检索结果-内蒙古大学图书馆

IAPR International Workshop on Document Analysis systems, DAS

作者： Cunzhao Shi Baihua Xiao Chunheng Wang Yang Zhang State Key Laboratory of Intelligent Control and Management of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

Interactive image segmentation which needs the user to give certain hard constraints has shown promising performance for object segmentation. In this paper, we consider characters in text image as a special kind of object, and propose an adaptive graph cut based text binarization method to segment text from background. The main contributions of the paper lie in: 1) in order to make the binarization local adaptive with uneven background, the text region image is firstly roughly split into several sub-images on which graph cut is applied, and 2) considering the unique characteristics of the text, we propose to automatically classify some pixels as text or background with high confidence, severed as hard constraints seeds for graph cut to extract text from background by spreading the seeds into the whole sub-image. The experimental results show that our approach could get better performance in both character extraction accuracy and recognition accuracy.

关键词： Image segmentation Image color analysis Image edge detection Character recognition Optical character recognition software Noise

来源：评论

学校读者我要写书评

暂无评论

Sparse Representation based on Matrix Rank Minimization and K-Means Clustering for Recognition

Sparse Representation based on Matrix Rank Minimization and ...

引用

International Joint Conference on Neural Networks

作者： Long Ma Chunheng Wang Baihua Xiao State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China 100190

ISBN: (纸本)9781467314886

In this paper, we propose a sparse coding algorithm based on matrix rank minimization and k-means clustering and for recognition. We consider the problem of removing the noise in the training samples and generating more samples at the same time. To accomplish this, we extended the matrix rank minimization problem to cope with complex data. Samples from the same class are segmented into several groups by k-means clustering algorithm, and matrix rank minimization is applied on the clustered data to separate the noises and recover the low-rank structures in the grouped data. An over-complete dictionary is constructed by connecting the low-rank structures and the training samples together to keep the samples diversity. Sparse representation is operated based on this over-complete dictionary for recognition. Furthermore, a parameter is introduced to adjust the weighting of the coefficients that code the noises. We apply the proposed algorithm for character and face recognition. Experiments with improved performances validate the effectiveness of the proposed algorithm.

关键词： sparse representation Noise Recognition (Psychology) Rank of data matrices Sparse coding Dictionaries as Topic

来源：评论

学校读者我要写书评

暂无评论

Graph-Based Background Suppression for Scene Text Detection

Graph-Based Background Suppression for Scene Text Detection

引用

IAPR International Workshop on Document Analysis systems, DAS

Detecting text in video or natural scene image is quite challenging due to the complex background, various fonts and illumination conditions. The preprocessing period, which suppresses the nontext areas so as to highlight the text areas, is the basis for further text detection. In this paper, a novel graph-based background suppression method for scene text detection is proposed. Considering each pixel as a node in the graph, our approach incorporates pixel-level and context-level features into a graph. Various factors contribute to the unary and pair wise cost function which is optimized via max-flow/min-cut algorithm [16] to get a binary image whose nontext pixels are suppressed so that text pixels are highlighted. Furthermore, the proposed background suppression method could be easily combined with other detection methods to improve the performance. Experimental results on ICDAR 2011 competition dataset show promising performance.

关键词： Image edge detection Cost function Image color analysis Text categorization Feature extraction Computer vision

来源：评论

学校读者我要写书评

暂无评论

Artificial power system based on ACP approach

Artificial power system based on ACP approach

引用

2012 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2012

作者： Dong, Xisong Xiong, Gang Hou, Jiachen Fan, Dong State Key Laboratory of Management and Control for Complex Systems Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Beijing China Dongguan Research Institute of CASIA Cloud Computing Center Chinese Academy of Sciences Songshan Lake Dongguan China

