检索结果-内蒙古大学图书馆

computer Analysis of images and Patterns 1

丛书名： Lecture Notes in computer Science

1000年

作者： Pedro Real Daniel Diaz-Pernil Helena Molina-Abril Ainhoa Berciano Walter Kropatsch

ISBN: (数字)9783642236785

ISBN: (纸本)9783642236778

The two volume set LNCS 6854/6855 constitutes the refereed proceedings of the International Conference on computer Analysis of images and Patterns, CAIP 2011, which took place in Seville, Spain, August 29-31, 2011. The 138 papers presented together with 2 invited talks were carefully reviewed and selected from 286 submissions. The papers are organized in topical section on: motion analysis, image and shape models, segmentation and grouping, shape recovery, kernel methods, medical imaging, structural pattern recognition, Biometrics, image and video processing, calibration; and tracking and stereo vision.

关键词： Pattern Recognition Biometrics Data Mining and Knowledge Discovery computer Imaging, Vision, Pattern Recognition and graphics Natural Language processing (NLP) Artificial Intelligence

来源：评论

学校读者我要写书评

暂无评论

Partial Differential Equations is All You Need for Generating Neural Architectures - A Theory for Physical Artificial Intelligence Systems

arXiv

引用

arXiv 2021年

作者： Guo, Ping Huang, Kaizhu Xu, Zenglin Image Processing & Pattern Recognition Lab. Beijing Normal University Beijing100875 China Data Science Research Center Duke Kunshan University Jiangsu Kunshan215316 China School of Computer Science and Technology Harbin Institute of Technology at ShenZhen Peng Cheng National Lab Guangdong Shenzhen510855 China

In this work, we generalize the reaction-diffusion equation in statistical physics, Schrödinger equation in quantum mechanics, and Helmholtz equation in paraxial optics into the neural partial differential equations (NPDE), which can be considered as the fundamental equations in the field of artificial intelligence research. We take the finite difference method to discretize NPDEs for finding the numerical solution. Moreover, the basic building blocks of deep neural network architectures, including multi-layer perceptron, convolutional neural networks, and recurrent neural networks, are generated. The learning strategies, such as Adaptive moment estimation, L-BFGS, pseudoinverse learning algorithms, and partial differential equation constrained optimization, are also developed. This work is of significance in that it presents a clear view of interpretable deep neural networks physically, enables high possibility to be applied to analog computing device design, and paves the road to physical artificial intelligence. © 2021, CC BY-NC-SA.

关键词： Schrodinger equation

来源：评论

学校读者我要写书评

暂无评论

Neuron segmentation using 3D wavelet integrated encoder-decoder network

arXiv

引用

arXiv 2021年

作者： Li, Qiufu Shen, Linlin Computer Vision Institute College of Computer Science and Software Engineering Shen zhen University Shenzhen518060 China AI Research Center for Medical Image Analysis and Diagnosis Shenzhen University Shenzhen518060 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China Marshall Laboratory of Biomedical Engineering Shenzhen University Shenzhen518060 China

Motivation: 3D neuron segmentation is a key step for the neuron digital reconstruction, which is essential for exploring brain circuits and understanding brain functions. However, the fine line-shaped nerve fibers of neuron could spread in a large region, which brings great computational cost to the neuron segmentation. Meanwhile, the strong noises and disconnected nerve fibers bring great challenges to the task. Results: In this paper, we propose a 3D wavelet and deep learning based 3D neuron segmentation method. The neuronal image is first partitioned into neuronal cubes to simplify the segmentation task. Then, we design 3D WaveUNet, the first 3D wavelet integrated encoder-decoder network, to segment the nerve fibers in the cubes;the wavelets could assist the deep networks in suppressing data noises and connecting the broken fibers. We also produce a Neuronal Cube Dataset (NeuCuDa) using the biggest available annotated neuronal image dataset, BigNeuron, to train 3D WaveUNet. Finally, the nerve fibers segmented in cubes are assembled to generate the complete neuron, which is digitally reconstructed using an available automatic tracing algorithm. The experimental results show that our neuron segmentation method could completely extract the target neuron in noisy neuronal images. The integrated 3D wavelets can efficiently improve the performance of 3D neuron segmentation and reconstruction. © 2021, CC BY.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

