检索结果-内蒙古大学图书馆

CNN-based invertible wavelet scattering for the investigation of diffusion properties of the in vivo human heart in diffusion tensor imaging

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Deng, Zeyu Wang, Lihui Kuai, Zixiang Chen, Qijian Cheng, Xinyu Yang, Feng Yang, Jie Zhu, Yuemin Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province College of Computer Science and Technology Guizhou University Guiyang550025 China Imaging Center Harbin Medical University Cancer Hospital Harbin150081 China School of Computer and Information Technology Beijing Jiaotong University Beijing100044 China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai200240 China University Lyon INSA Lyon CNRS Inserm IRP Metislab CREATIS UMR5220 U1206 LyonF-69621 France

In vivo diffusion tensor imaging (DTI) is a promising technique to investigate noninvasively the fiber structures of the in vivo human heart. However, signal loss due to motions remains a persistent problem in in vivo cardiac DTI. We propose a novel motion-compensation method for investigating in vivo myocardium structures in DTI with free-breathing acquisitions. The method is based on an invertible Wavelet Scattering achieved by means of Convolutional Neural Network (WSCNN). It consists of first extracting translation-invariant wavelet scattering features from DW images acquired at different trigger delays and then mapping the fused scattering features into motion-compensated spatial DW images by performing an inverse wavelet scattering transform achieved using CNN. The results on both simulated and acquired in vivo cardiac DW images showed that the proposed WSCNN method effectively compensates for motion-induced signal loss and produces in vivo cardiac DW images with better quality and more coherent fiber structures with respect to existing methods, which makes it an interesting method for measuring correctly the diffusion properties of the in vivo human heart in DTI under free breathing. Copyright © 2019, The Authors. All rights reserved.

关键词： Diffusion tensor imaging

Learning data-adaptive nonparametric kernels

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Liu, Fanghui Huang, Xiaolin Gong, Chen Yang, Jie Li, Li Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Department of Automation Tsinghua University

Kernel methods have been extensively used in a variety of machine learning tasks such as classification, clustering, and dimensionality reduction. For complicated practical tasks, the traditional kernels, e.g., Gaussian kernel and sigmoid kernel, or their combinations are often not sufficiently flexible to fit the data. In this paper, we present a Data-Adaptive Nonparametric Kernel (DANK) learning framework in a data-driven manner. To be specific, in model formulation, we impose an adaptive matrix on the kernel/Gram matrix in an entry-wise strategy. Since we do not specify the formulation of the adaptive matrix, each entry in the adaptive matrix can be directly and flexibly learned from the data. Therefore, the solution space of the learned kernel is largely expanded, which makes our DANK model flexible to capture the data with different local statistical properties. Specifically, the proposed kernel learning framework can be seamlessly embedded to support vector machines (SVM) and support vector regression (SVR), which has the capability of enlarging the margin between classes and reducing the model generalization error. Theoretically, we demonstrate that the objective function of our DANK model embedded in SVM/SVR is gradient-Lipschitz continuous. Thereby, the training process for kernel and parameter learning in SVM/SVR can be efficiently optimized in a unified framework. Further, to address the scalability issue in nonparametric kernel learning framework, we decompose the entire optimization problem in DANK into several smaller easy-to-solve problems, so that our DANK model can be efficiently approximated by this partition. The effectiveness of this approximation is demonstrated by both empirical studies and theoretical guarantees. Experimentally, the proposed DANK model embedded in SVM/SVR achieves encouraging performance on various classification and regression benchmark datasets when compared with other representative kernel learning based algorithms. Copyrig

关键词： Matrix algebra

Segmentation-based Euler number with multi-levels for image feature description

学校读者我要写书评

暂无评论

Procedia Computer Science 2017年 111卷 245-251页

作者： Qian Zhang Lin Wang Jiang-Hao Yu Minggui Zhang Academic Affairs Office Guizhou Minzu University GuiYang 550025 China Pattern Recognition & Intelligent System Key Laboratory of Gui Zhou Province GuiYang 550025 China

This paper proposes a new and efficient image feature descriptor using Euler Number with the help of segmentation according to given number of levelsest. The proposed Segmentation-based Euler Number for image description algorithm (SENA) works as the following steps. First, transforming the image into gray image if the image is color image; then, dividing the gray image into different sets using the given number of levelsets; next, decomposing the gray image into binary images with multi-thresh using the otsu algorithm; following, computing the Euler Number of each binary image; finally, combining the Euler Numbers, mean and variance to form the feature vector for an input image. The proposed SENA was employed to the image classification on three public available dataset (Stanford Dogs Dataset, 17 flower dataset, and Caltech 256 dataset). We compute SENA with LBP and Gabor on the Stanford Dogs Dataset, the detail classification results on 17 flower dataset is given as confusion matrix, and the result of SENA on the Caltech 256 dataset is compared with those of the recently reported. The experiments demonstrate a competitive performance of SENA for classification task.

