检索结果-内蒙古大学图书馆

22nd British National Conference on Databases, BNCOD 22

作者： Liang, Dong Yang, Jie Lu, Jin-Jun Chang, Yu-Chou Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai 200030 China

Weighted Color Co-occurrence Matrix (WCCM) is introduced as a novel feature for image retrieval. When indexing images with WCCM feature, the similarities of diagonal elements and non-diagonal elements are weighted respectively based on the Isolation Parameters of the query and prototype images. After weighting, the similarity of relevant matches to the query image is strengthened and the similarity of non-relevant matches to the query is weakened. The experiments show the effectiveness of WCCM based method. © Springer-Verlag Berlin Heidelberg 2005.

关键词： image retrieval

来源：评论

学校读者我要写书评

暂无评论

Face recognition using kernel principal component analysis and genetic algorithms 12

Face recognition using kernel principal component analysis a...

引用

12th IEEE Workshop on Neural Networks for Signal processing, NNSP 2002

作者： Zhang, Yankun Liu, Chongqing Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai200030 China

ISBN: (纸本)0780376161

Kernel principal component analysis (KPCA) as a powerful nonlinear feature extraction method has proven as a preprocessing step for classification algorithm. A face recognition approach based on KPCA and genetic algorithms (GAs) is proposed. By the use of the polynomial functions as a kernel function in KPCA, the high order relationships can be utilized and the nonlinear principal components can be obtained. After we obtain the nonlinear principal components, we use GAs to select the optimal feature set for classification. At the recognition stage, we employed linear support vector machines (SVM) as classifier for the recognition tasks. Two face databases were used to test our algorithm and higher recognition rates were obtained which show that our algorithm is effective. © 2002 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

image recognition Based on Combined Filters with Pseudoinverse Learning Algorithm 15th

Image Recognition Based on Combined Filters with Pseudoinver...

引用

15th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2019

作者： Deng, Xiaodan Sun, Xiaoxuan Guo, Ping Yin, Qian Image Processing and Pattern Recognition Laboratory School of Systems Science Beijing Normal University Beijing100875 China Image Processing and Pattern Recognition Laboratory College of Information Science and Technology Beijing Normal University Beijing China

ISBN: (纸本)9783030198220

Deep convolution neural network (CNN) is one of the most popular Deep neural networks (DNN). It has won state-of-the-art performance in many computer vision tasks. The most used method to train DNN is Gradient descent-based algorithm such as Backpropagation. However, backpropagation algorithm usually has the problem of gradient vanishing or gradient explosion, and it relies on repeated iteration to get the optimal result. Moreover, with the need to learn many convolutional kernels, the traditional convolutional layer is the main computational bottleneck of deep CNNs. Consequently, the current deep CNN is inefficient on computing resource and computing time. To solve these problems, we proposed a method which combines Gabor kernel, random kernel and pseudoinverse kernel, incorporating with pseudoinverse learning (PIL) algorithm to speed up DNN training processing. With the multiple fixed convolution kernels and pseudoinverse learning algorithm, it is simple and efficient to use the proposed method. The performance of the proposed model is tested on MNIST and CIFAR-10 datasets without using GPU. Experimental results show that our model is better than existing benchmark methods in speed, at the same time it has the comparative recognition accuracy. © 2019, IFIP International Federation for Information processing.

关键词： image recognition

来源：评论

学校读者我要写书评

暂无评论

The projective equation of a circle and its application in camera calibration

The projective equation of a circle and its application in c...

引用

作者： Zheng, Yinqiang Liu, Yuncai Image Processing and Pattern Recognition Institute Shanghai Jiao Tong University China

ISBN: (纸本)9781424421756

In this article, we present the projective equation of a circle in a perspective view, which naturally encodes such important geometric entities as the projected circle center, the vanishing point of the normal direction of the circle's supporting plane and the degenerate conic envelope spanned by the image of circular points (ICPs). Based on this projective equation, we propose an easy technique to calibrate the focal length and the extrinsic parameters of a camera merely by using one perspective view of two arbitrary coplanar circles. Unlike existing optimization algorithm, our method offers a closed form solution through simple matrix manipulation. Experimental results verify the correctness and efficiency of our proposed technique. © 2008 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

A simple but effective denoising algorithm in projection domain of CBCT 8th

A simple but effective denoising algorithm in projection dom...