GazeGAN: A robust generative adversarial saliency model based on invariance analysis of human gaze during scene free viewing

arXiv

引用

arXiv 2019年

作者： Che, Zhaohui Borji, Ali Zhai, Guangtao Min, Xiongkuo Guo, Guodong Le Callet, Patrick Institute of Image Communication and Network Engineering Shanghai Key Laboratory of Digital Media Processing and Transmissions Shanghai Jiao Tong University Shanghai200240 China MarkableAI United States Institute of Deep Learning Baidu Research Department of Computer Science and Electrical Engineering West Virginia University MorgantownWV United States Equipe Image Perception et Interaction Laboratoire des Sciences du Numérique de Nantes Université de Nantes France

—Data size is the bottleneck for developing deep saliency models, because collecting eye-movement data is very time-consuming and expensive. Most of current studies on human attention and saliency modeling have used high-quality stereotype stimuli. In real world, however, captured images undergo various types of transformations. Can we use these transformations to augment existing saliency datasets? Here, we first create a novel saliency dataset including fixations of 10 observers over 1900 images degraded by 19 types of transformations. Second, by analyzing eye movements, we find that observers look at different locations over transformed versus original images. Third, we utilize the new data over transformed images, called data augmentation transformation (DAT), to train deep saliency models. We find that label-preserving DATs with negligible impact on human gaze boost saliency prediction, whereas some other DATs that severely impact human gaze degrade the performance. These label-preserving valid augmentation transformations provide a solution to enlarge existing saliency datasets. Finally, we introduce a novel saliency model based on generative adversarial network (dubbed GazeGAN). A modified U-Net is proposed as the generator of the GazeGAN, which combines classic "skip connections" with a novel "center-surround connection (CSC)", in order to leverage multi-level features. We also propose a histogram loss based on Alternative Chi-Square Distance (ACS HistLoss) to refine the saliency map in terms of luminance distribution. Extensive experiments and comparisons over 3 datasets indicate that GazeGAN achieves the best performance in terms of popular saliency evaluation metrics, and is more robust to various perturbations. We also provide a comprehensive quantitative comparison of 22 state-of-the-art saliency models on distorted images, which contributes a robustness benchmark for saliency community. Our code and data are available at: https://***/CZHQuality/

关键词： Luminance

来源：评论

学校读者我要写书评

暂无评论

Computational fluid flow simulation on body fitted mesh geometry with IBM cell broadband engine architecture

Computational fluid flow simulation on body fitted mesh geom...

引用

European Conference on Circuit Theory and Design, ECCTD

作者： Zoltan Nagy Andras Kiss Sandor Kocsardi Arpad Csik Computer and Automation Research Institute Hungarian Academy of Sciences Changzhou China Department Information Technology Pázmány Péter Catholic University Changzhou China Department Image Processing and Neurocomputing University of Pannonia Veszprem Hungary Department of Mathematics and Computational Sciences Széchenyi István University Gyor Hungary

The solutions of partial differential equations (PDEs) play a key role in today's real world simulations. Computational Fluid Dynamics (CFD) is an important part of this area, which involves the problem of gas or fluid flow over different obstacles, e.g., air flow around vehicles, buildings, or the flow of water in the oceans. In engineering applications the temporal evolution of non-ideal, compressible fluids is quite often modeled by the system of Navier-Stokes equations. They are a coupled set of nonlinear hyperbolic partial differential equations and form a relatively simple, yet efficient model of compressible fluid dynamics. In the paper the implementation of a CFD on Body Fitted Mesh geometry on the Cell Broadband Engine is described. An arbitrary surface can be more easily simulated on body fitted mesh than on rectangular computation domain.

关键词： Fluid flow Computational modeling Solid modeling Computational geometry Engines computer architecture Computational fluid dynamics Partial differential equations Marine vehicles Buildings

来源：评论

学校读者我要写书评

暂无评论

PARTICLE SWARM OPTIMIZATION（PSO）OF POWER ALLOCATION IN COGNITIVE RADIO SYSTEMS WITH INTERFERENCE CONSTRAINTS

PARTICLE SWARM OPTIMIZATION（PSO）OF POWER ALLOCATION IN COG...