关键词： Number image feature image segmentation image classification LevelSet

ChaLearn looking at people: IsoGD and ConGD large-scale RGB-D gesture recognition

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Wan, Jun Lin, Chi Wen, Longyin Li, Yunan Miao, Qiguang Escalera, Sergio Anbarjafari, Gholamreza Guyon, Isabelle Guo, Guodong Li, Stan Z. National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China JD Finance Mountain ViewCA United States University of Southern California Los AngelesCA90089-0911 United States School of Computer Science and Technology Xidian University & Xi'an Key Laboratory of Big Data and Intelligent Vision 2nd South Taibai Road Xi'an710071 China Universitat de Barcelona Computer Vision Center Spain iCV Lab Institute of Technology University of Tartu Estonia Faculty of Engineering Hasan Kalyoncu University Gaziantep Turkey Institute of Digital Technologies Loughborough University London United Kingdom ChaLearn United States University Paris-Saclay France institute of Deep Learning Baidu Research National Engineering Laboratory for Deep Learning Technology and Application China

The ChaLearn large-scale gesture recognition challenge has been run twice in two workshops in conjunction with the International Conference on pattern recognition (ICPR) 2016 and International Conference on Computer Vision (ICCV) 2017, attracting more than 200 teams around the world. This challenge has two tracks, focusing on isolated and continuous gesture recognition, respectively. This paper describes the creation of both benchmark datasets and analyzes the advances in large-scale gesture recognition based on these two datasets. We discuss the challenges of collecting large-scale ground-truth annotations of gesture recognition, and provide a detailed analysis of the current state-of-the-art methods for large-scale isolated and continuous gesture recognition based on RGB-D video sequences. In addition to recognition rate and mean jaccard index (MJI) as evaluation metrics used in our previous challenges, we also introduce the corrected segmentation rate (CSR) metric to evaluate the performance of temporal segmentation for continuous gesture recognition. Furthermore, we propose a bidirectional long short-term memory (Bi-LSTM) baseline method, determining the video division points based on the skeleton points extracted by convolutional pose machine (CPM). Experiments demonstrate that the proposed Bi-LSTM outperforms the state-of-the-art methods with an absolute improvement of 8.1% (from 0.8917 to 0.9639) of CSR. Copyright © 2019, The Authors. All rights reserved.

关键词： Long short-term memory

Progressive Refinement Bilateral Filter

学校读者我要写书评

暂无评论

Progressive Refinement Bilateral Filter

IEEE International Conference on Automation, Electronics and Electrical Engineering (AUTEEE)

作者： Chanyi Lu Yong Zhao Lin Wang Guiying Zhang Fujian Feng Li Zhang College of Data Science and Information Engineering Guizhou Minzu University Guiyang China School of Electronic and Computer Engineering Shenzhen Graduate School of Peking University Shenzhen China Guizhou Key Laboratory of Pattern Recognition and Intelligent System Guizhou Minzu University Guiyang China Department of Medical Information Engineering Zunyi Medical University Zunyi China

ISBN: (纸本)9781538678626;9781538678619

In this paper, a coarse-to-fine framework for image noise removal is proposed. The bilateral filter is redefined by the manner of progressive refining to effectively eliminate noise, thus forming progressive refinement bilateral filter (PRBF), which estimates the pixel values of a noisy image through the method of progressive refinement with gradual recursion and its result retains more details, infinite close to the original image. PRBF is further integrated into the denoising model for the details processing again after denoising of the major part of the image. Our algorithm is evaluated and compared on two large standardized datasets and a number of selected images. The experimental results show that our algorithm consistently outperforms other approaches for image denoising and demonstrates the effectiveness of our framework for stereo matching.

关键词： Noise reduction Image denoising Mathematical model Filtering Filtering algorithms Kernel Biomedical imaging

Fast signal recovery from saturated measurements by linear loss and nonconvex penalties

学校读者我要写书评

暂无评论

arXiv 2018年

作者： He, Fan Huang, Xiaolin Liu, Yipeng Yan, Ming Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University The MOE Key Laboratory of System Control and Information Processing Shanghai200240 China School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu611731 China The Department of Computational Mathematics Science and Engineering Michigan State University MI United States

Sign information is the key to overcoming the inevitable saturation error in compressive sensing systems, which causes information loss and results in bias. For sparse signal recovery from saturation, we propose to use a linear loss to improve the effectiveness from existing methods that utilize hard constraints/hinge loss for sign consistency. Due to the use of linear loss, an analytical solution in the update progress is obtained, and some nonconvex penalties are applicable, e.g., the minimax concave penalty, the 0 norm, and the sorted 1 norm. Theoretical analysis reveals that the estimation error can still be bounded. Generally, with linear loss and nonconvex penalties, the recovery performance is significantly improved, and the computational time is largely saved, which is verified by the numerical experiments. Copyright © 2018, The Authors. All rights reserved.

