检索结果-内蒙古大学图书馆

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Kun Gai Zhenwei Shi Changshui Zhang State Key Laboratory on Intelligent Technology and Systems Tsinghua National Laboratory for Information Science and Technology (TNList) Department of Automation Tsinghua University Beijing China Image Processing Center School of Astronautics Beihang University Beijing China

We consider the blind separation of source layers from superimposed mixtures thereof, involving unknown motions and unknown mixing coefficients of layers in each mixture. Previous blind separation approaches for such problems assume motions to be uniform translations, and hence are limited for real world applications. In this paper, we develop a sparse blind separation algorithm to estimate both parameterized motions and mixing coefficients. Then, a novel reconstruction approach is presented to recover all layers, by utilizing not only the mixing model but also the statistical properties of natural images. The whole method can handle more general motions than translations, including scalings, rotations and other transformations. In addition, the number of layers is automatically identified, and all layers can be recovered even in the under-determined case where mixtures are fewer than layers. The effectiveness of this technology is shown in the experiments on two simulated mixtures of four layers, real photos containing transparency and reflections, and real crossfade images from videos.

关键词： image reconstruction Motion estimation Optical reflection Cameras Laboratories Space technology Parameter estimation Videos Glass Layout

来源：评论

学校读者我要写书评

暂无评论

Solving multidimensional 0–1 knapsack problem by tissue P systems with cell division

Solving multidimensional 0–1 knapsack problem by tissue P s...

引用

International Conference on Bio-Inspired Computing: Theories and Applications, BICTA

作者： Juanjuan He Zhengke Miao Zheng Zhang Xiaolong Shi Key Laboratory of Image Processing and Intelligent Control Department of Control Science and Engineering Huazhong University of Science and Technology Wuhan Hubei China Department of Mathematics XuZhou Normal University of China Xuzhou China

Tissue P systems with cell division are biologically inspired theoretical models of distributed and parallel computing, which provide the possibility to solve computationally hard problems in polynomial time. In this paper, we present a semi-uniform solution to the multidimensional 0-1 knapsack problem by such kind of devices, which is linear in terms of the number of variables, the number of constraint inequalities, and all coefficients related with variables.

关键词： Multidimensional systems Biomembranes Biology computing Polynomials Biological tissues Cells (biology) Biological system modeling Helium image processing intelligent control

来源：评论

学校读者我要写书评

暂无评论

Deterministic algorithm for the reordering problem using tile assembly

Deterministic algorithm for the reordering problem using til...

引用

International Conference on Bio-Inspired Computing: Theories and Applications, BICTA

作者： Yufang Huang Jin Xu Zhen Cheng Zhihua Chen Xuncai Zhang Key Laboratory of Image Processing and Intelligent Control Department of Control Science and Engineering Huazhong University of Science and Technology Wuhan Hubei China School of Electronics Engineering and Computer Science Peking University Beijing China

Algorithmic self-assembly, a generalization of crystal growth, has been proposed as a mechanism for the bottom-up fabrication of autonomous DNA computation. In theory, growth can be programmed by designing a set of molecular tiles with binding interactions that enforce assembly rules. There are many interesting applications of the reordering problem in Mathematics, as well as Computer Sciences. It is a useful primitive operation for computation and construction in the field of science and engineering. It is worth exploring more efficient approach to solve this problem. In this paper, we provide a description of a novel method for the reordering problem by use of the programmable tile assembly model. We propose the thought of block assembly model which takes full advantage of the huge parallelism inherent in the tile assembly. On the basis of the structural property, we delicately devise a rule to produce a long reporter strand which can connect all the inputs of the given problem with the final results. It is proved that this method can be extended to any reordering problem with arbitrary size in theory. The great advantage of our schema is that it only needs a constant number of tile types and in time linear with the size of the input problem to solve any reordering problem.

关键词： Tiles Assembly Self-assembly DNA computing Molecular computing Fabrication Logic Biology computing Laboratories intelligent control

来源：评论

学校读者我要写书评

暂无评论

Effects of Epidural Spinal Cord Stimulation and Treadmill Training on Locomotion Function and Ultrastructure of Spinal Cord Anterior Horn after Moderate Spinal Cord Injury in Rats

引用

中国康复医学杂志 2009年第6期24卷 485-488页

作者： WANG Yizhao HUANG Xiaolin XU Jiang XU Tao FANG Zhengyu XU Qi TU Xikai YANG Peipei Department of Rehabilitation Medicine Tongji Hospital Tongji Medical College Huazhong University of Science and Technology Wuhan 430030 China Key Laboratory of Image Processing and Intelligent Control Department of Control Science and Technology Huazhong University of Science and Technology Wuhan 430000 China

