检索结果-内蒙古大学图书馆

arXiv 2017年

作者： Huang, Xiaolin Yan, Ming Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University MOE Key Laboratory of System Control and Information Processing Shanghai200240 China Department of Computational Mathematics Science and Engineering Department of Mathematics Michigan State University East LansingMI48824 United States

One-bit measurements widely exist in the real world and can be used to recover sparse signals. This task is known as one-bit compressive sensing (1bit-CS). In this paper, we propose novel algorithms based on both convex and nonconvex sparsity-inducing penalties for robust 1bit-CS. We consider the dual problem, which has only one variable and provides a sufficient condition to verify whether a solution is globally optimal or not. For positive homogeneous penalties, a globally optimal solution can be obtained in two steps: a proximal operator and a normalization step. For other penalties, we solve the dual problem, and it needs to evaluate the proximal operators for many times. Then we provide fast algorithms for finding analytical solutions for three penalties: minimax concave penalty (MCP), 0norm, and sorted 1penalty. Specifically, our algorithm is more than 200 times faster than the existing algorithm for MCP. Its efficiency is comparable to the algorithm for the 1penalty in time, while its performance is much better than 1. Among these penalties, sorted 1is most robust to noise in different settings. Copyright © 2017, The Authors. All rights reserved.

关键词： Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

An efficient algorithm and implementation for residue to binary number conversion

An efficient algorithm and implementation for residue to bin...

引用

International Conference on Communications, Circuits and Systems (ICCCAS)

作者： Chengyi Xiong Zhirong Gao Jinwen Tian Key Laboratory of Education Commission for Image Processing and Intelligent Control Institute of Pattern Recognition & Artificial Intelligence Huazhong University of Science and Technology Wuhan China Department of Computer Science Wuhan University of Science & Engineering Wuhan China Key Laboratory of Education Commission for Image Processing Huazhong University of Science & Technology China

The residue number system (RNS) has computational advantages in addition and multiplication compared with weighted number systems, such as the binary number system (BNS), since operations on residue digits are performed independently and these processes can be performed in parallel. Thus they are widely used in digital signal processing etc. Since residue to binary conversion is critical and difficult for the practicality of RNS, in this paper, a novel residue to binary (R/B) conversion algorithm for the restricted moduli set (2/sup n/ -1, 2/sup n/, 2n+1), based on exploring the periodicity of modulo (2/sup n/ /spl plusmn/ 1) operations is presented. A new 2n-bit adder based R/B converter is also proposed. The performance comparison results demonstrate that the new converter is faster and requires less area compared with the others reported in the previous literature.

关键词： Signal processing algorithms Image converters Educational institutions Computer science Concurrent computing Digital signal processing Arithmetic Laboratories Image processing Intelligent control

来源：评论

学校读者我要写书评

暂无评论

Adaptive dynamic loading and unloading mechanism applied to development environment for image processing algorithm

Adaptive dynamic loading and unloading mechanism applied to ...

引用

2011 International Conference on Computer Science and Service System, CSSS 2011

作者： Lu, Haifeng Zhang, Tianxu Yan, Wei Cheng, Zhao State Key Laboratory for Multispectral Information Processing Technologies Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan 430074 China Department of Technology Hubei Daily Media Group Wuhan 430077 China

ISBN: (纸本)9781424497638

An advanced development environment contributes to research process greatly. This paper presents a novel adaptive dynamic loading and unloading mechanism applied to development environment for image processing algorithm and two implementation methods of the mechanism. Based on the inherent characteristic of variable arguments of functions in programming language and explicit linking technique for dynamic link library (DLL), the mechanism is to integrate the image processing algorithm into the DLL file which is independent from the development environment, and to make the development environment identify the normative algorithm DLL and load functions of image processing algorithm successfully when needed. The proposed mechanism has been implemented in a development environment written by C/C++ language. The results show that the development environment based on the novel mechanism can improve work efficiency by making researchers only focus on the development of image processing algorithm rather than the other inefficient and repetitive work. At the same time the standardability, reusability and confidentiality of image processing algorithm can be promoted greatly. This mechanism is also applicable to other similar systems. © 2011 IEEE.

关键词： Reusability

来源：评论

学校读者我要写书评

暂无评论

VIRTUAL WORK SPACE FOR ASSEMBLY

引用

SYSTEMS AND COMPUTERS IN JAPAN 1994年第7期25卷 92-100页

作者： HIRATA, Y MIZUGUCHI, T SATO, M KAWARADA, H Precision and Intelligence Laboratory Tokyo Institute of Technology Yokohama Japan 227 Members Hiroshi Kawarda is currently a Professor in the Precision and Intelligence Laboratory Tokyo Institute of Technology. His research interests include digital processing and pattern recognition. He received a B.E. in Electrical Engineering in 1962 and a doctorate in 1967 from the Tokyo Institute of Technology.

