检索结果-内蒙古大学图书馆

Locality-constrained framework for face alignment

Frontiers of Computer Science 2019年第4期13卷 789-801页

作者： Jie ZHANG Xiaowei ZHAO Meina KAN Shiguang SHAN Xiujuan CHAI Xilin CHEN Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China University of Chinese Academy of Sciences Beijing 100049 China Alibaba Group Hangzhou 311121 China

Although the conventional active appearance model (AAM) has achieved some success for face alignment, it still suffers from the generalization problem when be applied to unseen subjects and images. To deal with the gem eralization problem of AAM, we first reformulate the original AAM as sparsity-regularized AAM, which can achieve more compact/better shape and appearance priors by selecting nearest neighbors as the bases of the shape and appearance model. To speed up the fitting procedure, the sparsity in sparsity?regularized AAM is approximated by using the locality (i.e., AT-nearest neighbor), and thus inducing the locality-constrained active appearance model (LC-AAM). The LC-AAM solves a constrained AAM-like fitting problem with the K-nearest neighbors as the bases of shape and appearance model. To alleviate the adverse influence of inaccurate AT-nearest neighbor results, the locality constraint is further embedded in the discriminative fitting method denoted as LC-DFM, which can find better K-nearest neighbor results by employing shape-indexed feature, and can also tolerate some inaccurate neighbors benefited from the regression model rather than the generative model in AAM. Extensive experiments on several datasets demonstrate that our methods outperform the state-of-the-arts in both detection accuracy and generalization ability.

关键词： locality-constrained AAM locality-constrained DFM face alignment sparsity-regularization

来源：评论

学校读者我要写书评

暂无评论

Dual form back propagation on the EM algorithm

Dual form back propagation on the EM algorithm

引用

2011 IEEE International Conference on Granular computing, GrC 2011

作者： Hu, Hong Shi, Zhongzhi Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Science Beijing 100190 China

ISBN: (纸本)9781457703713

Vladimir N. Vapnik. (1998) pointed out that maxlikelihood functions in EM algorithms are just a special risk function. Based on this opinion, a novel EM algorithm uses a risk function differ with maxlikelihood functions, in stead, a risk formula based on the least square method is used. The gradient descending approach should be used in such kind approaches. Such kind EM algorithms can estimate the parameters of a random model from both labeled and unlabeled samples, and are suitable for semi-supervised learning. © 2011 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Optimal multilevel thresholding based on molecular kinetic theory optimization algorithm and line intercept histogram

引用

Journal of Central South University 2016年第4期23卷 880-890页

作者：范朝冬任柯张英杰易灵芝 Key Laboratory of Intelligent Computing and Information Processing(Xiangtan University) Xiangtan 411105China Hunan Province Cooperative Innovation Center for Wind Power Equipment and Energy Conversion Xiangtan 411101China College of Information Science and Engineering Hunan UniversityChangsha 410082China

Among all segmentation techniques, Otsu thresholding method is widely used. Line intercept histogram based Otsu thresholding method(LIH Otsu method) can be more resistant to Gaussian noise, highly efficient in computing time, and can be easily extended to multilevel thresholding. But when images contain salt-and-pepper noise, LIH Otsu method performs poorly. An improved LIH Otsu method(ILIH Otsu method) is presented, which can be more resistant to Gaussian noise and salt-and-pepper noise. Moreover, it can be easily extended to multilevel thresholding. In order to improve the efficiency, the optimization algorithm based on the kinetic-molecular theory(KMTOA) is used to determine the optimal thresholds. The experimental results show that ILIH Otsu method has stronger anti-noise ability than two-dimensional Otsu thresholding method(2-D Otsu method), LIH Otsu method, K-means clustering algorithm and fuzzy clustering algorithm.

关键词： image segmentation multilevel thresholding Otsu thresholding method kinetic-molecular theory （KMTOA） line intercept histogram

来源：评论

学校读者我要写书评

暂无评论

A Gradient-Guided Evolutionary Approach to Training Deep Neural networks

引用

IEEE TRANSACTIONS ON NEURAL networkS AND LEARNING SYSTEMS 2022年第9期33卷 4861-4875页

作者： Yang, Shangshang Tian, Ye He, Cheng Zhang, Xingyi Tan, Kay Chen Jin, Yaochu Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Institutes of Physical Science and Information Technology Anhui University Hefei China Department of Computer Science and Engineering Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Southern University of Science and Technology Shenzhen China Department of Computing The Hong Kong Polytechnic University Hong Kong SAR Department of Computer Science University of Surrey Guildford U.K

