检索结果-内蒙古大学图书馆

IEEE international conference on High Performance Computing and Communications (HPCC)

作者： Zahid Mahmood Muhammad Usman Shahid Khan Muhammad Jawad Samee U. Khan Laurence T. Yang Department of Electrical & Computer Engineering North Dakota State University USA North Dakota State University Fargo ND US Department of Computer Science St. Francis Xavier University Antigonish NS Canada

image analytics, biometrics access control, security, and surveillance applications utilize complex machine learning and computer vision algorithms, such as face detection andrecognition. Speedup and accuracy are two important factors that need to be addressed in all such complex applications. Parallel computing breaks down the complex tasks into discrete fragments to be solved concurrently on multiple processors. The parallel computing procedure significantly reduces the executiontime with improved speedup. This paper presents a parallel framework for object detection and recognition for a secure vehicle parking. The proposed framework is divided in to three steps: (1) vehicle detection at the parking entry junction, (2)driver's face detection, and (3) identification of driver's face from the huge database of stored facial images. On successful identification of authorized person, vehicle is allowed to enter inthe parking-lot. The adaptive boosting algorithm is used for vehicle and face detection, while Eigenfaces based approach is employed for face recognition. Moreover, the scalability comparison of parallely executed driver face recognition algorithm indicates high speedup compared to serial execution. Furthermore, the results of the proposed framework reveal promising performance and encourage outcomes to be deployed in real-time at entrance/exits of the public/private vehicle parking areas.

关键词： Vehicles Face Face recognition Training Face detection Object detection Parallel processing

来源：评论

学校读者我要写书评

暂无评论

There are plenty of places like home: Using relational representations in hierarchies for distance-based image understanding

引用

NEUROCOMPUTING 2014年 123卷 75-85页

作者： Antanas, Laura van Otterlo, Martijn Mogrovejo, Jose Oramas Tuytelaars, Tinne De Raedt, Luc Katholieke Univ Leuven Dept Comp Sci B-3001 Heverlee Belgium Radboud Univ Nijmegen NL-6525 ED Nijmegen Netherlands Katholieke Univ Leuven Dept Elect Engn Louvain Belgium

Understanding images in terms of logical and hierarchical structures is crucial for many semantic tasks, including image retrieval, scene understanding and robotic vision. This paper combines robust feature extraction, qualitative spatial relations, relational instance-based learning and compositional hierarchies in one framework. For each layer in the hierarchy, qualitative spatial structures in images are detected, classified and then employed one layer up the hierarchy to obtain higher-level semantic structures. We apply a four-layer hierarchy to street view images and subsequently detect corners, windows, doors, and individual houses. (C) 2013 Elsevier B.V. All rights reserved.

关键词： Relational representations Relational instance-based learning Hierarchical image understanding

来源：评论

学校读者我要写书评

暂无评论

Digital Right Management Control for Joint Ownership of Digital images using Biometric Features

Digital Right Management Control for Joint Ownership of Digi...

引用

1st international conference on Signal processing and Integrated Networks (SPIN)

作者： Singh, Anushikha Dutta, Malay Kishore Travieso, Carlos M. Soni, K. M. Amity Univ Dept Elect & Commun Engn Noida India

ISBN: (纸本)9781479928668

This paper proposes a method to establish joint ownership of digital images by embedding imperceptible digital pattern in the image. This digital pattern is generated from biometric features of more than one subject in a strategic matter so that the identification of individual subject can be done and the multiple ownership of the digital images can be established. This digital pattern was embedded and extracted from the image and the experiments were also carried out when the image was subjected to signal processing attacks. Coefficients of mid frequency band discrete cosine transform was used for embedding as these coefficients do not adversely affect the perceptual transparency and is also significantly robust to normal signal processing attacks. Experimental results indicate that the insertion of this digital pattern does not change the perceptual properties of the image and the pattern survives signal processing attacks which can be extracted for unique identification.

关键词： Multiple biometric features Iris pattern recognition Robustness Perceptual Transparency Signal processing Attacks Digital watermarking

来源：评论

学校读者我要写书评

暂无评论

Semantic object recognition by merging decision tree with object ontology

Semantic object recognition by merging decision tree with ob...