To implement a human interface for efficiently modeling 3-D shapes on a computer, a virtual works space enabling direct manipulation of a shape model on a computer similar to manipulating a real 3-D object must be constructed. In this virtual work space, the tactile and force sensations arising while the object is manipulated must be fed back to the person. We previously proposed the space interface device SPIDAR capable of force feedback to the person's fingertips. However, only one finger could be used in SPIDAR, so operations where the object is held were not possible. In this paper, we extend SPIDAR and propose the space interface device SPIDAR II to implement a virtual work space where operations involving holding and moving objects are possible. This device measures the position of the minimum of the two fingers needed to manipulate objects and can provide tactile feedback to the fingertips while an object is being held. A prototype device is built and a virtual work space is constructed where holding and moving objects is possible. Further, an experiment is conducted to investigate the effect of tactile feedback to work operability in this virtual work space, and its effectiveness is confirmed.

关键词： VIRTUAL REALITY VIRTUAL WORK SPACE ASSEMBLY SHAPE MODELING HUMAN INTERFACE

来源：评论

学校读者我要写书评

暂无评论

New design for 9/7-tap wavelet filter and its VLSI implementation

引用

Jisuanji Xuebao/Chinese Journal of Computers 2008年第3期31卷 411-418页

作者： Tian, Xin Tan, Yi-Hua Tian, Jin-Wen State Key Laboratory for Multi-Spectral Information Processing Technologies Institute for Pattern Recognition and Artificial Intelligence Wuhan 430074 China

This paper designs a new kind of lifting 9-7-tap wavelet filter with binary characteristics and presents a high speed VLSI structure for the wavelet filter. The coefficients of the lifting filters are binary numbers, so it can simplify the VLSI design. The test results for compression performances have shown that the new filter is good almost as CDF97 under PSNR. when the data has a finite accuracy, it may have a better performance than CDF97. The filter can be implemented with using adders and shifters. Therefore the hardware resources can be saved and the critical path can be shortened. According to using the folding technology and the retiming technology, the architecture of the design can be transformed into a kind of embedded folding architecture which leads to the parallel computation of addition operations. So the critical path can be shortened to nearly the time of a addition operation and the utilization of the hardware resources also has a good performance. Simulation results show that the max working frequency could almost reach 250 MHz which is the four times by the CDF97;The occupied logic cell is reduced by 66.7 compared with the CDF97+4 stages pipeline. So it is especially suitable for the high speed VLSI design.

关键词： VLSI circuits

来源：评论

学校读者我要写书评

暂无评论

A Semantic Segmentation Method of Buildings in Remote Sensing Image Based on Improved UNet 2

A Semantic Segmentation Method of Buildings in Remote Sensin...

引用

2nd International Conference on Signal Image processing and Communication, ICSIPC 2022

作者： Li, Zhongyu Liu, Yang Kuang, Yin Wang, Huajun Liu, Cheng College of Computer Science Chengdu Normal University Chengdu611130 China College of Geophysics Chengdu University of Technology Chengdu610059 China Key Laboratory of Pattern Recognition and Intelligent Information Processing of Sichuan Chengdu University Chengdu610106 China Artificial Intelligence Key Laboratory of Sichuan Province Zigong643000 China Key Laboratory of interior Layout optimization and Security Institutions of Higher Education of Sichuan Province Chengdu Normal University Sichuan Chengdu611130 China College of Movie and Media Sichuan Normal University Chengdu610066 China

ISBN: (纸本)9781510657694

Aiming at the problem of model instability and overfitting of deep neural networks with the deepening of the number of network layers, the current mainstream method is to use batch normalization (BN) to alleviate them. However, since the BN method is more sensitive to batch size when the batch size is small, the model performance will be poor. For a relatively large model, due to the limitation of video memory, the batch size cannot take a large value, limiting the model's performance. Because of the dependence of BN on batch size, this paper adopts group normalization (GN) instead of batch normalization (BN) in the UNet network to alleviate the impact of the model on batch size. Then experiments are carried out on the WHUBuilding dataset. The experimental results show that the improved model (UNet-GN) improves the mean intersection over union (MIoU) and mean pixel accuracy (MPA) by 10.66% and 1.65% respectively compared with the original model (UNet-BN). © 2022 SPIE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Text scanner with text detection technology on image sequences

Text scanner with text detection technology on image sequenc...

引用

International Conference on pattern recognition

作者： Keechul Jung Kwang In Kim T. Kurata M. Kourogi JungHyun Han Pattern Recognition and Image Processing Laboratory Michigan State University USA Artificial Intelligence Laboratory KAIST South Korea National Institute for Advanced Industrial Science and Technology Japan School of Electrical and Computer Engineering Sung Kyun Kwan University South Korea

ISBN: (纸本)076951695X

We propose a text scanner which detects wide text strings in a sequence of scene images. For scene text detection, we use a multiple-CAMShift algorithm on a text probability image produced by a multi-layer perceptron. To provide enhanced resolution of the extracted text images, we perform the text detection process after generating a mosaic image in a fast and robust image registration method.