引用

2011 4th IEEE International Conference on Broadband Network and Multimedia Technology

作者： Saeed Motiian Mohammad Aghababaie Hamid Soltanian-Zadeh Control and Intelligent Processing Center of Excellence School of Electrical and Computer Engineering Colleague of EngineeringUniversity of TehranTehran 14399-57131Iran School of Cognitive Sciences Institute for Research in Fundamental Sciences(IPM)Tehran 19548-56316 Iran Image Analysis Laboratory Radiology DepartmentHenry Ford HospitalDetroitMichigan 48202USA

Cognitive radio is used for enhancement of spectrum *** many works have been accomplished on the power allocation of cognitive radio,limited efforts have considered evolutionary *** this paper,we study this problem in the cognitive radio networks where interference constraints are defined for protection of quality of service（QoS）for both primary and secondary *** defined as functions of the signal-to-interference-plus-noise ratio（SINR） are matched for each secondary user which meets Nash’s *** general,the region of utilities that meets the constraints is *** is possible to make simplifications,generate a convex region,and then use common convex optimization approaches to obtain a ***,Particle Swarm Optimization（PSO）does not need such simplifications and thus its results are superior to those of the convex optimization *** is an evolutionary algorithm based on social intelligence,utilized in many optimization *** is a global optimizations algorithm that does not require the objective function be differentiable as required in classic optimization methods.

关键词： Cognitive radio Power allocation Particle Swarm Optimization（PSO）.

来源：评论

学校读者我要写书评

暂无评论

Fingertip interactive tracking registration method for AR assembly system

引用

Advances in Computational Intelligence 2022年第2期2卷 1-26页

作者： Jiu, Yong Jianguo, Wei Yangping, Wang Jianwu, Dang Xiaomei, Lei The National Virtual Simulation Experiment Teaching Center of Railway Traffic Information and Control Lanzhou Jiaotong University Lanzhou China College of Intelligence and Computing Tianjin University Tianjin China The National Experimental Teaching Demonstration Center of Computer Science and Technology Lanzhou Jiaotong University Lanzhou China The School of Electronic and Information Engineering Lanzhou Jiaotong University Lanzhou China Gansu Provincial Engineering Research Center for Artificial Intelligence and Graphics and Image Processing Lanzhou China Gansu Meteorological Service Meteorological Information and Technological Supporting Center Lanzhou China

Aiming at the problems of single input mode and lack of naturalness in the assembly process of existing AR systems, a tracking registration method of mobile AR assembly system is proposed based on multi-quantity and multi-degree of freedom natural fingertip interaction. Firstly, the real-time and stable tracking of hand area in complex environment is realized based on the hand region tracking; secondly, the fingertip detection and recognition based on K-COS and parallel vector is used to improve the precision and stability of fingertip recognition; thirdly, the special movement track of fingertip is recognized based on improved DTW algorithm, which has strong compatibility and feature gradient transformation for complex fingertip trajectory recognition; finally, through the real-time transformation of projection relationship between fingertip and virtual object, the interaction between fingertip and virtual object is made more natural and realistic. The experimental results show that in the complex environment of background, illumination, scale and rotation, the precision of fingertip detection and recognition is about 93%, and the precision of fingertip motion template matching is about 91%. The translation error of the registration method based on visual feature recognition is reduced by about 100pix compared with fingertip tracking registration method, and the efficiency of mobile AR-guided assembly method is improved by about 24.77% compared with the traditional manual assisted assembly method. These data verifies the strong interaction and practicability of the fingertips based on the user's multi-quantity and multi-degree of freedom features in the process of mobile AR guided assembly.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Impact of anthropogenic disturbance on a mangrove forest assessed by a id cellular automaton model using lotka-volterra-type competition

引用

International Journal of Design and Nature and Ecodynamics 2008年第4期3卷 296-320页

作者： Obade, P.T. Koedam, N. Soetaert, K. Neukermans, G. Bogaert, J. Nyssen, E. Van Nedervelde, F. Berger, U. Dahdouh-Guebas, F. Belgium Kenya Marine and Fisheries Research Institute Kenya Netherlands Belgium Department of Electronics and Informatics Image Processing and Machine Vision Group VUB Belgium Département de Biologie des Organismes Faculté des Sciences Complexité et Dynamique des Systèmes Tropicaux Belgium Department of Forest Biometry and Systems Analysis Institute of Forest Growth and Forest Computer Sciences Technische Universität Dresden Germany

