检索结果-内蒙古大学图书馆

13th International Conference on pattern recognition, ICPR 1996

作者： Leonardis, Aleš Bischof, Horst Department for Pattern Recognition and Image Processing Technical University Vienna Treitlstraße 3/1832 A -1040 Vienna Austria University of Ljubljana Faculty of Computer and Information Science Computer Vision Laboratory Ljubljana Slovenia

ISBN: (纸本)081867282X

We propose an extension of RBF networks which includes a mechanism for optimizing the complexity of the network. The approach involves two procedures: adaptation (training) and selection. The first procedure adaptively changes the locations and the width of the centers of the basis functions and trains the linear weights. The selection procedure performs the elimination of some of the basis functions using an objective function. By iteratively combining these two procedures we achieve a controlled way of training and modifying RBF networks, which balances accuracy, learning time, and complexity of the resulting network. © 1996 IEEE.

关键词： Radial basis function networks

来源：评论

学校读者我要写书评

暂无评论

JOINT BLURRED IMAGE RESTORATION WITH PARTIALLY KNOWN INFORMATION

JOINT BLURRED IMAGE RESTORATION WITH PARTIALLY KNOWN INFORMA...

引用

2006 International Conference on Machine Learning and Cybernetics(IEEE第五届机器学习与控制论坛)

作者： QING WU XING-CE WANG PING GUO Image Processing and Pattern Recognition Laboratory Beijing Normal University Beijing 100875 China

A new restoration method for joint blurred images with partially known information is proposed in this paper. The joint blur here is assumed to be motion blurs and defocus blur mixed together. Under the condition of two blur effects are supposed to be independent linear shift-invariant processes and motion blur parameter can be obtained with known information, a reduced update Kalman filter (RUKF) is used for degraded image restoration and the best defocus point spread function (PSF) parameter is determined based on the maximum entropy principle (MEP). Experimental results with real images show that the proposed approach works well.

关键词： PSF estimation Joint blurred image Reduced update Kalman filter Maximum entropy principle

来源：评论

学校读者我要写书评

暂无评论

Efficient Texture Classification using Short-time Fourier Transform with Spatial Pyramid Matching

Efficient Texture Classification using Short-time Fourier Tr...

引用

IEEE International Conference on Systems, Man, and Cybernetics

作者： Hassan Dawood Hussain Dawood Ping Guo Image Processing and Pattern Recognition Laboratory Beijing Normal University Beijing 100875 China

ISBN: (纸本)9781479906505

Texture feature extraction plays an important role in texture image classification. In this paper, we have proposed a texture feature extraction method by utilizing the Short-time Fourier Transform to provide local image information, and for the global geometric correspondence we have proposed to use Spatial Pyramid Matching in frequency domain named as Short-time Fourier Transform with Spatial Pyramid Matching (STFT-SPM). The experiments are conducted on standard benchmark datasets for texture classification like Brodatz and KTH-TIPS2-a, shows that STFT-SPM can achieve significant improvement compared to the Local Phase Quantization, Weber local Descriptor and local Binary pattern methods.

关键词： Spatial Pyramid Matching Texture classification Short-time Fourier Transform STFT Fourier Transform Pyramid texture image information textures standardized benchmark Feature extraction

来源：评论

学校读者我要写书评

暂无评论

MULTIPLE CLASSIFIERS BASED INCREMENTAL LEARNING ALGORITHM FOR LEARNING IN NONSTATIONARY ENVIRONMENTS

MULTIPLE CLASSIFIERS BASED INCREMENTAL LEARNING ALGORITHM FO...

引用

2007 International Conference on Machine Learning and Cybernetics(IEEE第六届机器学习与控制论国际会议)

作者： MICHAEL D.MUHLBAIER ROBI POLIKAR Signal Processing and Pattern Recognition Laboratory Rowan University Glassboro NJ 08028 USA

We describe an incremental learning algorithm designed to learn in challenging non-stationary environments, where the underlying data distribution that governs the classification problem changes at an unknown *** algorithm is based on a multiple classifier system that generates a new classifier every time a new dataset becomes available from the changing *** consider the particularly challenging form of this problem, where we assume that the previously generated data points are no longer available, even if some of those points may still be relevant in the new *** algorithm employs a strategic weighting mechanism to determine the error of each classifier on the current data distribution, and then combines the classifiers using a dynamically weighted majority *** describe the implementation details of algorithm, and track its performance as a function of the environment's rate of *** show that the algorithm is able to track the changing environment, even when the environment changes drastically over a short period of time.