It has been widely recognized that the efficient training of neural networks (NNs) is crucial to classification performance. While a series of gradient-based approaches have been extensively developed, they are criticized for the ease of trapping into local optima and sensitivity to hyperparameters. Due to the high robustness and wide applicability, evolutionary algorithms (EAs) have been regarded as a promising alternative for training NNs in recent years. However, EAs suffer from the curse of dimensionality and are inefficient in training deep NNs (DNNs). By inheriting the advantages of both the gradient-based approaches and EAs, this article proposes a gradient-guided evolutionary approach to train DNNs. The proposed approach suggests a novel genetic operator to optimize the weights in the search space, where the search direction is determined by the gradient of weights. Moreover, the network sparsity is considered in the proposed approach, which highly reduces the network complexity and alleviates overfitting. Experimental results on single-layer NNs, deep-layer NNs, recurrent NNs, and convolutional NNs (CNNs) demonstrate the effectiveness of the proposed approach. In short, this work not only introduces a novel approach for training DNNs but also enhances the performance of EAs in solving large-scale optimization problems.

关键词： Artificial neural networks Training Optimization Search problems Scalability Complexity theory Genetic algorithms Deep neural networks (DNNs) evolutionary algorithm (EA) genetic operator gradient descent sparsity

来源：评论

学校读者我要写书评

暂无评论

Detection of Impurity and Bubble Defects in Tire X-Ray Image Based on Improved Extremum Filter and Locally Adaptive-threshold Binaryzation

Detection of Impurity and Bubble Defects in Tire X-Ray Image...

引用

2018 International Conference on Security, Pattern Analysis, and Cybernetics, SPAC 2018

作者： Zheng, Xiunan Ding, Jianpei Pang, Zengzhi Li, Jinping Shandong Provincial Key Laboratory of Network Based Intelligent Computing China Shandong College University Key Laboratory of Information Processing and Cognitive Computing in 13th Five-year China School of Information Science and Engineering University of Jinan China

ISBN: (纸本)9781728105512

The manufacturing technology of all steel radial tire is complex. Some defects will inevitably appear in the tire due to the complex production process. Impurity and bubble are two typical kinds of defects in the tire. In this study, a unified detection of impurity and bubble defects in tire X-ray images is proposed by means of improved extremum filter and improved locally adaptive-threshold binaryzation. Firstly, the tire image is divided into cords and background by extremum filter. Secondly, an improved locally adaptive-threshold binaryzation is used to separate defects from the background. Finally, image denoising and marking are processed. In the experiment, we tested the proposed approach by using 280 tires with various types of defects from a tire factory. For the detection of clear and blur impurities and clear bubbles, the precision of our method can reach 97%, and the recall is 95.7%. It is to be noted that the proposed method can only be used to detect those two defects in sidewall and shoulder of the tire which we refer as the carcass. © 2018 IEEE.

关键词： Radial tires

来源：评论

学校读者我要写书评

暂无评论

Granular computing in the information transformation of patten recognition

Granular computing in the information transformation of patt...

引用

2007 IEEE International Conference on Granular computing, GrC 2007

作者： Hu, Hong Shi, Zhongzhi Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Science Beijing 100080 China

ISBN: (纸本)076953032X

In the past decade, many papers about granular computing(GrC) have been published, but the keypoints about granular computing(GrC) are still unclear. In this paper, we try to find the key points of GrC in the information transformation of the pattern recognition. The information similarity is the main point in the original insight of Granular computing (GrC) proposed by Zadeh(1997[1]). Many GrC researches are based on equivalence relation or more generally tolerance relation, equivalence relation or tolerance relation can be described by some distance functions and GrC can be geometrically defined in a framework of multiscale covering, at other hand, the information transformation in the pattern recognition can be abstracted as a topological transformation in a feature information space, so topological theory can be used to study GrC The key points of GrC are (1) there are two granular computing approaches to change a high dimensional complex distribution domain to a low dimensional and simple domain, (2)these two kind approaches can be used in turn if feature vector itself can be arranged in a granular way. © 2007 IEEE.

关键词： Granular computing

来源：评论

学校读者我要写书评

暂无评论

The possibility of using simple neuron models to design brain-like computers

The possibility of using simple neuron models to design brai...

