检索结果-内蒙古大学图书馆

IEEE International Conference on Systems, Man and Cybernetics

作者： P.J. Flynn A.K. Jain Pattern Recognition and Image Processing Laboratory Department of Computer Science Michigan State University East Lansing MI USA

The authors outline their approach for automatic translation of geometric entities produced by a CAD system into a relational graph structure. They have developed a system which uses 3-D object descriptions created on a commercial CAD system and expressed in the industry-standard IGES form, and performs geometric inferencing to object a relational graph representation of the object which can be stored in a database of models of object recognition. Details of the IGES standard, the geometric inference engine, and some formal properties of 3-D models are discussed. In addition to the process of translation from one data format to another, the interference engine extracts higher-level information from the CAD model and stores it explicitly in the new data structure. The higher-level features will allow the search space explored during the object recognition stage to be pruned early.< >

关键词： Computer vision Solid modeling Object recognition Engines Space exploration Industrial relations Relational databases Spatial databases Interference Data mining

来源：评论

学校读者我要写书评

暂无评论

Method of boundary extraction based on schrödinger equation 21

Method of boundary extraction based on schrödinger equation

引用

2008 21st ISPRS International Congress for Photogrammetry and Remote Sensing

作者： Lou, Liantang Zhan, Xin Fu, Zhongliang Ding, Mingyue School of Remote Sensing and Information Engineering Wuhan University Wuhan430072 China School of Science Wuhan Institute of Technology Wuhan430073 China Institute for Pattern Recognition and Artificial Intelligence Key Laboratory of Education Ministry for Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan430074 China

To overcome the main drawbacks of global minimal for active contour models (L. D. Cohen and Ron Kimmel) that the contour is only extracted partially for low SNR images, Method of boundary extraction based on Schrödinger Equation is proposed. Our Method is based on computing the numerical solutions of initial value problem for second order nonlinear Schrödinger equation by using discrete Fourier Transformation. Schrödinger transformation of image is first given. We compute the probability P(b,a) that a particle moves from a point a to another point b according to I-Type Schrödinger transformation of image and obtain boundary of object by using quantum contour model.

关键词： Initial value problems

来源：评论

学校读者我要写书评

暂无评论

image denoising using wavelet and support vector regression

Image denoising using wavelet and support vector regression

引用

International Conference on image and Graphics (ICIG)

作者： Hui Cheng Qiuze Yu Jinwen Tian Jian Liu Institute for Pattern Recognition and Aritificial Intelligence Key Laboratory of Education Ministry for Image Processing & Intelligence Control Huazhong University of Science and Technology Wuhan China

Wavelet image denoising has been well acknowledged as an important method of denoising in image processing. This paper describers a new method for the suppression of noise in image by fusing the wavelet denoising technique with support vector regression (SVR). Based on the least squares support vector machine (LS-SVM), a new denoising operators used in the wavelet domain are obtained. Simulated noise images are used to evaluate the denoising performance of the proposed algorithm along with the other wavelet-based denoising algorithm. Experimental results show that the proposed denoising method outperforms standard wavelet denoising techniques in terms of the signal-to-noise ratio and the prevented edge information in most cases. It also achieves better performance than the median filter.

关键词： image denoising Noise reduction Support vector machines Wavelet domain Wavelet transforms Wavelet analysis Support vector machine classification Wavelet coefficients Artificial intelligence image processing

来源：评论

学校读者我要写书评

暂无评论

Page segmentation using texture discrimination masks

Page segmentation using texture discrimination masks

引用

IEEE International Conference on image processing

作者： A.K. Jain Y. Zhong Pattern Recognition and Image Processing Laboratory Department of Computer Science Michigan State University East Lansing MI USA

We propose a new texture-based page segmentation algorithm which automatically extracts the text, halftone, and line-drawing regions from input greyscale document images. This approach utilizes a neural network to train a set of masks which is optimal for discriminating the three main texture classes in the page segmentation problem: halftone, background, and text and line-drawing regions. The test and line-drawing regions are further discriminated based on connectivity analysis. We have applied the algorithm to successfully segment English and Chinese document images. We also demonstrate that the masks can perform language separation (English/Chinese) when appropriately trained.

