检索结果-内蒙古大学图书馆

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

Learning with Explicit Shape Priors for Medical image Segmentation

arXiv

引用

arXiv 2023年

作者： You, Xin He, Junjun Yang, Jie Gu, Yun The Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai200240 China Shanghai AI Laboratory Shanghai200240 China

Medical image segmentation is a fundamental task for medical image analysis and surgical planning. In recent years, UNet-based networks have prevailed in the field of medical image segmentation. However, convolution-neural networks (CNNs) suffer from limited receptive fields, which fail to model the long-range dependency of organs or tumors. Besides, these models are heavily dependent on the training of the final segmentation head. And existing methods can not well address these two limitations at the same time. Hence, in our work, we proposed a novel shape prior module (SPM), which can explicitly introduce shape priors to promote the segmentation performance of UNet-based models. The explicit shape priors consist of global and local shape priors. The former with coarse shape representations provides networks with capabilities to model global contexts. The latter with finer shape information serves as additional guidance to boost the segmentation performance, which relieves the heavy dependence on the learnable prototype in the segmentation head. To evaluate the effectiveness of SPM, we conduct experiments on three challenging public datasets. And our proposed model achieves state-of-the-art performance. Furthermore, SPM shows an outstanding generalization ability on classic CNNs and recent Transformer-based backbones, which can serve as a plug- and-play structure for the segmentation task of different datasets. Source codes are available at https://***/AlexYouXin/Explicit-Shape-Priors Copyright © 2023, The Authors. All rights reserved.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

A new approach of color quantization based on ant colony clustering algorithm

A new approach of color quantization based on ant colony clu...

引用

International Conference on Information Technology: Coding and Computing (ITCC)

作者： Xinrong Hu Tianzhen Wang Dehua Li Institute for Pattern Recognition and Artificial Intelligence State Education Commission Laboratory Image Processing and Intelligence Control Huazhong University of Science and Technology Wuhan China Institute of Image Processing Wuhan University of Technology China

ISBN: (纸本)0769523153

Color quantization is wildly exploited for many applications especially in the fields of computer graphics and image processing. After studying the approaches of color clustering, a new approach based on ant colony clustering algorithm applied in color image quantization is proposed in the paper. According to the picking up-dropping theory, a promoted ant algorithm is applied to group colors into certain clusters in RGB space. It finishes color quantization after colors mapping of every pixel. Our experiment shows that the algorithm proposed in this paper has rather good performance with an excellent robustness, a less time consumption, and a simple realization.

关键词： Quantization Clustering algorithms Information technology

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

Ant Colony Optimization Algorithm for Feature Selection and Classification of Multispectral Remote Sensing image

Ant Colony Optimization Algorithm for Feature Selection and ...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Lintao Wen Qian Yin Ping Guo Image Processing and Pattern Recognition Laboratory Beijing Normal University Beijing China School of Computer Science and Technology Beijing Institute of Technology Beijing China

In classification of a multispectral remote sensing image, it is usually difficult to obtain higher classification accuracy if we only consider the image's spectral feature or texture feature alone. In this paper, we present a new approach by applying the Ant Colony Optimization (ACO) algorithm to find a multi-feature vector composed of spectral and texture features in order to get a better result in the classification. The experimental results show that ACO algorithm is helpful in subset searching of the features used to classify the multispectral remote sense image. Using the combination of the spectral and texture features obtained by ACO in classification always produces a better accuracy.