关键词： Incremental learning Non-stationary learning Learn++ Ensemble systems Multiple classifier systems

来源：评论

学校读者我要写书评

暂无评论

Two-dimensional Spectral Image Calibration Based on Feed-forward Neural Network

Two-dimensional Spectral Image Calibration Based on Feed-for...

引用

International Joint Conference on Neural Networks

作者： Mingze Li Hasitieer Haerken Ping Guo Fuqing Duan Qian Yin Xin Zheng Image Processing and Pattern Recognition Laboratory Beijing Normal University Beijing 100875 China

ISBN: (纸本)9781509061839

In this paper, we present a novel method on image calibration, utilizing Total Least Square (TLS) method and Feed-forward Neural Network, to solve the aberration problem of LAMOST two-dimensional astronomical spectral images. In our method, training sample set is generated with domain knowledge, from which a number of discrete points are are extracted from spectral images with fiber tracing method, and output vectors are formed by the corresponding calibrated points, obtained by utilizing the TLS method. The Feed-forward Neural Network is trained to obtain the transformation matrix, casting about for the matching relationship between the input and output sets. We also perform comparative experiments on fiber tracing and spectrum extraction results between calibrated spectral images and uncalibrated spectral images, the results show an advantage of higher accuracy and precision by our proposed method.

关键词： Nonlinear distortion Calibration Neural networks Training Optical distortion Imaging

来源：评论

学校读者我要写书评

暂无评论

Multi-regularization parameters estimation for Gaussian mixture classifier based on MDL principle

Multi-regularization parameters estimation for Gaussian mixt...

引用

International Conference on Neural Computation Theory and Applications, NCTA 2011

作者： Zhou, Xiuling Guo, Ping Philip Chen, C.L. Laboratory of Image Processing and Pattern Recognition Beijing Normal University Beijing 100875 China Artificial Intelligence Institute Beijing City University Beijing China Faculty of Science and Technology University of Macau Macau China

ISBN: (纸本)9789898425843

Regularization is a solution to solve the problem of unstable estimation of covariance matrix with a small sample set in Gaussian classifier. And multi-regularization parameters estimation is more difficult than single parameter estimation. In this paper, KLIM-L covariance matrix estimation is derived theoretically based on MDL (minimum description length) principle for the small sample problem with high dimension. KLIM-L is a generalization of KLIM (Kullback-Leibler information measure) which considers the local difference in each dimension. Under the framework of MDL principle, multi-regularization parameters are selected by the criterion of minimization the KL divergence and estimated simply and directly by point estimation which is approximated by two-order Taylor expansion. It costs less computation time to estimate the multi-regularization parameters in KLIM-L than in RDA (regularized discriminant analysis) and in LOOC (leave-one-out covariance matrix estimate) where cross validation technique is adopted. And higher classification accuracy is achieved by the proposed KLIM-L estimator in experiment.

关键词： Parameter estimation

来源：评论

学校读者我要写书评

暂无评论

Shadow detection using regression tree fields with paired regions

引用

Journal of Computational Information Systems 2013年第11期9卷 4309-4317页

作者： Tao, Wei Zhou, Yue Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Shanghai 200240 China

In this paper, we try to deal with the problem of shadow detection from static images and video sequences. In instead to considering individual regions separately, we use relative illumination conditions between segmented regions and perform pair-wise classification based on such information. We use Regression Tree Fields to solve the labeling of shadow and non-shadow regions. And we use continuous value to describe the possibility of the shadow of the region. We evaluate our method on static images and a series of video sequences. © 2013 by Binary Information Press.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

A cross-domain person re-identification algorithm based on distribution-consistency and multi-label collaborative learning

引用

Multimedia Tools and Applications 2024年第38期83卷 85939-85962页

作者： Zhang, Baohua Hao, Chen Lv, Xiaoqi Gu, Yu Wang, Yueming Liu, Xin Ren, Yan Li, Jianjun School of Information Engineering Inner Mongolia University of Science and Technology Inner Mongolia Baotou014010 China School of Information Engineering Mongolia Industrial University Inner Mongolia Huhehaote010051 China Inner Mongolia Key Laboratory of Pattern Recognition and Intelligent Image Processing Inner Mongolia Baotou014010 China