引用

8th International Conference on image and Graphics, ICIG 2015

作者： Chang, Shaojie Zhang, Yanbo Bai, Ti Chen, Xi Xu, Qiong Mou, Xuanqin Institute of Image Processing and Pattern Recognition Xi’an Jiaotong University Xi’anShaanxi710049 China

ISBN: (纸本)9783319219776

There are growing concerns on the potential side effect of radiation, which could be decreased by lowering the tube current. However, this manner will lead to a degraded image since X-ray imaging is a quantum accumulation process. Great efforts have been devoted to alleviate this problem. In this paper, a simple Wiener filter was employed to denoise projection data in detector domain. And then an enhancement filter was exploited to strengthen small structures. As a consequence, this combination leaded to a reconstruction with good trade-off between noise and resolution. For the purpose of comparison, block-matching and 3D/4D denoising algorithm (BM3D/BM4D) were also adopted to denoise the projections. Experimental results demonstrated that the proposed algorithm could deliver a reconstruction with comparable quality as BM4D algorithm while better than that of BM3D denoising algorithm. Note that the propose algorithm has a much higher computation efficiency than BM3D/BM4D, and hence provides an insight into the clinical utility where real time is of high importance. © Springer International Publishing Switzerland 2015.

关键词： Noise abatement

来源：评论

学校读者我要写书评

暂无评论

A modified Hopfield neural network used in bilevel image restoration and reconstruction

A modified Hopfield neural network used in bilevel image res...

引用

1992 Singapore: Communications on the Move, ICCS/ISITA 1992

作者： Sun, Yi Yu, Song-Yu Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai200030 China

ISBN: (纸本)0780308034

Approach for bilevel image restoration and reconstruction using a modified Hopfield neural network is proposed in this paper. A group of threshold update (TU) algorithms with respective to simultaneous, partially simultaneous and sequential update modes is given. The network with the TU algorithms is asymptotically stable. The upper bounds of residuals of the convergent solutions are presented. Simulation results are shown. © 1992 IEEE.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

An eliminating highest error criterion in Hopfield neural network for bilevel image restoration

An eliminating highest error criterion in Hopfield neural ne...

引用

1992 Singapore: Communications on the Move, ICCS/ISITA 1992

作者： Sun, Yi Yu, Song-Yu Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai200030 China

ISBN: (纸本)0780308034

In Hopfield neural network approach for bilevel image restoration the autoconnections of the network generally weight heavier than interconnections. This characteristic exists in general degradation models of image restoration and can be utilized to guide the network to be updated more efficiently. Based on this a criterion for choice of the neurons to be updated at each step is proposed. A proposed algorithm using the criterion converges to more precise solutions with less updates as shown by simulation. © 1992 IEEE.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

image feature ratio model: similarity measures with both semantic and visual features in interactive image retrieval

Image feature ratio model: similarity measures with both sem...

引用

MIPPR 2005: image Analysis Techniques

作者： Tang, Hong Fang, Tao Shi, Peng-Fei Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai 200030 China

The feature contrast model (FCM), which is the simplest form of the matching function in Tversky's set-theoretic similarity, is a famous similarity model in psychological society. Although FCM can be employed to explain the similarity with both semantic and perceptual features, it is very difficult for FCM to measure natural image similarity with semantic features because of the requirement that all features must be binary and the complex mechanism that semantic features are transformed into binary features. The fuzzy feature contrast model (FFCM) is an extension of FCM, which replaces the complex feature representation mechanism with a proper fuzzy membership function. By this fuzzy logic, visual features, in the FFCM, can be represented as multidimensional points instead of expansible feature set and used to measure visual similarity between two images. Based on the analysis of the distinction between two feature structures (i.e., the expansible feature set and multidimensional vector), we propose a ratio model, which expresses similarity between two images as a ratio of the measures of semantic features set to that of multidimensional visual features. Experiments results, over real-world image collections, show that our model addresses the distinction between semantic and visual feature structures to some extension. In particular, our model is suit for the case that semantic features are implicitly obtained from interaction with users and the visual features are transparent for users, for example, the relevance feedback in interactive image retrieval.