ISBN: (纸本)9781467324007

Modern power system is a typical multi-level complex giant system consisting of physical infrastructures, human operators, and social resources, etc. The conventional analytical methods and simulation systems can't provide sufficient guidance for its operation and management, because they are mainly based on physical models, natural phenomenon, or other existing control methods which are based on reductionism. ACP approach, mainly consisting of artificial systems (A), computational experiments (C) and parallel execution (P), which is based on holism and complex system theory, has its specific advantages in the research on power systems. In this article, ACP approach is applied to build up artificial power system (APS) by using multi-agent complex networks. With the help of APS, actual power system's control, scheduling, optimization and management can be improved further via providing theoretical guidance and technical support for the rolling optimizations in normal situations and emergency management in abnormal situations. As a case study, an APS constructed with actual data from North China power grid is constructed and its vulnerability is simulated and analyzed under random, dynamic and static attacks. © 2012 IEEE.

关键词： complex networks

来源：评论

学校读者我要写书评

暂无评论

Training Strategies for a Lower Limb Rehabilitation Robot Based on Impedance control

Training Strategies for a Lower Limb Rehabilitation Robot Ba...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society

作者： Jin Hu Zengguang Hou Feng Zhang Yixiong Chen Pengfeng Li State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China

ISBN: (纸本)9781424441198

This paper proposes three training strategies based on impedance control, including passive training, damping-active training and spring-active training, for a 3- DOF lower limb rehabilitation robot designed for patients with paraplegia or hemiplegia. controllers with similar structure are developed for these training strategies, consisting of dual closed loops, the outer impedance control loop and the inner position/ velocity control loop, known as position-based impedance control method. Simulation results verify that position-based impedance control approach is feasible to accomplish the training strategies.

关键词： Training Strategies Lower Limb Rehabilitation Robot Based Impedance control

来源：评论

学校读者我要写书评

暂无评论

Polarization trend in sponsored search auctions

Polarization trend in sponsored search auctions

引用

22nd Workshop on Information Technologies and systems, WITS 2012

作者： Yuan, Yong Zeng, Daniel Zhao, Huimin Cheng, Jiesi State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Department of Management Information Systems University of Arizona Tucson AZ United States Sheldon B. Lubar School of Business University of Wisconsin-Milwaukee Milwaukee WI United States

Quality score (QS) plays a critical role in sponsored search auctions and in practice is closely related to the historical click-through rate (CTR) of an advertisement. Existing research, however, has not explicitly considered this correlation between QS and historical CTR. In this paper, we strive to bridge this gap. Based on a discrete time-dependent optimal control model, which explicitly captures the CTR-QS correlation, we analyze the optimal positioning strategy and the widely-observed greedy positioning strategy for advertisers. We find that both strategies lead advertisers to monotonically increase or decrease their ranks over time, and thus may result in a polarization trend in sponsored search markets. Our findings can help characterize advertisers' behavior dynamics and also offer valuable insights and suggestions to search engines.

关键词： Polarization

来源：评论

学校读者我要写书评

暂无评论

Erratum to: Antimicrobials: a global alliance for optimizing their rational use in intra-abdominal infections (AGORA)