To decrease domain shift in cross-domain person re-identification, existing methods generate pseudo labels for training models, however, the inherent distribution between source domain data and the hard quantization loss is ignored. Therefore, a cross-domain person re-identification method based on distribution consistency and multi-label collaborative learning is proposed. Firstly, a soft binary cross-entropy loss function is constructed to constrain the inter-sample relationship of cross-domain transformation, which can ensure the consistency of appearance features and sample distribution, and achieving feature cross-domain alignment. On this basis, in order to suppress the noise of hard pseudo labels, a multi-label collaborative learning network is constructed. The soft pseudo labels are generated by using the collaborative foreground features and global features to guide the network training, making the model adapt to the target domain. The experimental results show that the proposed method has better performance than that of recent representative methods. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Answer-supervised question reformulation for enhancing conversational machine comprehension 2

Answer-supervised question reformulation for enhancing conve...

引用

2nd Workshop on Machine Reading for Question Answering, MRQA@EMNLP 2019

作者： Li, Qian Su, Hui Niu, Cheng Wang, Daling Li, Zekang Feng, Shi Zhang, Yifei School of Computer Science and Engineering Northeastern University Shenyang China Pattern Recognition Center WeChat Ai Tencent Inc China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences

ISBN: (纸本)9781950737819

In conversational machine comprehension, it has become one of the research hotspots integrating conversational history information through question reformulation for obtaining better answers. However, the existing question reformulation models are trained only using supervised question labels annotated by annotators without considering any feedback information from answers. In this paper, we propose a novel Answer-Supervised Question Reformulation (ASQR) model for enhancing conversational machine comprehension with reinforcement learning technology. ASQR utilizes a pointer-copy-based question reformulation model as an agent, takes an action to predict the next word, and observes a reward for the whole sentence state after generating the end-of-sequence token. The experimental results on QuAC dataset prove that our ASQR model is more effective in conversational machine comprehension. Moreover, pretraining is essential in reinforcement learning models, so we provide a high-quality annotated dataset for question reformulation by sampling a part of QuAC dataset. © 2019 MRQA@EMNLP 2019 - Proceedings of the 2nd Workshop on Machine Reading for Question Answering. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

AMCF-Net: A Novel Adaptive Multi-Channel Fusion Network for Computer-Aided Diagnosis of Lung Nodules in Chest Computed Tomography

引用

IET Communications 2025年第1期19卷

作者： Nan Wang Yu Gu Lidong Yang Baohua Zhang Jing Wang Xiaoqi Lu Jianjun Li Dahua Yu Ying Zhao Xin Liu Siyuan Tang Qun He Inner Mongolia Key Laboratory of Pattern Recognition and Intelligent Image Processing School of Digital and Intelligent Industry Inner Mongolia University of Science and Technology Baotou China School of Information and Electronics Beijing Institute of Technology Beijing China College of Information Engineering Inner Mongolia University of Technology Hohhot China School of Computer Science and Technology Baotou Medical College Inner Mongolia University of Science and Technology Baotou China

Malignant lung nodules can significantly affect patients' normal lives and, in severe cases, threaten their survival. Owing to the heterogeneity of computed tomography scans and the varying sizes of nodules, physicians often face challenges in diagnosing this condition. Therefore, a novel adaptive multi-channel fusion network (AMCF-Net) is proposed for computer-aided diagnosis of lung nodules. First, a Multi-Channel Fusion Model module is designed, which divides the channels into two parts in specific proportions, effectively extracting multi-scale channel information while reducing network parameters. After the feature maps output at each layer of the AMCF-Net, a novel adaptive depth-wise separable convolution with a squeeze-and-excitation module is designed to adaptively integrate the feature maps of various stages of the AMCF-Net, ensuring that the key lesions of lung nodules are not lost during classification. Finally, a hybrid loss scheme based on an adaptive mixing ratio is proposed to solve the problem of an imbalanced number of positive and negative nodule samples in the dataset. The model achieved the following test results: an accuracy of 90.22%, a specificity of 98.19%, an F1-score of 86.57%, a sensitivity of 86.49%, and a G-mean of 87.72%. Compared with other advanced networks, AMCF-net delivers high-precision lung nodule classification with minimal inference cost. Related codes have been released at: https://***/GuYuIMUST/AMCF-net .

关键词： computer networks convolution health care image processing neural nets

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：