检索结果-内蒙古大学图书馆

2017 IEEE International Conference on Applied System Innovation, ICASI 2017

作者： Wang, Maosen Niu, Shaozhang Yang, Xuan Beijing Key Lab of Intelligent Telecommunication Software and Multimedia Beijing University of Posts and Telecommunications Beijing100876 China Institute of Image Processing and Pattern Recognition North China University of Technology No.5 Jinyuanzhuang Road Shijingshan District Beijing China

ISBN: (纸本)9781509048977

image stitching technique is to integrate multiple images with overlapping regions into a complete image with a wide viewing angle, less distortion, and no obvious suture. image stitching could be used for global positioning and robot autonomous navigation without changing the hardware. SIFT feature and SURF feature are the classical algorithm in the image stitching. But they have the long time-consuming problem. Facing this problem, a novel fast image stitching algorithm based on ORB (Oriented FAST and Rotated BRIEF) features is proposed in this paper. The algorithm firstly selects ORB algorithm which adds the direction information to the FAST detector for image feature extracting and matching. Secondly, RASANC (Random Sample Consensus) algorithm is used to eliminate false matching points. Finally, weighted average method is used to speed up the image fusion. Experimental results show that the stitching effect of the algorithm in this paper is the same as that of SIFT algorithm and SURF algorithm. The two obvious advantages of our algorithm include: (1) stitching speed is much faster than that of Shift and Surf;(2)The algorithm is robust to external parameters of camera. So the proposed algorithm is hopefully applied to some handed electrical devices. © 2017 IEEE.

关键词： image fusion

来源：评论

学校读者我要写书评

暂无评论

Tasks-oriented channel optimization and resource allocation in vehicular networks: a hierarchical reinforcement learning based approach

引用

IEEE Transactions on Vehicular Technology 2024年第5期74卷 7624-7636页

作者： Lin, Runtao Guo, Caili Zhang, Biling Chen, Jiujiu Li, Hanyang Beijing University of Posts and Telecommunications Beijing Key Laboratory of Network System Architecture and Convergence School of Information and Communication Engineering Beijing100876 China Nanchang Hangkong University Key Laboratory of Processing and Pattern Recognition of Jiangxi Province School of Information Engineering Nanchang330063 China China Mobile Communication Co. Ltd Wireless and Terminal Technology Research Institute Beijing100053 China

The number of devices, data volume, and pictures and videos in the vehicular networks have all increased significantly as a result of the continued development of 6G technology, putting an enormous burden on the edge communication resources. To solve this problem, a good resource allocation scheme is necessary. Existing resource allocation algorithms often pursue accurate transmission and ignore time-varying channels. In order to further obtain real and reasonable resource allocation results, this paper introduces semantic communication. It then decomposes that problem to further establish a hierarchical framework. The problem is addressed via a task-oriented channel optimization and resource allocation scheme based on a hierarchical reinforcement learning (TCRS-HRL) algorithm. First, a channel optimization and resource allocation problem under an imperfect channel state is developed, and it is divided into two separate sub problems for optimization. Second, the resource allocation problem at the edge is addressed with the introduction of hierarchical reinforcement learning and the TCRSHRL algorithm. The ideal channel state and resource allocation approach are found by constructing the state space, action space, and environmental feedback for each aspect individually. Finally, simulations have demonstrated the superiority and performance benefits of the proposed algorithm compared to current methods, showing that the implementation of TCRS-HRL can result in an accuracy improvement of roughly 8%. © 1967-2012 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Generalized tube model: recognizing 3D elongated objects from 2D intensity images

Generalized tube model: recognizing 3D elongated objects fro...

引用

Conference on Computer Vision and pattern recognition (CVPR)

作者： Q. Huang G.C. Stockman Pattern Recognition and Image Processing Laboratory Department of Computer Science Michigan State University East Lansing MI USA

The issue of recognizing 3D elongated objects from 2D intensity images is addressed. A tube model, locally similar to generalized cones, is developed for the class of elongated objects. A recognition strategy that combines 2D contour properties and surface shading information is used to exploit the power of the 3D model. Reliable contours provide constraints for localizing the objects of interest. The theory of optimal filters is adopted in verifying the shading of hypothesized objects. Object recognition is achieved through optimizing the signal-to-noise response with respect to model parameters. A sweeping operation is proposed as a further stage of identifying objects so that the overall performance of the system does not heavily rely on the quality of local feature detection.< >

关键词： image recognition Filters Object recognition Object detection Robustness image processing Laboratories Computer science Filtering theory Power system modeling

来源：评论

学校读者我要写书评

暂无评论

The design and implementation of a Chinese financial invoice recognition system

The design and implementation of a Chinese financial invoice...

