检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： M. Ventresca H.R. Tizhoosh Pattern Analysis and Machine Intelligence (PAMI) laboratory in the Systems Design Engineering Department University of Waterloo Waterloo ONT Canada

The backpropagation algorithm is a very popular approach to learning in feed-forward multi-layer perceptron networks. However, in many scenarios the time required to adequately learn the task is considerable. Many existing approaches have improved the convergence rate by altering the learning algorithm. We present a simple alternative approach inspired by opposition-based learning that simultaneously considers each network transfer function and its opposite. The effect is an improvement in convergence rate and over traditional backpropagation learning with momentum. We use four common benchmark problems to illustrate the improvement in convergence time.

关键词： Convergence Transfer functions Neural networks Backpropagation algorithms Genetic algorithms pattern analysis machine intelligence Laboratories System analysis and design Design engineering

来源：评论

学校读者我要写书评

暂无评论

An Anatomy of IrisCode for Precise Phase Representation

An Anatomy of IrisCode for Precise Phase Representation

引用

International Conference on pattern Recognition

作者： A. Kong D. Zhang M. Kamel Pattern Analysis and Machine Intelligence Laboratory University of Waterloo Canada Biometric Research Centre Hong Kong Polytechnic University Hong Kong China

IrisCode, a widely deployed iris recognition algorithm, developed in 1993 and continuously modified by Daugman has attracted considerable attentions. IrisCode using a coarse phase representation has number of properties such as rapid matching, binomial imposter distribution and predictable false acceptance rate. Although many similar coding methods have been developed for irises and palmprintgs based on IrisCode, a theoretical analysis of IrisCode has not been provided. In this paper, we aim at studying (1) the nature of IrisCode, (2) the property of the phase of Gabor function, (3) the extension of bitwise Hamming distance and (4) the theoretical foundation of the binomial imposter distribution and extending the coarse phase representation to a precise phase representation. Precisely, we demonstrate that IrisCode is a clustering algorithm with four prototypes; the locus of a Gabor function is a two-dimensional ellipse with respect to the phase parameter and bitwise Hamming can be regarded as angular distance. Using these properties, we provide a precise phase representation for IrisCode with an effective implementation for filtering and matching. Practically, the imposter distribution of IrisCode follows binomial distribution. However, the theoretical evidence is incomplete according to our analysis

关键词： Anatomy Hamming distance Biometrics Databases pattern analysis machine intelligence Iris recognition Waveguide discontinuities Clustering algorithms Prototypes

来源：评论

学校读者我要写书评

暂无评论

Does EigenPalm work? A System and Evaluation Perspective

Does EigenPalm work? A System and Evaluation Perspective

引用

International Conference on pattern Recognition

作者： King-Hong Cheung A. Kong D. Zhang M. Kamel J. You Department of Computing Hong Kong Polytechnic University Hong Kong China Pattern Analysis and Machine Intelligence Laboratory University of Waterloo Waterloo ONT Canada

Recently, there are keen interests in EigenPalm, which, collectively, refers to those methods that extract palmprint features directly from the appearance by means of principal component analysis (PCA) for (dis)similarity matching. Encouraging results have been reported with the use of EigenPalm. However, we find a different story under a system and evaluation perspective. In this paper, we would like to introduce three issues that should be considered: the effects of templates from two different sessions, the effects of identical twins and the effects of unseen subjects. They are missing in the previous studies of EigenPalm

关键词： Principal component analysis Biometrics Feature extraction Testing Discrete transforms Karhunen-Loeve transforms Databases pattern analysis machine intelligence pattern matching

来源：评论

学校读者我要写书评

暂无评论

Increasing Object Recognition Rate using Reinforced Segmentation

Increasing Object Recognition Rate using Reinforced Segmenta...