关键词： Ant colony optimization Remote sensing Remote monitoring Multispectral imaging image analysis Data mining Feature extraction Entropy image processing pattern recognition

来源：评论

学校读者我要写书评

暂无评论

An improved convex programming model for the inverse problem in intensity-modulated radiation therapy

引用

International Journal of Performability Engineering 2018年第5期14卷 871-884页

作者： Lan, Yihua Zhang, Xingang Zhang, Jianyang Wang, Yang Hung, Chih-Cheng School of Computer and Information Technology Nanyang Normal University Nanyang473061 China Institute of Image Processing and Pattern Recognition Nanyang Normal University Nanyang473061 China Radiology Department Central Hospital of Nanyang Nanyang473061 China Laboratory for Machine Vision and Security Research College of Computing and Software Engineering Kennesaw State University - Marietta Campus 1100 South Marietta Parkway MariettaGA30067-2896 United States

Intensity modulated radiation therapy technology (IMRT) is one of the main approaches in cancer treatment because it can guarantee the killing of cancer cells while optimally protecting normal tissue from complications. Inverse planning, which is the core component of the entire IMRT system, is mainly based on accurate mathematical modeling and associated fast solving methods. In inverse planning, the fluence map optimization, which considers the multi-leaf collimator (MLC) modulation, is the current research focus. Although the hitting constrain problem with the unidirectional movement of leaf-sweeping has been solved, our goal is to solve the hitting constrain problem with the bidirectional movement of leaf-sweeping. In this study, we propose a non-synchronized type to solve the hitting constrain problem with the bidirectional movement of leaf-sweeping schemes for IMRT. In solving this problem, a new mathematical model is proposed under the framework of convex programming. The advantage of the convex model is to avoid the uncertainty and inaccuracy that occurs in the non-convex programming solving process. Experimental results for two clinical testing cases show that under the same condition of total number of monitoring units, the new proposed model produces better dose distribution than those of the total variance and quadratic models. © 2018 Totem Publisher, Inc. All rights reserved.

关键词： Convex optimization

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

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

Motion Planning and Tracking Control Method Based on CoppeliaSim for UGV in Irregular Terrain

Motion Planning and Tracking Control Method Based on Coppeli...

引用

WRC Symposium on Advanced Robotics and Automation (WRC SARA)

作者： Jiale Huang Zhihua Chen Yongbo Zhong Wenrui Zeng Chuanmin Ji key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition and MOE Key Lab of Nondestructive Testing Technology Nanchang Hangkong University Nanchang China

Path planning and tracking algorithms are one of the cores of autonomous navigation technology for unmanned ground vehicle (UGV). In this paper, a local obstacle avoidance method based on event-triggered control is proposed to ensure that the UGV avoids obstacles in the tracking process. First, the path planning and tracking control problem of the UGV is modeled and formulated. Second, the improvement and logical correlation of the relevant algorithms are described in detail. Finally, ajoint simulation of MATLAB and V-rep is performed. The simulation results show that event-triggered control can largely improve the reliability of the UGV path planning and tracking process, and verify the effectiveness of the algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparative studies of Feature Extraction methods with application to face recognition

Comparative studies of Feature Extraction methods with appli...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Yunfei Jiang Ping Guo Laboratory of Image Processing and Pattern Recognition Beijing Normal University Beijing China School of Computer Science and Technology Beijing Institute of Technology Beijing China

In face recognition, the dimensionality of raw data is very high, dimension reduction (feature extraction) should be applied before classification. There exist several feature extraction methods, commonly used are principle component analysis (PCA) and linear discriminant analysis (LDA) techniques. In this paper, we present a comparative study of some feature extraction methods for face recognition in the same conditions. The methods evaluated here include eigenfaces, kernel principal component analysis (KPCA), fisherfaces, direct linear discriminant analysis (D-LDA), regularized linear discriminant analysis (R-LDA), and kernel direct discriminant analysis (KDDA). For the purpose of comparison on feature extraction methods, we adopt nearest neighbor (NN) algorithm from existed classifiers of face recognition, since this classifier is common and simpleness. Empirical studies are conducted to evaluate these feature extraction methods with images from ORL Face Database, and it is found that in most cases LDA-based methods are efficient than PCA-based ones.

关键词： Feature extraction Face recognition Linear discriminant analysis Principal component analysis Kernel pattern recognition Nearest neighbor searches Neural networks Face detection image databases

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：