sch Traff & Transportat Chongqing Peoples R China

It is a key segment of the traffic management system about detecting traffic parameters. With the continuous development of computer vision, the video traffic detection method is paid more and more attention. For comprehensive utilization of the technology of image processing, computer vision and pattern recognition, video detection technology has many advantages, compared with traditional geography induction coils, ultrasonic and laser detector etc, such as simple installation, convenient maintenance, not to harm the roadbed, low cost, high accuracy, wide monitoring area. It is constructed that an Epi-polar Plane Image(EPI) method reflect the surface and movement characteristics of the vehicle, then the EPI is processing of normalization, filtering and texture detection. Finally, based on the EPI, it is given about the detection methods of mean velocity and length of the vehicle, traffic flow. (C) 2011 Published by Elsevier Ltd.

关键词： EPI computer vision Traffic Parameter Border Detection

来源：评论

学校读者我要写书评

暂无评论

Character extraction in web image for text recognition

Character extraction in web image for text recognition

引用

21st International Conference on pattern recognition, ICPR 2012

作者： Su, Bolan Lu, Shijian Phan, Trung Quy Tan, Chew Lim Department of Computer Science School of Computing National University of Singapore 13 Computing Drive Singapore 117417 Singapore Department of Computer Vision and Image Understanding Institute for Infocomm Research 1 Fusionopolis Way Singapore 138632 Singapore

ISBN: (纸本)9784990644109

Images with text are frequently used on Internet for different purposes. Automatic recognition of text from web images plays an important role on extraction and retrieval of web information. However, the web images are usually in low resolution with artifacts and special effects, which makes word recognition a challenge task even after the text has been localized. In this paper, we propose a robust text recognition technique to efficiently convert the web images into text format. The proposed technique first makes use of the L0 norm smoothing to increase the edge contrast of the input web images. The images are then binarized on each color channel. A connected component analysis is followed to identify the possible character components. Finally the character candidates are recognized by the OCR engine after skew correction. Extensive experiments have been conducted on the latest ICDAR 2011 robust reading competition dataset for born-digital text. The experimental results show the superior performance of our proposed technique. © 2012 ICPR Org Committee.

关键词： Special effects

来源：评论

学校读者我要写书评

暂无评论

Extrinsic analysis on manifolds is computationally faster than intrinsic analysis with applications to quality control by machine vision

引用

APPLIED STOCHASTIC MODELS IN BUSINESS AND INDUSTRY 2012年第3期28卷 222-235页

作者： Bhattacharya, R. N. Ellingson, L. Liu, X. Patrangenaru, V. Crane, M. Florida State Univ Tallahassee FL 32306 USA Univ Arizona Tucson AZ USA US EPA Off Res & Dev Cincinnati OH 45268 USA

In our technological era, non-Euclidean data abound, especially because of advances in digital imaging. Patrangenaru (Asymptotic statistics on manifolds, PhD Dissertation, 1998) introduced extrinsic and intrinsic means on manifolds, as location parameters for non-Euclidean data. A large sample nonparametric theory of inference on manifolds was developed by Bhattacharya and Patrangenaru (J. Stat. Plann. Inferr., 108, 2335, 2002;Ann. Statist., 31, 129, 2003;Ann. Statist., 33, 12111245, 2005). A flurry of papers in computer vision, statistical learning, pattern recognition, medical imaging, and other computational intensive applied areas using these concepts followed. While pursuing such location parameters in various instances of data analysis on manifolds, scientists are using intrinsic means, almost without exception. In this paper, we point out that there is no unique intrinsic analysis because the latter depends on the choice of the Riemannian metric on the manifold, and in dimension two or higher, there are infinitely such nonisometric choices. Also, using John Nash's celebrated isometric embedding theorem and an equivariant version, we show that for each intrinsic analysis there is an extrinsic counterpart that is computationally faster and give some concrete examples in shape and image analysis. The computational speed is important, especially in automated industrial processes. In this paper, we mention two potential applications in the industry and give a detailed presentation of one such application, for quality control in a manufacturing process via 3D projective shape analysis from multiple digital camera images. Copyright (C) 2011 John Wiley & Sons, Ltd.

关键词： extrinsic and intrinsic analysis directional data analysis shape analysis of planar closed curves Kendall's shape spaces statistical size-and-shape analysis 3D-projective shape analysis nonparametric inference quality control machine 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：