检索结果-内蒙古大学图书馆

IEEE International Conference on Image Processing

作者： M. J. Shafiee A. G. Chung A. Wong P. Fieguth Vision & Image Processing Lab Systems Design Engineering Dept. University of Waterloo

ISBN: (纸本)9781479983407

Markov random fields (MRFs) and conditional random fields (CRFs) are influential tools in image modeling, particularly for applications such as image segmentation. Local MRFs and CRFs utilize local nodal interactions when modeling, leading to excessive smoothness on boundaries (i.e., the short-boundary bias problem). Recently, the concept of fully connected conditional random fields with stochastic cliques (SFCRF) was proposed to enable long-range nodal interactions while addressing the computational complexity associated with fully connected random fields. While SFCRF was shown to provide significant improvements in segmentation accuracy, there were still limitations with the preservation of fine structure boundaries. To address these limitations, we propose a new approach to stochastic clique formation for fully connected random fields (G-SFCRF) that is guided by the structural characteristics of different nodes within the random field. In particular, fine structures surrounding a node are modeled statistically by probability distributions, and stochastic cliques are formed by considering the statistical similarities between nodes within the random fields. Experimental results show that G-SFCRF outperforms existing fully connected CRF frameworks, SFCRF, and the principled deep random field framework for image segmentation.

关键词： Stochastic Cliques SFCRF Guided Stochastic Cliques CRF Segmentation Fully connected Corticotropin-Releasing Hormone segmentation Segmentation image segmentation fine structure Modeling Random Markov random fields all-pass Ganglia Probability distribution Structural properties complexity classes

来源：评论

学校读者我要写书评

暂无评论

HIGH DYNAMIC RANGE MAP ESTIMATION VIA FULLY CONNECTED RANDOM FIELDS WITH STOCHASTIC CLIQUES

HIGH DYNAMIC RANGE MAP ESTIMATION VIA FULLY CONNECTED RANDOM...

引用

IEEE International Conference on Image Processing

作者： F. Y. Li M. J. Shafiee A. G. Chung B. Chwyl F. Kazemzadeh A. Wong J. Zelek Vision & Image Processing Lab Systems Design Engineering Dept. University of Waterloo

ISBN: (纸本)9781479983407

The reconstruction of high dynamic range (HDR) images via conventional camera systems and low dynamic range (LDR) images is a growing field of research in image acquisition. The radiance map associated with the HDR image of a scene is typically computed using multiple images of the same scene captured at different exposures (i.e., bracketed LDR imzages). This approach, though inexpensive, is sensitive to noise under high camera ISO. Each bracketed image is associated with a different level of noise due to the change in exposure time, and the noise is further amplified when tone-mapping the HDR image for display. A new framework is proposed to address the associated noise in the context of random fields. The estimation of the HDR image from a set of LDR images is formulated as a stochastically fully connected conditional random field where the spatial information is incorporated to compute the HDR value in combination with the LDR image values. Experimental results show that the proposed framework compensated the non-stationary ISO noise while preserving the boundaries in the estimated HDR images.

关键词： High Dynamic Range Imaging Conditional Random Fields Image Denoising HDR Reconstruction SFCRF image denoising hot dry rocks GATA3 gene LAND DISPOSAL RESTRICTIONS Noise images HIGH DYNAMIC RANGE Markov random fields field surveys Noise levels Brackets Cameras

来源：评论

学校读者我要写书评

暂无评论

EXTERNAL FORCES FOR ACTIVE CONTOURS USING THE UNDECIMATED WAVELET TRANSFORM

EXTERNAL FORCES FOR ACTIVE CONTOURS USING THE UNDECIMATED WA...

引用

IEEE International Conference on Image Processing

作者： Ahmed Gawish Paul Fieguth Vision and Image Processing (VIP) Lab Department of Systems Design Engineering University of Waterloo

ISBN: (纸本)9781479983407

A limitation of active contours models (both parametric and geometric) is their sensitivity to noise. Many solutions to noise sensitivity have been proposed in the literature, with the current state-of-the-art based on image blurring and multiresolution processing. However a significant drawback of both approaches is the side effect of edge delocalization. In this paper, gradient information extracted from all resolutions of the undecimated wavelet transform is used to build the external force map for the active contour. The new map accurately drives the active contour and improves edge localization. The proposed method builds on both Gradient Vector Flow and Vector Field Convolution active contours. Comparisons to classical and state-of-the-art methods show a dramatic improvement in active contour convergence for all levels of noise.