关键词： Compressed sensing

<i>L</i>(2,1)-Labeling of the Brick Product Graphs

学校读者我要写书评

暂无评论

Journal of Applied Mathematics and Physics 2017年第8期5卷 1529-1536页

作者： Xiujun Zhang Hong Yang Hong Li School of Information Science and Engineering Chengdu University Chengdu China Key Laboratory of Pattern Recognition and Intelligent Information Processing Institutions of Higher Education of Sichuan Province Chengdu University Chengdu China

A k-L(2,1)-labeling for a graph G is a function such that whenever and whenever u and v are at distance two apart. The λ-number for G, denoted by λ(G), is the minimum k over all k-L(2,1)-labelings of G. In this paper, we show that for or 11, which confirms Conjecture 6.1 stated in [X. Li, V. Mak-Hau, S. Zhou, The L(2,1)-labelling problem for cubic Cayley graphs on dihedral groups, J. Comb. Optim. (2013) 25: 716-736] in the case when or 11. Moreover, we show that? if 1) either (mod 6), m is odd, r = 3, or 2) (mod 3), m is even (mod 2), r = 0.

关键词： Graph Labeling Brick Product Graph L((2 1)-Labeling Frequency Assignment Problem

A localization method avoiding flip ambiguities for micro-UAVs with bounded distance measurement errors

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Guo, Qingbei Zhang, Yuan Lloret, Jaime Kantarci, Burak Seah, Winston K.G. Shandong Provincial Key Laboratory of Network Based Intelligent Computing University of Jinan Jinan Shandong China Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi214122 China Integrated Management Coastal Research Institute Universidad Politecnica de Valencia Spain School of Electrical Engineering and Computer Science University of Ottawa Canada School of Engineering and Computer Science Victoria University of Wellington New Zealand

Localization is a fundamental function in cooperative control of micro unmanned aerial vehicles (UAVs), but is easily affected by flip ambiguities because of measurement errors and flying motions. This study proposes a localization method that can avoid the occurrence of flip ambiguities in bounded distance measurement errors and constrained flying motions;to demonstrate its efficacy, the method is implemented on bilateration and trilateration. For bilateration, an improved bi-boundary model based on the unit disk graph model is created to compensate for the shortage of distance constraints, and two boundaries are estimated as the communication range constraint. The characteristic of the intersections of the communication range and distance constraints is studied to present a unique localization criterion which can avoid the occurrence of flip ambiguities. Similarly, for trilateration, another unique localization criterion for avoiding flip ambiguities is proposed according to the characteristic of the intersections of three distance constraints. The theoretical proof shows that these proposed criteria are correct. A localization algorithm is constructed based on these two criteria. The algorithm is validated using simulations for different scenarios and parameters, and the proposed method is shown to provide excellent localization performance in terms of average estimated error. Our code can be found at: https://***/QingbeiGuo/***. Copyright © 2018, The Authors. All rights reserved.

关键词： Measurement errors

DNA Sequence Alignment Algorithm Based on k-tuple Statistics

学校读者我要写书评

暂无评论

DNA Sequence Alignment Algorithm Based on k-tuple Statistics

2017 2nd International Conference on Software, Multimedia and Communication Engineering（SMCE 2017)

作者： Jun-yan ZHANG Chen-hui YANG Hai-ying WANG College of Information Science and Engineering Chengdu UniversityChengdu 610106China Key Laboratory of Pattern Recognition and Intelligent Information Processing of Sichuan Chengdu University

DNA Sequence Alignment is one of the most basic and most important operations in *** this paper,we put forward to SDk S algorithm based on k-tuple statistic,which is a kind of probability *** positive transition probability matrix,the negative transition probability matrix,and the logarithmic ration are computed based on Markov *** obtaining converting sequence,we get the results of k-tuple ***,the similarity measurement can be gained according to above *** the minimum support is given,we can identify two DNA sequences is similarity or *** experimental results show that SDk S algorithm has better effective performance in saving computing time.

关键词： Sequence alignment k-tuple statistic Markov model Similarity measurement