关键词： image segmentation Neural networks Gabor filters Natural languages image analysis Multi-layer neural network image texture analysis pattern recognition image processing Laboratories

来源：评论

学校读者我要写书评

暂无评论

On-line fingerprint verification

On-line fingerprint verification

引用

International Conference on pattern recognition

作者： A. Jain Lin Hong Pattern Recognition and Image Processing Laboratory Department of Computer Science Michigan State University East Lansing MI USA

We describe the design and implementation of an online fingerprint verification system which operates in two stages: (i) minutia extraction and (ii) minutia matching. An improved minutia extraction algorithm that is much faster and more accurate than our earlier algorithm has been implemented. For minutia matching, an alignment-based elastic matching algorithm has been developed. This algorithm is capable of finding the correspondences between input minutiae and the stored template without resorting to exhaustive search and has the ability to adaptively compensate for the nonlinear deformations and inexact pose transformations between finger prints. The system has been tested on two sets of finger print images captured with inkless scanners. The verification accuracy is found to be over 99% with a 15% reject rate. Typically, a complete fingerprint verification procedure takes, on an average, about 8 seconds on a SPARC 20 workstation. It meets the response time requirements of on-line verification with high accuracy.

关键词： Fingerprint recognition Access control Feature extraction Flowcharts pattern recognition image processing Laboratories Computer science pattern matching System testing

来源：评论

学校读者我要写书评

暂无评论

An image compression-encryption algorithm based on 2-D compressive sensing

引用

Journal of Computational Information Systems 2013年第24期9卷 10057-10064页

作者： Mo, Yan Zhang, Aidi Zheng, Fen Zhou, Nanrun Jiangxi Province Key Laboratory of Image Processing and Pattern Recognition Nanchang Hangkong University Nanchang 330063 China Department of Electronic Information Engineering Nanchang University Nanchang 330031 China

An image compression-encryption algorithm based on 2-D compressive sensing is proposed, which can accomplish encryption and compression simultaneously. The measurements are performed in two directi-ons and the measurement matrices are constructed as partial Hadamard matrices, which are controlled by chaos map. The proposed algorithm is sensitive to the keys and it can resist various attacks. Simulation results verify the validity and reliability of the proposed algorithm. Copyright © 2013 Binary Information Press.

关键词： Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Double Backpropagation for Training Autoencoders against Adversarial Attack

arXiv

引用

arXiv 2020年

作者： Sun, Chengjin Chen, Sizhe Huang, Xiaolin 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

Deep learning, as widely known, is vulnerable to adversarial samples. This paper focuses on the adversarial attack on autoencoders. Safety of the autoencoders (AEs) is important because they are widely used as a compression scheme for data storage and transmission, however, the current autoencoders are easily attacked, i.e., one can slightly modify an input but has totally different codes. The vulnerability is rooted the sensitivity of the autoencoders and to enhance the robustness, we propose to adopt double backpropagation (DBP) to secure autoencoder such as VAE and DRAW. We restrict the gradient from the reconstruction image to the original one so that the autoencoder is not sensitive to trivial perturbation produced by the adversarial attack. After smoothing the gradient by DBP, we further smooth the label by Gaussian Mixture Model (GMM), aiming for accurate and robust classification. We demonstrate in MNIST, CelebA, SVHN that our method leads to a robust autoencoder resistant to attack and a robust classifier able for image transition and immune to adversarial attack if combined with GMM. Copyright © 2020, The Authors. All rights reserved.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Research on Laser Measurement of 3D curved Glass Contour based on computer Vision 7

Research on Laser Measurement of 3D curved Glass Contour bas...