关键词： Active contours Undecimated wavelet transform Active contours contour image blur Noise sensitivity Side Effect wavelet transforms Gradient vector Noise Parametric

来源：评论

学校读者我要写书评

暂无评论

COVIDx CT-3: A Large-scale, Multinational, Open-Source Benchmark Dataset for Computer-aided COVID-19 Screening from Chest CT Images

arXiv

引用

arXiv 2022年

作者： Gunraj, Hayden Tuinstra, Tia Wong, Alexander Vision and Image Processing Lab University of Waterloo Canada Department of Systems Design Engineering University of Waterloo Canada Waterloo AI Institute University of Waterloo Canada DarwinAI Corp Canada

Computed tomography (CT) has been widely explored as a COVID-19 screening and assessment tool to complement RT-PCR testing. To assist radiologists with CT-based COVID-19 screening, a number of computer-aided systems have been proposed. However, many proposed systems are built using CT data which is limited in both quantity and diversity. Motivated to support efforts in the development of machine learning-driven screening systems, we introduce COVIDx CT-3, a large-scale multinational benchmark dataset for detection of COVID-19 cases from chest CT images. COVIDx CT-3 includes 431,205 CT slices from 6,068 patients across at least 17 countries, which to the best of our knowledge represents the largest, most diverse dataset of COVID-19 CT images in open-access form. Additionally, we examine the data diversity and potential biases of the COVIDx CT-3 dataset, finding that significant geographic and class imbalances remain despite efforts to curate data from a wide variety of sources. Copyright © 2022, The Authors. All rights reserved.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

CMNN: cooperative modular neural network

CMNN: cooperative modular neural network

引用

International Conference on Neural Networks

作者： G. Auda M. Kamel Pattern Analysis And Machine Intelhgence Lab Systems Design Engineering Department University of Waterloo Canada

The current generation of nonmodular neural network classifiers is unable to cope with classification problems which have a wide range of overlap among classes. This is due to the high coupling among the networks' hidden nodes. We propose the Cooperative Modular Neural Network (CMNN) architecture, which deals with different levels of overlap in different modules. The modules share their information and cooperate in taking a global classification decision through voting. Moreover, special modules are dedicated to resolve high overlaps in the input-space. The performance of the new model outperforms that of the nonmodular alternative when when applied to ten famous benchmark classification problems.

关键词： Neural networks Clustering algorithms Buildings Subspace constraints Pattern analysis System analysis and design design engineering systems engineering and theory Voting Electronic learning

来源：评论

学校读者我要写书评

暂无评论

Q(/spl Lambda/)-based image thresholding

Q(/spl Lambda/)-based image thresholding

引用

Canadian Conference on Computer and Robot Vision, CRV

作者： M. Shokri H.R. Tizhoosh Pattern Analysis and Machine Intelligence Lab Systems Design Engineering University of Waterloo ONT Canada

One of the problems in image processing is finding an appropriate threshold in order to convert an image to a binary one. In this paper we introduce a new method for image thresholding. We use reinforcement learning as an effective way to find the optimal threshold. Q(Λ) is implemented as a learning algorithm to achieve more accurate results. The reinforcement agent uses objective rewards to explore/exploit the solution space. It means that there is not any experienced operator involved and the reward and punishment function must be defined for the agent. The results show that this method works successfully and can be trained for any particular application.

关键词： Learning Histograms Image processing Image converters Image segmentation Pattern analysis Machine intelligence System analysis and design design engineering systems engineering and theory

来源：评论

学校读者我要写书评

暂无评论

EVOL: ensembles voting online

EVOL: ensembles voting online

引用

International Joint Conference on Neural Networks (IJCNN)

作者： G. Auda M. Kamel Pattern Analysis And Machine Intelligence Lab Systems Design Engineering Department University of Waterloo Canada

Cooperation by voting is one of the popular modular neural network decision-making strategies. Ensemble classifiers are multiple identical modules which use voting for post-learning classification. This paper suggests a new cooperation scheme for ensembles which utilizes voting in the learning process itself. According to the suggested scheme, different modules would, automatically, focus on different regions in the input space. Hence, temporal crosstalk decreases and decision boundaries are drawn accurately in complex overlapping regions of the input space.

关键词： Voting Neural networks Decision making Multi-layer neural network Filtering Crosstalk Pattern analysis Machine intelligence System analysis and design design engineering

来源：评论

学校读者我要写书评

暂无评论

UNDECIMATED HIERARCHICAL ACTIVE CONTOURS FOR OCT IMAGE SEGMENTATION

UNDECIMATED HIERARCHICAL ACTIVE CONTOURS FOR OCT IMAGE SEGME...