引用

1st international conference on Advanced Technologies for Signal and image processing (ATSIP)

作者： Damak, Wafa Rebai, Issam Kallel, Imene Khanfir Higher Inst Comp & Multimedia Comp Imaging Elect Syst CEM Lab Sfax Tunisia Sfax Engn Sch Comp Imaging Elect Syst CEM Lab Sfax Tunisia Telecom Bretagne Dept Comp Sci Brest France

ISBN: (纸本)9781479948888

In this work, we propose an object recognition strategy in a domestic environment. Our contribution is to use low-level features extracted from images with high-level concepts generated from an ontology of domestic objects to get richer decision. It consists in developing a semantic classification by providing for a white cane user the class of the obstacle and the scene in which it is located. The classification is performed with a decision tree that provides a better recognition rate than SVM. The combination of color and texture features resolves the ambiguities of shape features for some objects that have similar shape.

关键词： Object recognition classification learning SVM decision tree ontology

来源：评论

学校读者我要写书评

暂无评论

Sufficient statistics Feature Mapping over Deep Boltzmann machine for Detection 22

Sufficient Statistics Feature Mapping over Deep Boltzmann Ma...

引用

22nd international conference on pattern recognition (ICPR)

作者： Zhang, Chao Li, Xiong Yan, Junchi Chu, stephen Wang, Yu Tian, Chunhua Zhao, Yuming Shanghai Jiao Tong Univ Shanghai 200030 Peoples R China

ISBN: (纸本)9781479952083

As an important and fundamental methodology in the fields of pattern recognition and image processing, learning middle level feature has attracted increasing interest during the recent years, where generative feature mapping has shown highly completive performance in diverse applications. In this paper, a middle level feature representation is proposed based on Deep Boltzmann machine (DBM) and sufficient statistics (SS) feature mapping for detection. In the approach, DBM is employed to model data distribution and the hidden information inferred by DBM together with other informative variables are then exploited by SS to form the middle level features. The features, learnt from data, can be fed to standard classifiers for classification. In order to evaluate the performance of our method, we apply our feature mapping method to two challenging tasks: (1) contour detection through distinguishing border and non-border pixels;(2) sales pipeline prediction, which predicts the winning propensity of the ongoing sales opportunity in the pipeline. In comparison with other leading methods in the literature on the Berkeley Segmentation Dataset and Sales Pipeline Database (SPDB), our proposed algorithm performs favorably against state-of-the-art methods in terms of effectiveness and efficiency.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

Development of an image processing Based Sheet Music recognition System for iOS Devices 1

Development of an Image Processing Based Sheet Music Recogni...

引用

1st IEEE international conference on Consumer Electronics - Taiwan (ICCE-TW)

作者： Wang, Bo-Ren Chen, Ching-Yung Natl Kaohsiung First Univ Sci & Technol Dept Comp & Commun Engn Kaohsiung Taiwan

ISBN: (纸本)9781479948512

Intelligent mobile devices with multiple sensors and technologies have been spread widely and gradually. This paper presents a sheet music recognition system that can automatically recognize and perform the musical score with a simulated piano on iOS devices. The overall music recognition system consists of three functional parts. The first part is designed to pre-process the input image of a musical score. The major task of the second part is to segment each individual object on the musical score followed by note and pitch recognition. Finally, the recognized notes are transformed to the MIDI forms and the musical score is performed by a simulated piano. The proposed system has been implemented as an App which can be run of iOS devices.

关键词： Computers image recognition Intelligent sensors Mobile handsets Performance evaluation Transforms Mobile phones recognition system intelligent sensors image recognition Transform Computers Performance Evaluation image processing PIANO

来源：评论

学校读者我要写书评

暂无评论

Gait recognition Based on Modified Phase Only Correlation

Gait Recognition Based on Modified Phase Only Correlation

引用

6th international conference on image and Signal processing (ICISP)

作者： Rida, Imad Bouridane, Ahmed Al Kork, Samer Bremond, Francois INSA Rouen LITIS EA 4108 St Etienne France Northumbria Univ Dept Comp Sci & Digital Technol Newcastle England ESPCI Paris Tech Signal Proc & Machine Learning Lab Paris France INRIA Sophia Antipolis STARS team Sophia Antipolis Sophia Antipolis France

ISBN: (纸本)9783319079981;9783319079974

Clothing, carrying conditions, and other intra-class variations, also referred as "covariates", affect the performance of gait recognition systems. This paper proposes a supervised feature extraction method which is able to select relevant features for human recognition to mitigates the impact of covariates and hence improve the recognition performance. The proposed method is evaluated using CASIA Gait Database (Dataset B) and the experimental results suggest that our method yields attractive results.

