检索结果-内蒙古大学图书馆

International IEEE/EMBS Conference on Neural Engineering, CNE

作者： Ali Bashashati Rabab Ward Gary Birch Electrical & Computer Engineering Department University of British Columbia Canada

Unlike synchronous brain computer interfaces (BCI), self-paced (asynchronous) BCIs have the advantage of being operational at all times. A 3-state self-paced BCI is capable of detecting two different brain states (e.g. two movements) from the ongoing EEG, while a 2-state one can only detect one brain state. This study improves the performance of a 3-state self-paced BCI designed to detect right and left hand extension movements. Instead of using the values of features at each instant of time, the improved BCI uses all past features' values to detect the presence of a movement at any specific time. After detecting the presence of a movement, the system uses spectral features to determine whether the detected movement is a right or a left hand extension. Using data from two able-bodied individuals, it is shown that the correct detection of a right or a left hand movement, on average, increases from 44.3% to 55.9%, for a fixed false positive rate of 1%. In differentiating between right and left hand movements the average performance increases from 64% to 68.5%. At the false positive rate of 0.5%, the average true positive rate increases from 20.2% to 27.6% and the differentiation rate between right and left hand extensions increase from 71% to is 72.5%.

关键词： Brain computer interfaces Control systems Electroencephalography computer vision Communication system control Maintenance engineering System testing Switches Fingers pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Block-Based Adaptive Vector Lifting Schemes for Multichannel Image Coding

引用

EURASIP JOURNAL ON IMAGE AND VIDEO PROCESSING 2007年第1期2007卷 013421-013421页

作者： Benazza-Benyahia, Amel Pesquet, Jean-Christophe Hattay, Jamel Masmoudi, Hela Ecole Super Commun SUPCOM URISA Tunis 2083 Tunisia Univ Marne La Vallee Inst Gaspard Monge F-77454 Marne La Vallee 2 France Univ Marne La Vallee CNRS UMR 8049 F-77454 Marne La Vallee 2 France George Washington Univ Dept Elect & Comp Engn Washington DC 20052 USA US FDA Ctr Devices & Radiol Hlth Div Imaging & Appl Math Rockville MD 20852 USA

We are interested in lossless and progressive coding of multispectral images. To this respect, nonseparable vector lifting schemes are used in order to exploit simultaneously the spatial and the interchannel similarities. The involved operators are adapted to the image contents thanks to block-based procedures grounded on an entropy optimization criterion. A vector encoding technique derived from EZW allows us to further improve the efficiency of the proposed approach. Simulation tests performed on remote sensing images show that a significant gain in terms of bit rate is achieved by the resulting adaptive coding method with respect to the non-adaptive one. Copyright (C) 2007 Amel Benazza-Benyahia et al.

关键词： Entropy Image Processing pattern recognition computer vision Optimization Criterion

来源：评论

学校读者我要写书评

暂无评论

Attention-driven dynamic graph convolutional network for multi-label image recognition

arXiv

引用

arXiv 2020年

作者： Ye, Jin He, Junjun Peng, Xiaojiang Wu, Wenhao Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China School of Biomedical Engineering Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China

Recent studies often exploit Graph Convolutional Network (GCN) to model label dependencies to improve recognition accuracy for multi-label image recognition. However, constructing a graph by counting the label co-occurrence possibilities of the training data may degrade model generalizability, especially when there exist occasional co-occurrence objects in test images. Our goal is to eliminate such bias and enhance the robustness of the learnt features. To this end, we propose an Attention-Driven Dynamic Graph Convolutional Network (ADD-GCN) to dynamically generate a specific graph for each image. ADD-GCN adopts a Dynamic Graph Convolutional Network (D-GCN) to model the relation of content-aware category representations that are generated by a Semantic Attention Module (SAM). Extensive experiments on public multi-label benchmarks demonstrate the effectiveness of our method, which achieves mAPs of 85.2%, 96.0%, and 95.5% on MS-COCO, VOC2007, and VOC2012, respectively, and outperforms current state-of-the-art methods with a clear margin. All codes can be found at https://***/Yejin0111/ADD-GCN. Copyright © 2020, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Modeling and analyzing InSAR phase profiles at building locations

Modeling and analyzing InSAR phase profiles at building loca...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： A. Thiele E. Cadario K. Schulz U. Thoennessen U. Soergel Research Institute for Optronics and Pattern Recognition FGAN-FOM Ettlingen Germany Institute of Photogrammetry and GeoInformation Leibniz University Hannover Hanover Germany