引用

IEEE International Conference on Image Processing

作者： Farhang Sahba Hamid R. Tizhoosh Magdy M.A. Salama Systems Design Engineering University of Waterloo Waterloo ONT Canada Electrical and Computer Engineering Pattern Analysis and Machine Intelligence Laboratory Waterloo ONT Canada

In this paper a new approach to object extraction and recognition based on reinforcement learning is presented. We use this novel idea as a method to optimally segment the image and increase the recognition rate. The ... 详细信息

关键词： Object recognition Learning Image segmentation Data mining Design engineering pattern analysis machine intelligence Laboratories Image recognition Object detection

来源：评论

学校读者我要写书评

暂无评论

A Reinforcement Learning Framework for Medical Image Segmentation

A Reinforcement Learning Framework for Medical Image Segment...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： F. Sahba H.R. Tizhoosh M.M.A. Salama Pattern Analysis and Machine Intelligence Laboratory Department of System Design Engineering University of Waterloo Waterloo ONT Canada Department of Electrical and Computer Engineering University of Waterloo Waterloo ONT Canada

This paper introduces a new method to medical image segmentation using a reinforcement learning scheme. We use this novel idea as an effective way to optimally find the appropriate local thresholding and structuring element values and segment the prostate in ultrasound images. Reinforcement learning agent uses an ultrasound image and its manually segmented version and takes some actions (i.e., different thresholding and structuring element values) to change the environment (the quality of segmented image). The agent is provided with a scalar reinforcement signal determined objectively. The agent uses these objective reward/punishment to explore/exploit the solution space. The values obtained using this way can be used as valuable knowledge to fill a Q-matrix. The reinforcement learning agent can use this knowledge for similar ultrasound images as well. The results demonstrate high potential for applying reinforcement learning in the field of medical image segmentation.

关键词： Learning Biomedical imaging Image segmentation Ultrasonic imaging Medical diagnostic imaging pattern analysis machine intelligence Laboratories System analysis and design Design engineering

来源：评论

学校读者我要写书评

暂无评论

Cooperation: Concepts and General Typology

Cooperation: Concepts and General Typology

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Alaa M. Khamis Mohamed S. Kamel Miguel A. Salichs Pattern Analysis and Machine Intelligence (PAMI) Laboratory University of Waterloo Canada RoboticsLab Department of Systems Engineering and Automation Carlos III Technical University of Madrid Spain PAMI Laboratory Electrical and Computer Engineering Department University of Waterloo Canada

Life on this planet is full of astonishing examples of cooperation. Individual species depend upon one another for sustenance, often forming surprising alliances to achieve a common goal: continuance of the species. The majority of living things also display amazing altruism in order to protect and provide the best care for their offspring, incomparable to any form of sacrifice shown by human beings. Studying the cooperation patterns between living things and their intelligent behaviors has been source of inspiration for many new algorithms, theories and systems. This paper addresses the concept of cooperation and why it is important. It highlights the available biologically-inspired models and algorithms, and their potential applications. The paper also presents a general typology of cooperation patterns, which can help to understand how systems could work cooperatively in an intelligent manner.

关键词： Intelligent systems Biological system modeling Intelligent robots Artificial intelligence Cybernetics Planets Displays Protection Humans Multiagent systems

来源：评论

学校读者我要写书评

暂无评论

Search Space analysis of Recurrent Spiking and Continuous-time Neural Networks

Search Space Analysis of Recurrent Spiking and Continuous-ti...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： M. Ventresca B. Ombuki Systems Design Engineering and member of the Pattern Analysis and Machine Intelligence Laboratory University of Waterloo Waterloo ONT Canada Department of Computing and Information Science University of Guelph Guelph ONT Canada Computer Science Department Brock University Saint Catharines ONT Canada

The problem of designing recurrent continuous-time and spiking neural networks is NP-Hard. A common practice is to utilize stochastic searches, such as evolutionary algorithms, to automatically construct acceptable networks. The outcome of the stochastic search is related to its ability to navigate the search space of neural networks and discover those of high quality. In this paper we investigate the search space associated with designing the above recurrent neural networks in order to differentiate which network should be easier to automatically design via a stochastic search. Our investigation utilizes two popular dynamic systems problems; (1) the Henon map and (2) the inverted pendulum as a benchmark.