Objective:To investigate the effects of epidural spinal cord stimulation(ESCS) and treadmill training on the locomotion function and ultrastructure of spinal cord anterior horn after moderate spinal cord injury in ***:Nine adult female Sprague-Dawley rats were randomly distributed into three groups:①spinal cord injury group(SI,n=3).②spinal cord injury plus ESCS group(SE,n=3).③spinal cord injury plus treadmill training group(TT,n=3).All rats received a moderate spinal cord injury *** weeks after surgery,rats in SE group received an electrode implantation procedure,with the electrode field covering spinal cord segments *** weeks after electrode implantation,rats received subthreshold ESCS for 30 min/*** in TT group received 4cm/s treadmill training for 30min/*** in SI group received no intervention,as a control *** procedures in these three groups lasted four *** open field Basso,Beattie and Bresnahan(BBB) scale was used before and after intervention to evaluate rats' hindlimb motor ***:After four weeks intervention,rats in TT group improved their open field locomotion scores to *** contrast,no significant improvement was observed in groups SI and *** morphology of synapses and neurons were similar regardless of whether rats had undergone ESCS,treadmill training or ***:ESCS alone was not sufficient to improve the walking ability of spinal cord injured *** or treadmill training alone might not contribute to the changes of ultrastructure in anterior horn of spinal cord that underlie the recovery of walking *** research is needed to understand the contributions of combination of ESCS and treadmill training to the rehabilitation of spinal cord injured rats.

关键词：脊髓损伤神经元治疗方法跑步训练

来源：评论

学校读者我要写书评

暂无评论

Multisensor image adaptive fusion based on nonsubsampled contourlet

引用

Jisuanji Xuebao/Chinese Journal of Computers 2009年第11期32卷 2227-2238页

作者： Chang, Xia Jiao, Li-Cheng Jia, Jian-Hua Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China Institute of Intelligent Information Processing Xidian University Xi'an 710071 China School of Information Engineering Jingdezhen Ceramic Institute Jingdezhen Jiangxi 333002 China

An adaptive fusion method of multisensor images based on nonsubsampled contourlet transform is proposed in this paper, which can select the fusion weights of the low-frequency coefficients adaptively via golden section algorithm. The nonsubsampled contourlet transform is a flexible multi-scale, multi-direction and shift-invariant image decomposition, which is suitable for representing images bearing abundant detail and directional information. This is employed for fusing the directional high-frequency coefficients. For the directional high-frequency coefficients, the higher adding level of the directional subbands is used to select the better coefficient for fusion. The nonsubsampled contourlet transform can also avoids introducing ringing artifacts to fused images compared to ordinary method. Experimental results show that the proposed method achieves better fusion efficiency compared to image fusion methods based on Laplacian pyramid transform, wavelet transform, stationary wavelet transform and contourlet transform respectively.

关键词： Contourlet transform

来源：评论

学校读者我要写书评

暂无评论

Micro-assembly of micro parts using uncalibrated microscopes visual servoing method

引用

Information Technology Journal 2008年第3期7卷 497-503页

作者： Xiangjin, Zeng Xinhan, Huang Min, Wang Key Laboratory of Image Processing and Intelligent Control Department of Control Science and Engineering HUST Wuhan 430074 China

In micromanipulation, the microscope vision servoing can achieve a high performance. In order to avoid the complicated calibration of intrinsic parameter of camera, We apply an improved broyden's method to estimate the image jacobian matrix on line, which employs Chebyshev polynomial to construct a cost function to approximate the optimization value, obtaining a fast convergence for online estimation. Using the estimated jacobian matrix, a PD visual controller is used to make features converge to desired values with satisfactory dynamic performance. The experiments of micro-assembly of micro parts m microscopes confirm that the proposed method is effective and feasible. © 2008 Asian Network for Scientific Information.

关键词： Chebyshev polynomials

来源：评论

学校读者我要写书评

暂无评论

Research of invariant moments and improved support vector machine in micro-targets identification

引用

Journal of Applied Sciences 2008年第21期8卷 3969-3974页

作者： Zeng, Xiangjin Huang, Xinhan Wang, Min Key Laboratory of Image Processing and Intelligent Control Department of Control Science and Engineering Huazhong University of Science and Technology Wuhan 430074 China