引用

IEEE Region 8 International Symposium on Video/image processing and Multimedia Communications (EURASIP)

作者： Ming Delie Liu Jian Tian Jinwen State Key Laboratory for Image Processing and Intelligent Control Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan Hubei China

This paper designs and implements a financial invoice recognition system based on the features of the Chinese financial invoice. By using the linear whole block moving method in each vertical segment, a new fast algorithm is put forward to detect and rectify slanted images. To distinguish the different form types (the foundation necessary for locating the form fields, filtering the form lines, etc), several representative form features are discussed and an invoice-type features library is built by using a semi-automatic machine study method. On the basis of the recognized invoice type, a real invoice form is re-oriented against the corresponding blank form according to the invoice type feature, solving the problem of adhesion of characters and form lines, as well as the problem of character segmentation and recognition. Based on the financial Chinese invoice image feature, a mutual rectification mechanism founded on the recognition results of financial Chinese characters and Arabic numerals is put forward to raise the recognition rate. Finally, experimental results and conclusions are presented.

关键词： Character recognition Optical character recognition software image recognition image segmentation image processing pattern recognition High speed optical techniques Optical filters System testing Laboratories

来源：评论

学校读者我要写书评

暂无评论

DAmageNet: A universal adversarial dataset

arXiv

引用

arXiv 2019年

作者： Chen, Sizhe Huang, Xiaolin He, Zhengbao Sun, Chengjin Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University MOE Key Laboratory of System Control and Information Processing 800 Dongchuan Road Shanghai200240 China

It is now well known that deep neural networks (DNNs) are vulnerable to adversarial attack. Adversarial samples are similar to the clean ones, but are able to cheat the attacked DNN to produce incorrect predictions in high confidence. But most of the existing adversarial attacks have high success rate only when the information of the attacked DNN is well-known or could be estimated by massive queries. A promising way is to generate adversarial samples with high transferability. By this way, we generate 96020 transferable adversarial samples from original ones in imageNet. The average difference, measured by root means squared deviation, is only around 3.8 on average. However, the adversarial samples are misclassified by various models with an error rate up to 90%. Since the images are generated independently with the attacked DNNs, this is essentially zero-query adversarial attack. We call the dataset DAmageNet, which is the first universal adversarial dataset that beats many models trained in imageNet. By finding the drawbacks, DAmageNet could serve as a benchmark to study and improve robustness of DNNs. DAmageNet could be downloaded in http://***/Show/56/122 Copyright © 2019, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Topologically logic ally clustering: A method for discarding mismatches

Topologically logic ally clustering: A method for discarding...

引用

MIPPR 2007: pattern recognition and Computer Vision

作者： Yongtao, Wang Dazhi, Zhang Chenqiang, Gao Jinwen, Tian State Key Laboratory for Multi-Spectral Information Processing Technologies Huazhong University of Science and Technology Wuhan 430074 China Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)9780819469526

Wide baseline stereo correspondence has become a challenging and attractive problem in computer vision and its related applications. Getting high correct ratio initial matches is a very important step of general wide baseline stereo correspondence algorithm. Ferrari et al. suggested a voting scheme called topological filter in [3] to discard mismatches from initial matches, but they didn't give theoretical analysis of their method. Furthermore, the parameter of their scheme was uncertain. In this paper, we improved Ferraris' method based on our theoretical analysis, and presented a novel scheme called topologically clustering to discard mismatches. The proposed method has been tested using many famous wide baseline image pairs and the experimental results showed that the developed method can efficiently extract high correct ratio matches from low correct ratio initial matches for wide baseline image pairs.

关键词： image analysis

来源：评论

学校读者我要写书评

暂无评论

High-Precision Discrete Convolution Algorithm Based on Moments

High-Precision Discrete Convolution Algorithm Based on Momen...