The improved ground resolution of state-of-the-art synthetic aperture radar (SAR) sensors suggests utilizing SAR data for the analysis of urban areas. Even in the case of InSAR, for building recognition usually the analysis is triggered mainly from features detected in the magnitude images. However, considering InSAR data significant phase profiles in range direction at building locations are observable. In this paper a simple model for these characteristic profiles in layover areas is proposed. The model takes into account that in layover areas a mixture of several signal sources contribute to the interferometric phase of a range cell. At building locations a combination of contributions from ground, wall, and roof is observed. The resulting phase profiles are characterized by sensor and illumination parameters as well as object parameters. In the first part of this paper, simulated phase images at building locations based on a given surface profile in range direction are presented. In the second part, real InSAR data sets of the airborne sensors AeS-1 (Intermap) and AER-II (FGAN-FHR) with a slant range resolution of 38 cm respectively 94 cm are used to calculate interferometric phase truth data which are then compared with the simulation results.

关键词： Synthetic aperture radar interferometry Synthetic aperture radar Sensor phenomena and characterization Data analysis Urban areas Image recognition Image analysis computer vision Radar detection Lighting

来源：评论

学校读者我要写书评

暂无评论

A Hierarchical Approach for Fast and Robust Ellipse Extraction

A Hierarchical Approach for Fast and Robust Ellipse Extracti...

引用

IEEE International Conference on Image Processing

作者： F. Mai Y. S. Hung H. Zhong W. F. Sze Department of Electrical and Electronic Engineering University of Hong Kong Hong Kong China

This paper presents a hierarchical approach for fast and robust ellipse extraction from images. At the lowest level, the image is described as a set of edge pixels, from which line segments are extracted. Then, line segments that are potential candidates of elliptic arcs are linked to form arc segments according to connectivity and curvature relations. After that, arc segments that belong to the same ellipse are grouped together. Finally, a robust statistical method, namely RANSAC, is applied to fit ellipses. This method does not need a high dimensional parameter space like Hough transform based algorithms, and so it reduces the computation and memory requirements. Experiments on both synthetic and real images demonstrate that the proposed method has excellent performance in handling occlusion and overlapping ellipses.

关键词： Robustness Image segmentation Image edge detection Joining processes Pixel pattern recognition Genetic algorithms Data mining Statistical analysis computer vision

来源：评论

学校读者我要写书评

暂无评论

A Linear-Time Two-Scan Labeling Algorithm

A Linear-Time Two-Scan Labeling Algorithm

引用

IEEE International Conference on Image Processing

作者： Lifeng He Yuyan Chao Kenji Suzuki Department of Radiology University of Chicago Chicago IL USA Shaanxi University of Science and Technology China Aichi Prefectural University Nagakute Aichi Japan

This paper presents a fast linear-time two-scan algorithm for labeling connected components in binary images. In the first scan, provisional labels are assigned to object pixels in the same way as do most conventional labeling algorithms. To improve efficiency, we use corresponding equivalent label sets and a representative label table for resolving label equivalences. When the first scan is finished, all provisional labels belonging to each connected component in a given image are combined in the corresponding equivalent label set, and they are assigned a unique representative label with the representative label table. During the second scan, by use of the completed representative label table, all provisional labels belonging to each connected component are replaced by their representative label. Our algorithm is very simple in principle, and is easy to implement. Experimental results demonstrated that the efficiency of our algorithm is superior to that of other labeling algorithms.

关键词： Labeling Pixel pattern recognition Chaos Radiology Biology Image processing computer vision Noise reduction Interpolation

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Optimization ofWavelet Feature Sets for Real-Time Pedestrian Classification

Evolutionary Optimization ofWavelet Feature Sets for Real-Ti...

引用

International Conference on Hybrid Intelligent Systems (HIS)

作者： Jan Salmen Thorsten Suttorp Johann Edelbrunner Christian Igel Institut für Neuroinformatik Ruhr Universität Bochum Bochum Germany

computer vision for object detection often relies on complex classifiers and large feature sets to achieve high detection rates. But when real-time constraints have to be met, for example in driver assistance systems, fast classifiers are required. Here we consider the design of a computationally efficient system for pedestrian detection. We propose an evolutionary algorithm for the optimization of a small set of wavelet features, which can be computed very efficiently. These features serve as input to a linear classifier. The classification performance of the optimized system is on par with recently published results obtained with support vector machines on large feature sets, while the computational time is lower by orders of magnitude.