引用

IEEE International Conference on Image Processing

作者： Ahmed Gawish Paul Fieguth Sebastian Marschall Kostadinka Bizheva Vision and Image Processing (VIP) Lab Dept. of Systems Design Engineering University of Waterloo Dept. of Physics and Astronomy University of Waterloo

ISBN: (纸本)9781479957521

A limitation of Optical Coherence Tomography (OCT) image segmentation is the poor signal-to-noise ratio of the imaging process, particularly because images are sampled quickly, at high resolutions, and in-vivo. Furthermore, speckle noise is generated by the reflections of the OCT LASER. Because OCT is widely used in imaging the cornea, retina, and skin, OCT layer segmentation is of key interest in all applications. In this paper, a multi-resolution parametric active contour is used for OCT segmentation. The proposed method uses an undecimated wavelet transform to obtain scale-dependent noise reduction, while the active contour is initialized with a generalized Hough transform. Experimental results show that the proposed method outperforms classical as well as state-of-the-art methods and segments OCT images with high level of accuracy.

关键词： Undecimated wavelet transform Optical coherence tomography Active contours Hough transform

来源：评论

学校读者我要写书评

暂无评论

Optimization of a Neural Dynamics Based Controller for a Nonholonomic Mobile Robot Using Genetic Algorithms

Optimization of a Neural Dynamics Based Controller for a Non...

引用

International Conference on Control and Automation (ICCA)

作者： Hao Li S.X. Yang F. Karray Pattern Analysis and Machine Intelligence (PAMI) Lab Systems Design Engineering University of Waterloo Waterloo ONT Canada Advanced Robotics and Intelligent Systems (ARIS) Laboratory School of Engineering University of Guelph Guelph ONT Canada

In this paper, a neural dynamics based controller for a nonholonomic mobile robot is proposed. The turn angle of the robot in the proposed model is characterized by a biologically inspired shunting equation derived from Hodgkin and Huxley’s membrane equation. This model is capable of generating smooth steering velocity command that drives the robot to track desired paths. Some parameters in the proposed neural dynamics based controller need to be selected. A genetic algorithm is designed to optimize the model parameters that can guarantee the convergence of tracking error of the mobile robot. Simulation studies of a fourdegree-of-freedom mobile robot are conducted, which demonstrate the effectiveness of the proposed motion controller.

关键词： Mobile robots Genetic algorithms Biological system modeling Equations Biomembranes Algorithm design and analysis design optimization Convergence Motion control

来源：评论

学校读者我要写书评

暂无评论

Wireless Federated Learning With Hybrid Local and Centralized Training: A Latency Minimization design

引用

IEEE Journal on Selected Topics in Signal Processing 2023年第1期17卷 248-263页

作者： Huang, Ning Dai, Minghui Wu, Yuan Quek, Tony Q. S. Shen, Xuemin State Key Lab of Internet of Things for Smart City China University of Macau Department of Computer and Information Science China University of Macau State Key Laboratory of Internet of Things for Smart City The Department of Computer and Information Science China Zhuhai Um Science and Technology Research Institute Zhuhai519031 China Singapore University of Technology and Design Information Systems Technology and Design Pillar 487372 Singapore National Cheng Kung University Taiwan University of Waterloo Department of Electrical and Computer Engineering WaterlooONN2L 3G1 Canada

Wireless federated learning (FL) is a collaborative machine learning (ML) framework in which wireless client-devices independently train their ML models and send the locally trained models to the FL server for aggregation. In this paper, we consider the coexistence of privacy-sensitive client-devices and privacy-insensitive yet computing-resource constrained client-devices, and propose an FL framework with a hybrid centralized training and local training. Specifically, the privacy-sensitive client-devices perform local ML model training and send their local models to the FL server. Each privacy-insensitive client-device can have two options, i.e., (i) conducting a local training and then sending its local model to the FL server, and (ii) directly sending its local data to the FL server for the centralized training. The FL server, after collecting the data from the privacy-insensitive client-devices (which choose to upload the local data), conducts a centralized training with the received datasets. The global model is then generated by aggregating (i) the local models uploaded by the client-devices and (ii) the model trained by the FL server centrally. Focusing on this hybrid FL framework, we firstly analyze its convergence feature with respect to the client-devices' selections of local training or centralized training. We then formulate a joint optimization of client-devices' selections of the local training or centralized training, the FL training configuration (i.e., the number of the local iterations and the number of the global iterations), and the bandwidth allocations to the client-devices, with the objective of minimizing the overall latency for reaching the FL convergence. Despite the non-convexity of the joint optimization problem, we identify its layered structure and propose an efficient algorithm to solve it. Numerical results demonstrate the advantage of our proposed FL framework with the hybrid local and centralized training as well as our proposed alg

关键词： Information management

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：