引用

World journal of emergency surgery : WJES 2017年第1期12卷 35页

作者： M Sartelli D G Weber E Ruppé M Bassetti B J Wright L Ansaloni F Catena F Coccolini F M Abu-Zidan R Coimbra E E Moore F A Moore R V Maier J J De Waele A W Kirkpatrick E A Griffiths C Eckmann A J Brink J E Mazuski A K May R G Sawyer D Mertz P Montravers A Kumar J A Roberts J L Vincent R R Watkins W Lowman B Spellberg I J Abbott A K Adesunkanmi S Al-Dahir M N Al-Hasan F Agresta A A Althani S Ansari R Ansumana G Augustin M Bala Z J Balogh O Baraket A Bhangu M A Beltrán M Bernhard W L Biffl M A Boermeester S M Brecher J R Cherry-Bukowiec O R Buyne M A Cainzos K A Cairns A Camacho-Ortiz S J Chandy A Che Jusoh A Chichom-Mefire C Colijn F Corcione Y Cui D Curcio S Delibegovic Z Demetrashvili B De Simone S Dhingra J J Diaz I Di Carlo A Dillip S Di Saverio M P Doyle G Dorj A Dogjani H Dupont S R Eachempati M A Enani V N Egiev M M Elmangory P Ferrada J R Fitchett G P Fraga N Guessennd H Giamarellou W Ghnnam G Gkiokas S R Goldberg C A Gomes H Gomi M Guzmán-Blanco M Haque S Hansen A Hecker W R Heizmann T Herzog A M Hodonou S K Hong R Kafka-Ritsch L J Kaplan G Kapoor A Karamarkovic M G Kees J Kenig R Kiguba P K Kim Y Kluger V Khokha K Koike K Y Kok V Kong M C Knox K Inaba A Isik K Iskandar R R Ivatury M Labbate F M Labricciosa P F Laterre R Latifi J G Lee Y R Lee M Leone A Leppaniemi Y Li S Y Liang T Loho M Maegele S Malama H E Marei I Martin-Loeches S Marwah A Massele M McFarlane R B Melo I Negoi D P Nicolau C E Nord R Ofori-Asenso A H Omari C A Ordonez M Ouadii G A Pereira Júnior D Piazza G Pupelis T M Rawson M Rems S Rizoli C Rocha B Sakakushev M Sanchez-Garcia N Sato H A Segovia Lohse G Sganga B Siribumrungwong V G Shelat K Soreide R Soto P Talving J V Tilsed J F Timsit G Trueba N T Trung J Ulrych H van Goor A Vereczkei R S Vohra I Wani W Uhl Y Xiao K C Yuan S K Zachariah J R Zahar T L Zakrison A Corcione R M Melotti C Viscoli P Viale Department of Surgery Macerata Hospital Via Santa Lucia 2 62100 Macerata Italy. Department of Trauma Surgery Royal Perth Hospital Perth Australia. Genomic Research Laboratory Geneva University Hospitals Geneva Switzerland. Infectious Diseases Division Santa Maria Misericordia University Hospital Udine Italy. Department of Emergency Medicine and Surgery Stony Brook University School of Medicine Stony Brook NY USA. General Surgery Department Papa Giovanni XXIII Hospital Bergamo Italy. Department of General Maggiore Hospital Parma Italy. Department of Surgery "Infermi" Hospital Rimini Italy. Department of Surgery College of Medicine and Health Sciences UAE University Al-Ain United Arab Emirates. Department of Surgery UC San Diego Medical Center San Diego USA. Department of Surgery University of Colorado Denver Health Medical Center Denver CO USA. Department of Surgery Division of Acute Care Surgery and Center for Sepsis and Critical Illness Research University of Florida College of Medicine Gainesville FL USA. Department of Surgery University of Washington Seattle WA USA. Department of Critical Care Medicine Ghent University Hospital Ghent Belgium. General Acute Care and Trauma Surgery Foothills Medical Centre Calgary AB Canada. General and Upper GI Surgery Queen Elizabeth Hospital Birmingham UK. Department of General Visceral and Thoracic Surgery Klinikum Peine Academic Hospital of Medical University Hannover Peine Germany. Department of Clinical microbiology Ampath National Laboratory Services Milpark Hospital Johannesburg South Africa. Department of Surgery School of Medicine Washington University in Saint Louis Saint Louis MO USA. Departments of Surgery and Anesthesiology Division of Trauma and Surgical Critical Care Vanderbilt University Medical Center Nashville TN USA. Department of Surgery University of Virginia Health System Charlottesville VA USA. Departments of Medicine Clinical Epidemiology and Biostatistics and Pathology and Mo

[This corrects the article DOI: 10.1186/s13017-016-0089-y.].