关键词： image analysis

来源：评论

学校读者我要写书评

暂无评论

Dysfunction and recovery of the cortical connectome gradient and its association with gene expression profiles in methamphetamine and heroin use disorders

引用

Progress in Neuro-Psychopharmacology and Biological Psychiatry 2025年 139卷 111391页

作者： Du, Zhe Yang, Wenhan Wen, Xinwen Cai, Suping Liu, Jun Yuan, Kai School of Life Science and Technology Xidian University Shaanxi Xi'an 710126 China Department of Radiology Second Xiangya Hospital Central South University Changsha 410011 China Inner Mongolia Key Laboratory of Pattern Recognition and Intelligent Image Processing School of Information Engineering Inner Mongolia University of Science and Technology Inner Mongolia Baotou 014010 China Engineering Research Center of Molecular and Neuro Imaging Ministry of Education Shaanxi Xi'an China Ganzhou City Key Laboratory of Mental Health The Third People's Hospital of Ganzhou City Jiangxi Ganzhou 341000 China Xi'an Key Laboratory of Intelligent Sensing and Regulation of Trans-Scale Life Information School of Life Science and Technology Xidian University Shaanxi Xi'an 710126 China

Background: The hierarchy and segregation of community-based brain networks can be characterized by functional connectome gradient (FCG). Whether the cortical FCG was disrupted and could even be reversed after prolonged abstinence in substance use disorders (SUDs) remained unclear. Less is known about the underlying genetic basis. Methods: We utilized three independent datasets (n = 247) to investigate cortical FCG dysfunction and recovery after prolonged abstinence in methamphetamine use disorder (MUD) (n = 131), and validated in heroin use disorder (HUD) (n = 36). Furthermore, magnetic resonance spectroscopy (MRS) was employed to test the relationship between the glutamate in the ventral tegmental area (VTA) and cortical FCG. Postmortem gene expression was utilized to assess the transcriptional profiles related to cortical FCG alterations. Support vector regression (SVR) model based on the baseline cortical FCG was built to predict craving changes after long-term abstinence. Results: MUD and HUD individuals exhibited similar cortical FCG dysfunction and recovery at global and network levels, mainly in dorsal and ventral attentions network (DAN and VAN), frontoparietal network (FPN) and default mode network (DMN). The glutamate levels in VTA were correlated with the gradient distance between FPN and limbic network (LIM). The transcriptional profiles explained variance of the altered gradient pattern, with the most related genes enriched in synaptic signaling. Baseline cortical FCG significantly predicted craving changes after long-term abstinence. Conclusions: We provided novel insights into the understanding of SUD as treatable health conditions from cortical FCG changes, which could be considered as the potential biomarkers of craving changes after prolonged abstinence for SUDs. © 2025 Elsevier Inc.

关键词： Cortical functional connectome gradient Gene expression Glutamate Heroin use disorder Methamphetamine use disorder Support vector regression

来源：评论

学校读者我要写书评

暂无评论

Blurred image recognition based on complex moment invariants

Blurred image recognition based on complex moment invariants

引用

2004 International Conference on image processing, ICIP 2004

作者： Tianxu, Zhang Jin, Liu Institute for Pattern Recognition and Artifical Intelligence State Key Laboratory of Image Processing and Intelligent Control HuaZhong University of Science and Technology China Institute for Pattern Recognition and Artifical Intelligence HuaZhong University of Science and Technology China

ISBN: (纸本)0780385543

An important class of radiometric degradations we are faced with often in practice is image blurring. Special attention is paid to the recognition of the blurred image by moment invariant approach. Some important rules of complex moments for the blurred image are presented. Based on these rules, a useful subset of moment invariants is introduced, that are not affected by the blur, rotation, scale, and translation of the images. The experiments have shown that these invariants can be successfully used in recognition of the blurred image. ©2004 IEEE.

关键词： pattern recognition

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：