引用

5th International Conference on Advances in Brain Inspired Cognitive Systems, BICS 2012

作者： Hu, Hong Shi, Zhongzhi Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Science Beijing 100190 China

ISBN: (纸本)9783642315602

IBM Research and five leading universities are partnering to create computing systems that are expected to simulate and emulate the brain's abilities. Although this project has achieved some successes, it meets great difficulties in the further research. The main difficulty is that it is almost impossible to analyze the dynamic character of neural networks in detail, when more than ten thousands neurons of complex nonlinear neural models are piled up. So it is nature to present such question: in order to simplify the design of brain-like computers, can we use simple neuron models to design brain-like computers or can we find a simplest neuron model which can simulate most neuron models with arbitrary precision? In this paper, we proved that almost all neural models found by neural scientists nowadays can be simulated by Hopfield neural networks. So it is possible to use simple neuron model to design Brain-like computers. © 2012 Springer-Verlag.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Variant quantifiers in L_(3)-valued first-order logic

引用

Frontiers of Computer Science 2021年第5期15卷 151-159页

作者： Wei LI Yuefei SUI State Key Laboratory of Software Development Environment Beihang UniversityBeijing 100083China Key Laboratory of Intelligent Information Processing Institute of Computing TechnologyChinese Academy of SciencesBeijing 100190China School of Computer Science and Technology University of Chinese Academy of SciencesBeijing 100049China

Traditional first-order logic has four definitions for quantifiers,which are defined by universal and existential *** L_(3)-valued(three-valued)first-order logic,there are eight kinds of definitions for quantifiers;and corresponding Gentzen deduction systems will be given and their soundness and completeness theorems will be proved.

关键词： L_(3)-valued(three-valued)first-order logic sequent quantifier soundness theorem completeness theorem

来源：评论

学校读者我要写书评

暂无评论

Monotonicity and nonmonotonicity in L3-valued propositional logic

引用

Frontiers of Computer Science 2022年第4期16卷 33-43页

作者： Wei Li Yuefei Sui State Key Laboratory of Software Development Environment Beihang UniversityBeijing100083China Key Laboratory of Intelligent Information Processing Institute of Computing TechnologyChinese Academy of SciencesBeijing100190China School of Computer Science and Technology University of Chinese Academy of SciencesBeijing100049China

A sequent is a pair (Γ, Δ), which is true under an assignment if either some formula in Γ is false, or some formula in Δ is true. In L_(3)-valued propositional logic, a multisequent is a triple Δ∣Θ∣Γ, which is true under an assignment if either some formula in Δ has truth-value t, or some formula in Θ has truth-value m, or some formula in Γ has truth-value f. There is a sound, complete and monotonic Gentzen deduction system G for sequents. Dually, there is a sound, complete and nonmonotonic Gentzen deduction system G′ for co-sequents Δ: Θ: Γ. By taking different quantifiers some or every, there are 8 kinds of definitions of validity of multisequent Δ∣Θ∣Γ and 8 kinds of definitions of validity of co-multisequent Δ: Θ: Γ, and correspondingly there are 8 sound and complete Gentzen deduction systems for sequents and 8 sound and complete Gentzen deduction systems for co-sequents. Correspondingly their monotonicity is discussed.

关键词： sequent mulisequent gentzen deduction system monotonicity nonmonotonicity

来源：评论

学校读者我要写书评

暂无评论

Identification of differential brain regions in MCI progression via clustering-evolutionary weighted SVM ensemble algorithm

引用

Frontiers of Computer Science 2021年第6期15卷 165-173页

作者： Xia-an BI Yiming XIE Hao WU Luyun XU Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal UniversityChangsha 410081China College of Information Science and Engineering Hunan Normal UniversityChangsha 410081China Business School of Hunan Normal University Changsha 410081China

Mild cognitive impairment(MCI)as the potential sign of serious cognitive decline could be divided into two stages,i.e.,late MCI(LMCI)and early MCI(EMCI).Although the different cognitive states in the MCI progression have been clinically defined,effective and accurate identification of differences in neuroimaging data between these stages still needs to be further *** this paper,a new method of clustering-evolutionary weighted support vector machine ensemble(CEWSVME)is presented to investigate the alterations from cognitively normal(CN)to EMCI to *** CEWSVME mainly includes two *** first step is to build multiple SVM classifiers by randomly selecting samples and *** second step is to introduce the idea of clustering evolution to eliminate inefficient and highly similar SVMs,thereby improving the final classification ***,we extracted the optimal features to detect the differential brain regions in MCI progression,and confirmed that these differential brain regions changed dynamically with the development of *** exactly,this study found that some brain regions only have durative effects on MCI progression,such as parahippocampal gyrus,posterior cingulate gyrus and amygdala,while the superior temporal gyrus and the middle temporal gyrus have periodic effects on the *** work contributes to understanding the pathogenesis of MCI and provide the guidance for its timely diagnosis.

关键词： machine learning MCI progression optimal feature extraction differential brain regions functional magnetic resonance imaging

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：