关键词：

来源：评论

学校读者我要写书评

暂无评论

Description for 3D images with histogram of gradients based on maximum directional derivative

International Journal of Digital Content Technology and its ...

引用

International Journal of Digital Content Technology and its Applications 2012年第4期6卷 15-23页

作者： Wang, Hu Zhang, Wensheng Liu, Jin State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China State Key Laboratory of software Engineering Computer School Wuhan University Wuhan 430072 China

The histogram of gradients for three-dimensional images (HOG3D) has been widely used to generate descriptors of local features for the matching of salient interest blobs between volumetric medical images. The distinctiveness of descriptors is essential to match similar patterns as well as differentiate different patterns. However, most methods for HOG3D are based on the unequal azimuth-elevation-angle division of the three-dimensional orientations, leading to the reduction of the distinctiveness. This paper presents a description method to extract distinctive descriptors by using a novel histogram of gradients based on the maximum directional derivative (HOG3DMAX). The three-dimensional orientations are divided equally into 24 homogeneous regions for the bins of gradient histogram to improve the distinctiveness. In addition, the interpolation of gradients is applied in HOG3DMAX according to the relatively simple form of the homogeneous regions in order to avoid harmful effects from boundary in images. Experiments were performed on three sets with different extents of similarity. The cluster analysis and classification accuracy were utilized to validate the proposed method. Compared with the commonly used azimuth-elevation based method, the new method shows lower intra-cluster pairwise distances relative to inter-cluster pairwise distances, and achieved 5% higher classification accuracy. The results indicate the improvement of distinctiveness by using equally divided regions and the interpolation of gradients. We conclude that the HOG3DMAX is an effective description method for three-dimensional images.

关键词： Cluster analysis

来源：评论

学校读者我要写书评

暂无评论

Application of feature matching in the vehicle violation detection in urban traffic

International Journal of Digital Content Technology and its ...

引用

International Journal of Digital Content Technology and its Applications 2012年第11期6卷 131-138页

作者： Ding, Huan Liu, Jin Zhao, Bo Zhang, Wensheng Dong, Wenyong State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Computer School Wuhan University China

Computer vision and video analytics become increasingly important for intelligent transport systems (ITSs), and violation detection is one of the key points in ITSs. It is widely recognized that image based systems are flexible and versatile for advanced traffic monitoring and enforcement applications. In the proposed method, we first locate the tails from the images captured by a stationary camera, and then SURF(Speeded Up Robust Features) feature points are extracted from these tail images. A matching based rough detection stage is taken place to identify the high risk tails which are seen as violations and the low risk tails which are omitted as regular vehicles. Finally, color and shape information are taken advantages of to accomplish violation detection in the undetermined vehicles in the previous stage. Experiments are conducted using real live video sequences captured from an urban cross road. Results show that our method can potentially have a good performance.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Research on students' mental crisis monitoring and intervention mechanism based on online social network

Research on students' mental crisis monitoring and intervent...

引用

2012 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2012

作者： Li, Suna Shao, Xia Zhao, Feifei Tianjin Polytechnic University Tianjin China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Dongguan Research Institute of CASIA Cloud Computing Center Chinese Academy of Sciences Songshan Lake Dongguan China

ISBN: (纸本)9781467324007

Internet as the fertile ground of free speech, everyone can express their emotions, cognition and views of things via the internet, especially in the era of Web2.0, the occurrence of blog which provides a wider space for personal speech. Internet provides a broad platform for contemporary college students to express thought and emotion, at the same time it provides a channel for education workers to understand students' thought and mental. Through real-time monitoring information on school area network, we can get real-time status, mood and some dynamic data which can portray characteristics of emotion of the concerned entity;also we can abstract the characterization of psychological crisis information, and use this feature to do data mining on these data. In this way we can find group of students which have tendency of psychological crisis, and use corresponding psychological crisis intervention online and offline methods to ease students' psychological crisis and to prevent tragic events in timely. © 2012 IEEE.

关键词： Students

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：