关键词： Gait phase only correlation feature selection

来源：评论

学校读者我要写书评

暂无评论

Low Computing Complexity A rchitecture Design of 2D-to-3D image Converter 1

Low Computing Complexity A rchitecture Design of 2D-to-3D Im...

引用

1st IEEE international conference on Consumer Electronics - Taiwan (ICCE-TW)

作者： Fan, Yu-Cheng Chen, Po-Wei Chen, Wei-Syuan

ISBN: (纸本)9781479948512

In this paper, we propose a low computing complexity architecture design of 2D-to-3D image converter. The presented approach establishes database of slope pattern to analyze the 2D image. According to slope and intersection, the scheme predicts vanishing points of 2D image. Then, depth map is reconstructed using vanishing points information. This approach focuses on fundamental structure analysis to reduce computing complexity and performs low computing complexity architecture of 2D-to-3D image converter.

关键词： Complexity theory Computer architecture image converters pattern analysis pattern recognition Three-dimensional displays

来源：评论

学校读者我要写书评

暂无评论

Dynamic Local Contrast Enhancement for Advanced Driver Assistance System in Harsh Environments 1

Dynamic Local Contrast Enhancement for Advanced Driver Assis...

引用

1st IEEE international conference on Consumer Electronics - Taiwan (ICCE-TW)

作者： Hsu, Sheng-Wei Chen, Guan-Yu Shen, Po-Chun Cho, Chao-Yi Guo, Jiun-In Natl Chiao Tung Univ Hsinchu Taiwan Ind Technol Res Inst Zhudong Township Taiwan

ISBN: (纸本)9781479948512

This paper presents a Dynamic Local Contrast Enhancement (DLCE) method, which can strengthen the image quality in most of inclement weather conditions. This improves unnatural image over-enhancement, reduce noise, make image more saturated, and can be applied on foggy day and night. DLCE reaches 50 fps D1 resolution and 120 fps CIF resolution on ATOM 1.6GHz in TREK-668 embedded platform.

关键词： Adaptive equalizers Computer vision Flowcharts Histograms image quality Meteorology pattern recognition adaptive equalisers Flowcharts image quality images Driver Assistance Systems histograms Meteorology computer vision pattern recognition contrast enhancement Harsh environments advanced driver assistance systems (ADAS)

来源：评论

学校读者我要写书评

暂无评论

Proceedings of 2014 1st international conference on Information and Communication Technologies Innovations and Applications, ICTIA 2014

Proceedings of 2014 1st International Conference on Informat...

引用

1st international conference on Information and Communication Technologies Innovations and Applications, ICTIA 2014

ISBN: (纸本)9781479969500

The proceedings contain 26 papers. The topics discussed include: development of a low-cost accurate phase measurement system;the construction of sequences for identification of digital circuits using simulated annealing (SA);fuzzy model for multicriteria decision making;affixal approach for Arabic decomposable word recognition : a validation on the multi-font printed script;detection of the thickness of scale on the inner surface of water pipes by infrared thermography;arabic handwritten word recognition with large vocabulary based on explicit segmentation;printed/handwritten Arabic script identification using local features and GMMs;the use of web 2.0 and online virtual communities to develop marketing strategies;the k-unobservability: a new privacy protection guarantee for e-service systems;e-learning and entrepreneurship: is it the perfect match?;fabrics defects detecting using image processing and neural networks;advanced hybrid tracking through neural network regression;nearest cluster center decision in hierarchical classification process;proposition to distinguish machine-printed from handwritten Arabic and Latin words;robust and blind watermarking of avatar faces;and remote laboratories across the Mediterranean, EOLES project, a case study and a point of start.

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：