关键词： Image sequences Layout Image registration Cameras Parameter estimation Videos Pixel Image processing Robustness Optical character recognition software

来源：评论

学校读者我要写书评

暂无评论

NiuEM: A Nested-iterative Unsupervised Learning Model for Single-particle Cryo-EM Image processing

NiuEM: A Nested-iterative Unsupervised Learning Model for Si...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Rui Hu Jiaming Cai Wangjie Zheng Yang Yang Hong-Bin Shen Shanghai Jiao Tong University and Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University and Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9781728162157

ISBN: (纸本)9781728162164

Cryo-electron microscopy (cryo-EM) has become a mainstream technology for solving spatial structures of biomacromolecules, while the processing of cryo-EM images is a very challenging task. One of the great challenges is the high noise in the images. A common method is to cluster the images with close projecting angles to get mean images, which are used for 3D reconstruction. However, due to the extremely low signal-to-noise-ratio, common clustering methods often fail to obtain high-quality mean images, leading to poorly reconstructed structures. In this study, we present a new unsupervised learning framework, called NiuEM, to discriminate images captured from different angles and yield cluster-mean images. NiuEM first generates pseudo-labels and then exploits both contrastive loss and cross-entropy loss for training convolutional layers to learn feature representations. Moreover, the pseudo-labels are updated iteratively to enhance the reliability of labels. We assess the performance of NiuEM on four data sets via both visualized and quantitative experiments. Especially, two kinds of metrics are adopted to measure the performance, regarding the clustering quality and the resolution of reconstructed 3D models, respectively. The experimental results show that NiuEM achieves very competitive clustering accuracy in the comparison with the state-of-the-art image clustering methods. Moreover, the cluster mean images yielded by NiuEM lead to better initial 3D models compared with the mainstream reconstruction tools.

关键词： Three-dimensional displays Feature extraction Image reconstruction Task analysis Solid modeling Electron microscopy Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Classification with Task-Adaptive Semantic Feature Learning

SSRN

引用

SSRN 2022年

作者： Pan, Mei-Hong Xin, Hong-Yi Xia, Chun-Qiu Shen, Hong-Bin Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China University of Michigan Shanghai Jiao Tong University Joint Institute Shanghai Jiaotong University Shanghai200240 China

Few-shot classification aims to learn a classifier that categorizes objects of unseen classes with limited samples. One general approach is to mine as much information as possible from limited samples. This can be achieved by incorporating data from multiple modals. However, existing multi-modality methods only use additional modality in support samples while adhering to a single modal in query samples. Such approach could lead to information imbalance between support and query samples, which confounds model generalization from support to query samples. Towards this problem, we propose a task-adaptive semantic feature learning mechanism to incorporate semantic features for both support and query samples. The semantic feature learner is trained episodic-wisely by regressing from the feature vectors of the support samples. It is utilized to predict semantic features for the query samples. Such method maintains a consistent training scheme between support and query samples and enables direct model transfer from support to query data, which significantly improves model generalization. We conduct extensive experiments on four benchmarks in both inductive and tranductive settings. Results show that the proposed TasNet outperforms state-of-the-art methods with an improvement of 1% to 5% in classification accuracy, demonstrating the superiority of our method. The exhaustive ablation studies further validate the effectiveness of our framework. © 2022, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

A Riemannian Residual Learning Mechanism for SPD Network

A Riemannian Residual Learning Mechanism for SPD Network

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Zhenyu Cai Rui Wang Tianyang Xu Xiaojun Wu Josef Kittler School of Artificial Intelligence and Computer Science Jiangnan University Wuxi China Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Wuxi China Centre for Vision Speech and Signal Processing University of Surrey Guildford U.K.

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

The generalization of Euclidean network paradigm to the Riemannian manifolds has attracted much attention for offering useful geometric representations in processing manifold-valued data in recent years. However, the information degradation during data compression mapping hinders Riemannian networks from going deeper, and there are very few solutions specifically designed for this problem. Given the remarkable success of deep Residual learning in Euclidean networks, a novel Riemannian residual learning mechanism (RRLM) is proposed in the context of Symmetric Positive Definite (SPD) manifolds, enabling the characterization of deep spatiotemporal features while preserving the manifold properties. Based on RRLM, a stack of SPD manifold-constrained residual-like blocks is designed on the tail of the original SPDNet(backbone) for the sake of conducting deep Riemannian residual learning. For simplicity, we refer to the network architecture introduced above as Riemannian residual SPD network (ResSPDNet). The experimental results achieved on three types of visual classification tasks, i.e., facial emotion recognition, drone recognition, and action recognition, demonstrate that our method can achieve improved accuracy with a deepened network structure.

关键词： Manifolds Learning systems Degradation Emotion recognition Visualization Accuracy Face 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：