引用

7th International Conference on Information Science and Control Engineering, ICISCE 2020

作者： Wang, Peng Wu, Jinmeng Yan, Guilin Bian, Shuo Wuhan Institute of Technology Hubei Key Laboratory of Optical Information and Pattern Recognition Hubei Research Centre of Video Image and High Definition Projection Wuhan China School of Electrical and Information Engineering School of Mechanical and Electrical Engineering

ISBN: (纸本)9781728164069

In the mobile phone glass industry, curved glass is widely used. Whether the curved glass is measured with high efficiency and precision and whether the curved edge profile error can be evaluated directly affects the quality and service cycle of glass products. In view of the difficulty of accurate measurement and evaluation of 3D mobile phones curved glass profile, a visual measurement method of 3D mobile phones curved glass profile error based on laser scanning and shape template matching is proposed in this paper. Accurate measurement of mobile phone curved glass greatly improves the fit between curved glass and mobile phone and the efficiency of production. Therefore, this paper proposes a method for evaluating the contour degree of curved glass on mobile phones based on Open Cascade and OpenCV. This method uses the lasers and camera equipment to extract the profile outline of the curved glass, then extract the profile outline of the mobile phone curved glass model that has been drawn in 3D software. The extracted contour lines are matched by methods such as translation and rotation, and finally the distance between the corresponding points is calculated as the contour error. Experimental results show that the method is able to accurately measure the profile error and greatly reduce the measurement instability and have good robustness. © 2020 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Detection of small target in infrared image sequences using attention mechanism

Detection of small target in infrared image sequences using ...

引用

Systems and Control in Aerospace and Astronautics, 2006. ISSCAA 2006. 1st International Symposium on

作者： Xun Yao Dehua Li Xianbin Sun Institute of pattern recognition and artificial intelligence Key Laboratory of Education Ministry for Image processing & Intelligence Control Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)0780393953

The requirement of algorithm for detecting small target in infrared image sequences is not only a high rate to identify the true target and a low false alarm rate, but also the computation efficiency. By employing the selective attention mechanism, biological visual system can interpret a complex incoming image in real time with limited hardware resources. Much evidence has suggested that the biological visual system processes information in a serial strategy which rapidly selects a small relevant region in scene for further complex and time consuming analysis. In this paper, a two component computation scheme is proposed to detect dim targets in infrared image sequences. In the first process stage, an efficient method is applied to extract the potential targets which are further identified in second phase, the true targets are detected, and the spurious objects are rejected. The attention-based approach reduces the computation complexity, while the other performance aspects are not traded off. Experimental results indicate that the proposed extraction and recognition modules exhibit excellent performance of detecting small target in infrared image sequences, especially in process speed aspect.

关键词： feature extraction image sequences infrared imaging biological visual system computation complexity computation efficiency false alarm rate feature extraction image recognition modules infrared image sequences selective attention mechanism small target d

来源：评论

学校读者我要写书评

暂无评论

Multi-sensor measurement adaptive filtering algorithm in measurement uncertainty

引用

Journal of Information and Computational Science 2012年第4期9卷 843-851页

作者： Hu, Zhentao Fu, Chunling Liu, Xianxing Laboratory of Image Processing and Pattern Recognition Henan University Kaifeng 475004 China Basic Experiment Teaching Center Henan University Kaifeng 475004 China

The reliable estimation of system state in multi-sensor uncertainty is always the hot and knotty issue of nonlinear filtering theory. Aiming to the reasonable utilization of measurement information, a novel multi-sensor measurement adaptive filtering algorithm is proposed in this paper. Firstly, Combining with the construction of measurement likelihood and maximize principle, the equivalent measurement are affirmed. Next, the selection and fusion of measurement without disturbance influence are accomplished by the introduction of statistic distance among the measurements, which can realize the optimization of equivalent measurement to some extend. The new method improves the adverse influence of disturbance in multi-sensor information fusion process, and retains the litter computational complexity relative to the distributed fusion structure. The theoretical analysis and experimental results show the efficiency of the proposed algorithm. Copyright © 2012 Binary Information Press.

关键词： Extended Kalman filters

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：