关键词： Object detection Cameras Real time systems Support vector machines Support vector machine classification pattern recognition Road accidents Face detection Pixel Hybrid intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Semantic Clinical Process Management

Semantic Clinical Process Management

引用

Annual IEEE Symposium on computer-Based Medical Systems

作者： Massimo Ruffolo Marco Manna Vittoria Cozza Raffaello Ursino ICAR-CNR University of Calabria Rende Italy Department of Mathematics University of Calabria Rende Italy Exeura s.r.l. University of Calabria Rende Italy Orangee s.r.l. University of Calabria Rende Italy

This work describes a clinical process management system aimed to support a process-centred vision of health care practices. The system is founded on knowledge representation and semantic information extraction approaches allowing medical knowledge modelling and acquisition. At the heart of the system there are formalisms and languages well suited for representing, clinical processes as workflows, medical and domain knowledge as ontologies and rules enabling the recognition of semantic patterns representing ontology concepts. The system acquires and stores clinical process instances into a medical knowledge base which parameters are obtained exploiting a semantic information extraction approach enabling automatic medical knowledge acquisition from unstructured clinical documents. The main goal of the system is to assists health care professional in executing and monitoring clinical processes by providing functionalities for automatic knowledge acquisition. Acquired information can be analyzed for identifying main causes of medical errors, high costs and, potentially, to suggest clinical processes restructuring or improvement able to enhance cost control and patient safety.

关键词： Medical services Data mining Ontologies Knowledge acquisition Costs Knowledge representation Heart pattern recognition Patient monitoring Biomedical monitoring

来源：评论

学校读者我要写书评

暂无评论

Object detection with convolutional context features

Object detection with convolutional context features

引用

IEEE Signal Processing and Communications Applications (SIU)

作者： Emre Can Kaya A. Aydın Alatan Elektrik-Elektronik Mühendisliği Orta Doğu Teknik Üniversitesi Ankara Türkiye

A novel extension to Hızlı B-ESA object detection algorithm is proposed in order to learn convolutional context features for determining boundaries of objects better. For input images, the hypothesis windows and their context around those windows are learned through convolutional layers as two parallel networks. The resulting object and context feature maps are combined in such a way that they preserve their spatial relationship. The proposed algorithm is trained and evaluated on PASCAL VOC 2007 detection benchmark dataset and yielded improvements in performance over state-of-the-art, for almost all classes, especially the ones with distinctive context.

关键词： computer vision Context Conferences Object detection pattern recognition Dogs Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Correntropy Supervised Non-negative Matrix Factorization

Correntropy Supervised Non-negative Matrix Factorization

引用

International Joint Conference on Neural Networks

作者： Wenju Zhang Naiyang Guan Dacheng Tao Bin Mao Xuhui Huang Zhigang Luo Science and Technology on Parallel and Distributed Processing Laboratory College of Computer National University of Defense Technology Changsha Hunan China 410073 Center for Quantum Computation and Intelligent Systems FEIT University of Technology Sydney Sydney NSW 2007 Australia College of Science National University of Defense Technology Changsha Hunan China 410073 Department of Computer Science and Technology College of Computer National University of Defense Technology Changsha Hunan China 410073

ISBN: (纸本)9781479919611

Non-negative matrix factorization (NMF) is a powerful dimension reduction method and has been widely used in many pattern recognition and computer vision problems. However, conventional NMF methods are neither robust enough as their loss functions are sensitive to outliers, nor discriminative because they completely ignore labels in a dataset. In this paper, we proposed a correntropy supervised NMF (CSNMF) to simultaneously overcome aforementioned deficiencies. In particular, CSNMF maximizes the correntropy between the data matrix and its reconstruction in low-dimensional space to inhibit outliers during learning the subspace, and narrows the minimizes the distances between coefficients of any two samples with the same class labels to enhance the subsequent classification performance. To solve CSNMF, we developed a multiplicative update rules and theoretically proved its convergence. Experimental results on popular face image datasets verify the effectiveness of CSNMF comparing with NMF, its supervised variants, and its robustified variants.

关键词： NMF subsequent classification NMF protocol matrix decomposition outliers Nonnegative LOSS FUNCTION images REDUCTION METHODS Dataset 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：