In order to identify multi micro objects, an improved support vector machine algorithm is present, which employs invariant moments based edge extraction to obtain feature attribute and then presents a heuristic attribute reduction algorithm based on rough set's discernibility matrix to obtain attribute reduction, with using support vector machine to identify and classify the targets. According to the feature attribute, the effectiveness of identifying multi micro objects using support vector machine is compared with the proposed improved support vector machine classification method. The experiment results under micro vision environment show that the proposed improved support vector machine classification method can meet the system application requirement, with the resolution is 95%. © 2008 Asian Network for Scientific Information.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Artificial immune network clustering algorithm based on support vector domain description

引用

Journal of Computational Information Systems 2008年第4期4卷 1483-1488页

作者： Huang, Wenlong Jiao, Licheng Jia, Jian Key Laboratory of Intelligent Perception and Image Understanding Institute of Intelligent Information Processing Xidian University Xi'an 710071 China Troops No.95948 of PLA Lanzhou 732750 China

This paper aims at the combination of the artificial immune network and the support vector domain description for clustering. A new artificial immune antibody network is proposed. In the network, the antibody neighborhood is represented as a support vector hypersphere, and an adaptive learning coefficient is presented. The input data set is firstly divided into subsets by antibodies, then each subset is mapped into a hypersphere respectively in a high dimensional feature space by support vector domain description. Finally the clustering results of the local support vector hyperspheres are combined to yield a global clustering solution by the minimal spanning tree, which need not a predefined number of clustering. The experimental results with several data sets illustrate the effectiveness of the proposed algorithm.

关键词： Antibodies

来源：评论

学校读者我要写书评

暂无评论

Neutrosophic combination rules based on dempster-shafer theory and Dezert-Smarandache theory

引用

Information Technology Journal 2008年第7期7卷 1023-1029页

作者： Gao, Jian Huang, Xinhan Wang, Min Li, Xinde Key Laboratory of Ministry of Education for Image Processing and Intelligent Control Department of CSE HUST Wuhan 430074 China School of Automation Southeast University Nanjing 210096 China

Several neutrosophic combination rules based on the Dempster-Shafer theory (DST) and Dezert-Smarandache theory (DSmT) are presented in this study. The new information fusing approaches proposed the neutrosophic belief assignment to represent the evidences and connect the DST and DSmT with neutrosophic theory. Neutrosophic theory used the components truth, indeterminacy and falsity to represent any idea, which provides a better approach to express the real world. The DST-based and DSmT-based combination rules can fuse information more effectively. The new combination rules utilized the advantages of DST, DSmT and neutrosophic theory. They are more adapted to describing the human mind and helping to make correct decisions. To fuse the information expressed in natural language, the qualitative neutrosophic combination rules of information have been proposed in this study too. Some application examples have been given to support the proposed combination rules. Compared with the original DST-based and DSmT-based combination rules, the neutrosophic combination rules can provide more useful information and have wider application field. © 2008 Asian Network for Scientific Information.

关键词： Information fusion

来源：评论

学校读者我要写书评

暂无评论

Multiobjective optimization using an immunodominance and clonal selection inspired algorithm

引用

Science in China(Series F) 2008年第8期51卷 1064-1082页

作者： GONG MaoGuo JIAO LiCheng MA WenPing DU HaiFeng Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China Institute of Intelligent Information Processing Xidian University Xi'an 710071 China School of Public and Administration Xi'an Jiaotong University Xi'an 710049 China

Based on the mechanisms of immunodominance and clonal selection theory, we propose a new multiobjective optimization algorithm, immune dominance clonal multiobjective algorithm （IDCMA）. IDCMA is unique in that its fitness values of current dominated individuals are assigned as the values of a custom distance measure, termed as Ab-Ab affinity, between the dominated individuals and one of the nondominated individuals found so far. According to the values of Ab-Ab affinity, all dominated individuals （antibodies） are divided into two kinds, subdominant antibodies and cryptic antibodies. Moreover, local search only applies to the subdominant antibodies, while the cryptic antibodies are redundant and have no function during local search, but they can become subdominant （active） antibodies during the subsequent evolution. Furthermore, a new immune operation, clonal proliferation is provided to enhance local search. Using the clonal proliferation operation, IDCMA reproduces individuals and selects their improved maturated progenies after local search, so single individuals can exploit their surrounding space effectively and the newcomers yield a broader exploration of the search space. The performance comparison of IDCMA with MISA, NSGA-Ⅱ, SPEA, PAES, NSGA, VEGA, NPGA, and HLGA in solving six well-known multiobjective function optimization problems and nine multiobjective 0/1 knapsack problems shows that IDCMA has a good performance in converging to approximate Pareto-optimal fronts with a good distribution.

关键词： multiobjective optimization immunodominance clonal selection artificial immune systems evolutionaryalgorithms

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：