引用

WRI International Conference on Communications and Mobile Computing, CMC

作者： Jianguo Liu Zhenbing Liu Guoyou Wang Key Laboratory of Education Ministry for Image Processing and Intelligent Control State Key Laboratory of Multispectral Information Processing Technologies Institute of Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan China

Convolution is an important and useful operation in the fields of digital signal processing. In this paper, based on the previous work of performing discrete Fourier transform (DFT) via linear sums of discrete moments, we have made development to eliminate multiplications in discrete Fourier transforms by performing appropriate bit operations and shift operations in binary system, which can be implemented by integer additions of fixed points; then using the convolution theorem with the DFT, we compute the convolution with two DFTs, a point-by-point product, and an inverse DFT. Our algorithm involves fewer multiplications and can deal with arbitrary length signals.

关键词： Convolution Signal processing algorithms Discrete Fourier transforms Very large scale integration Algorithm design and analysis Laboratories Educational technology Digital signal processing Mobile communication Mobile computing

来源：评论

学校读者我要写书评

暂无评论

High-Precision and Arbitrary-length Fixed-Point Fast Hartley Transform without Multiplications

High-Precision and Arbitrary-length Fixed-Point Fast Hartley...

引用

WRI International Conference on Communications and Mobile Computing, CMC

作者： Zhenbing Liu Jianguo Liu Guoyou Wang Key Laboratory of Education Ministry for Image Processing and Intelligent Control State Key Laboratory of Multispectral Information Processing Technologies Institute of Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan China

Discrete Hartley transform (DHT) is an important tool in digital signal processing. In this paper, based on our previous work of performing DHT via linear sums of discrete moments, we have made development to eliminate multiplications in discrete Hartley transforms by performing appropriate bit operations and shift in binary system, which can be implemented by integer additions of fixed points. An efficient and regular systolic array is designed to implement it, and the complexity analysis is also given. Different to other fast Hartley transforms, our algorithm can deal with arbitrary length signals and get high precision. The approach is also applicable to multi-dimensional DHT and DHT inverses.

关键词： Discrete transforms Signal processing algorithms Digital signal processing Systolic arrays Laboratories Educational technology Very large scale integration Hardware Mobile communication Mobile computing

来源：评论

学校读者我要写书评

暂无评论

Improvement and invariance analysis of Zernike moments

Improvement and invariance analysis of Zernike moments

引用

International Conference on Communications, Circuits and Systems (ICCCAS)

作者： Ye Bin Peng Jia Xiong State Key Laboratory for Image Processing and Intelligent Control Institute for Pattern Recognition & Artificial Intelligence Huazhong University of Science and Technology Wuhan Hubei China

An improved Zernike moment using a region-based shape descriptor is presented. The improved Zernike moment not only has rotation invariance, but also has scale invariance that the unimproved Zernike moment does not have. The experimental results show that the improved Zernike moment has better invariant properties than the unimproved Zernike moment using a region-based shape descriptor.

关键词： Shape Information retrieval image retrieval Content based retrieval image databases Multi-stage noise shaping Laboratories image processing Intelligent control pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Scene Text Detection with Feature Aggregation and Receptive Field Enhancement

Scene Text Detection with Feature Aggregation and Receptive ...

引用

IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC)

作者： Qin Tang Qishen Li Ruirui Wang Yanming Lai School of Information Engineering Nanchang Hangkong University Nanchang China Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Nanchang Jiangxi China

ISBN: (数字)9781728180281

ISBN: (纸本)9781728180298

We propose a scene text detection with feature aggregation and receptive field enhancement. It mainly improves the problem of wrong text segmentation. Specifically, a Feature Aggregation and Receptive Field Enhancement Module (FARE) adopts a ladder structure and constructs multi-scale feature aggregation with multiple branches to enhance the feature representation ability of texts of different scales. We add dilated convolution to expand the range of receptive field, which increases the detection of large-scale texts in low-level feature and obtains more accurate position information. Extensive experiments on the ICDAR 2015, ICDAR 2017 MLT, and CTW1500 show that the proposed method effectively improves the detection performance of the network. Notably, our proposed method has detected a precision of 87.4% on the curved text dataset CTW1500.

关键词： Automation Convolution Fuses Conferences Benchmark testing Feature extraction Information technology

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：