关键词： Neural networks Recurrent neural networks Stochastic processes Chaotic communication Neurons Biological system modeling Evolutionary computation Navigation Helium Visualization

来源：评论

学校读者我要写书评

暂无评论

Data partitioning evaluation measures for classifier ensembles

Data partitioning evaluation measures for classifier ensembl...

引用

6th International Workshop on Multiple Classifier Systems, MCS 2005

作者： Dara, Rozita A. Makrehchi, Masoud Kamel, Mohamed S. Pattern Analysis and Machine Intelligence Laboratory University of Waterloo Waterloo Ont. N2L-3G1 Canada

Training data modification has shown to be a successful technique for the design of classifier ensemble. Current study is concerned with the analysis of different types of training set distribution and their impact on the generalization capability of multiple classifier systems. To provide a comparative study, several probabilistic measures have been proposed to assess data partitions with different characteristics and distributions. Based on these measures, a large number of disjoint training partitions were generated and used to construct classifier ensembles. Empirical assessment of the resulted ensembles and their performances have provided insights into the selection of appropriate evaluation measures as well as construction of efficient population of partitions. © Springer-Verlag Berlin Heidelberg 2005.

关键词： Data processing

来源：评论

学校读者我要写书评

暂无评论

Texture classification using hierarchical linear discriminant space

Texture classification using hierarchical linear discriminan...

引用

作者： Kang, Yousun Morooka, Ken'ichi Nagahashi, Hiroshi Imaging Science and Engineering Laboratory Tokyo Institute of Technology Yokohama-shi 226-8503 Japan Imaging Science and Engineering Laboratory Tokyo Institute of Technology Japan IEEE Pattern Analysis and Machine Intelligence Society IEEE Robotics and Automation Society Information Processing Society of Japan Japan Institute of Electrical Engineers of Japan Japan

As a representative of the linear discriminant analysis, the Fisher method is most widely used in practice and it is very effective in two-class classification. However, when it is expanded to a multi-class classification problem, the precision of its discrimination may become worse. A main reason is an occurrence of overlapped distributions on the discriminant space built by Fisher criterion. In order to take such overlaps among classes into consideration, our approach builds a new discriminant space by hierarchically classifying the overlapped classes. In this paper, we propose a new hierarchical discriminant analysis for texture classification. We divide the discriminant space into subspaces by recursively grouping the overlapped classes. In the experiment, texture images from many classes are classified based on the proposed method. We show the outstanding result compared with the conventional Fisher method. Copyright © 2005 The Institute of Electronics, Information and Communication Engineers.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Automatic image registration using virtual circles

引用

International Journal of Image and Graphics 2004年第2期4卷 281-299页

作者： Alhichri, Haikel S. Kamel, Mohamed Pattern Analysis and Machine Intelligence Laboratory Systems Design Engineering University of Waterloo 200 University Ave. West WaterlooONN2L3G1 Canada University of Waterloo Canada

The main contribution of this work is a novel set of image features called the virtual circles and their use in the registration of images under similarity transformations. A virtual circle is a circle with maximal radius encompassing a background area that does not contain edge points. It has many useful properties such as its radius, and its dominant edge direction for example, which can be utilized for efficient registration. Furthermore, virtual circles are frequent and can be extracted efficiently with the help of the distance transform from many types of images. We have tested the new virtual circles method in the registration of 66 pairs of images, half of which are printed labels and the other half are indoor scenes. Experimental results have shown that this method has a linear complexity in terms of the number of pixels. It is also highly automatic, because it has a small number of parameters, which almost never need to be changed throughout the experiments. © 2004 World Scientific Publishing Company.

关键词： Image registration

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：