Mangrove forests are ecologically and economically important and frequently dominating protected coastal areas in the tropics and subtropics at suitable intertidal zones and are often subjected to disturbances that disrupt the structure of an ecosystem, that change resource availability and that create patterns in vegetation by producing a mosaic of serai stages that ecologists have long recognised as important to landscape-level patch mosaics. Several good reasons justify the need for pursuing a predictive understanding of the ecology of mangrove species competition including the role of disturbance events and the aftermath. A predictive understanding can challenge our assumptions concerning the factors that control plant distribution and abundance and provide techniques for predicting rates of species change ranges in response to disturbances. The aim of this study was to evaluate and predict the impact of canopy disturbances on Gazi Bay mangrove forests and the subsequent vegetation patterns both spatially and temporally. The use of a simple 1D cellular automaton provided a detailed and nearly comprehensive parameterisation of the model by forest structure parameters belonging to the standard measurements of mangrove field surveys. In the study presented, the field data were obtained for disturbance impacts at various spatial scales considering not only the spatial extent of the disturbance but also its particular location. For this, multiple sampling transects were selected a priori, based on the vegetation patterns observed on Quickbird satellite image (2002) of Gazi, to reflect major ecological zones and vegetation transitions in space. Earlier field studies already revealed different population trajectories in some cases for the same pairwise species interactions, which are consistent with the hypothesis that different scales of disturbances may affect succession trends. Simulation experiments supported these findings by demonstrating that varying disturbance

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

An advanced emulated digital retina model on FPGA to implement a real-time test environment

An advanced emulated digital retina model on FPGA to impleme...

引用

Proceedings of 2006 IEEE International Symposium on Circuits and Systems,Volume 4

作者： Z. Nagy Zs. Voroshazi P. Szolgay Department of Image Processing and Neurocomputing University of Veszprém Veszprem Hungary Analogic and Neural Computing Laboratory Computer and Automation Research Institute Hungarian Academy of Sciences Budapest Hungary

This paper presents an extended emulated digital retina model to compute two different retina channels in video real-time. The proposed emulated digital implementation of the two-channel retina model was compared to the previously developed single channel model from three different points of view: processing speed, number of physical cells and accuracy. A real-time test environment with camera input and display output is going to be set up to analyze the retina model implementation on emulated digital CNN (Cellular Neural/Nonlinear Network) model by using a 6M gate equivalent FPGA (Field Programmable Gate Array).

关键词： Retina Field programmable gate arrays Cellular neural networks Neurons Hardware Automatic testing Differential equations Cameras Nonhomogeneous media computer architecture

来源：评论

学校读者我要写书评

暂无评论

Asymmetry Total Variation and Framelet Regularized Nonconvex Low-Rank Tensor Completion

SSRN

引用

SSRN 2022年

作者： Chen, Yongyong Zhao, Xiaojia Xu, Tingting Zeng, Haijin Xu, Yanhui Chen, Junxing The School of Computer Science and Technology Harbin Institute of Technology Shenzhen518055 China Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies Shenzhen518055 China Image Processing and Interpretation Imec Research Group Ghent University Belgium Department of Electrical and Computer Engineering Faculty of Science and Technology University of Macau China The College of Medicine and Biological Information Engineering Northeastern University Shenyang110004 China

The low-rank tensor representation has shown enormous potential and advantages in diverse applications. However, (1) due to the inherent limitations of the low-rank tensor model, the tensor nuclear norm is utilized yet as a biased estimate of the tensor rank, which limits the image recovery performance. (2) most current low-rank approximation-based methods focus on the preservation of global information, while ignoring the local details preservation such as the spatial piece-wise smoothness and sharp edges. To overcome he above obstacles, we propose a novel asymmetry three-dimensional total variation and framelet regularized nonconvex low-rank tensor completion (ATV-FNTC) model, which integrates the nonconvex penalty function and asymmetric three-dimensional total variation into one unified model. Specifically, ATV-FNTC introduces one nonconvex penalty function as a tighter regularizer to approximate the tensor rank. Different from existing methods, the asymmetric three-dimensional total variation regularization is developed to achieve more accurate recovery of detailed information and flexibly control the smoothing strength of different dimensions of tensor data. Furthermore, we design an iterative algorithm to solve the nonconvex ATV-FNTC model by the alternating direction methods of multipliers. Experimental results reveal the superiority of the proposed method compared with several state-of-the-art methods when handling different completion tasks. © 2022, The Authors. All rights reserved.

关键词： Tensors

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：