检索结果-内蒙古大学图书馆

3rd International Conference on Bioinformatics and Biomedical Engineering, iCBBE 2009

作者： Haifeng, Zhao Xingming, Xu Sibao, Chen Bin, Luo Key Lab of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei 230039 China

ISBN: (纸本)9781424429028

As Magnetic Resonance Imaging (MRI) is an important technology of radiological evaluation and computeraided diagnosis, the accuracy of the MR image segmentation directly influences the validity of following processing. The paper concerns medical image segmentation based on t-mixture model because of merits of the model. By analyzing the features of MR images, the main procedure of white matter segmentation of brain MR Images based on t-mixture model is outlined follows. The parameters of t-mixture model for the image are firstly estimated. Then the posterior probabilities of the pixels of the image are computed. At last, the image is segmented according to the Bayes decision rule for minimum error. Experimental results show that t-mixture model fits for medical image segmentation. ©2009 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Improving Transferability Reversible Adversarial Examples Based on Flipping Transformation 9th

Improving Transferability Reversible Adversarial Examples Ba...

引用

9th International Conference of Pioneering Computer Scientists, Engineers and Educators, ICPCSEE 2023

作者： Fang, Youqing Jia, Jingwen Yang, Yuhai Lyu, Wanli Key Lab of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei230601 China

ISBN: (纸本)9789819959679

Adding subtle perturbations to an image can cause the classification model to misclassify, and such images are called adversarial examples. Adversarial examples threaten the safe use of deep neural networks, but when combined with reversible data hiding (RDH) technology, they can protect images from being correctly identified by unauthorized models and recover the image lossless under authorized models. Based on this, the reversible adversarial example (RAE) is rising. However, existing RAE technology focuses on feasibility, attack success rate and image quality, but ignores transferability and time complexity. In this paper, we optimize the data hiding structure and combine data augmentation technology, which flips the input image in probability to avoid overfitting phenomenon on the dataset. On the premise of maintaining a high success rate of white-box attacks and the image’s visual quality, the proposed method improves the transferability of reversible adversarial examples by approximately 16% and reduces the computational cost by approximately 43% compared to the state-of-the-art method. In addition, the appropriate flip probability can be selected for different application scenarios. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Reversible Data Hiding for 3D Mesh Model Based on Block Modulus Encryption and Multi-MSB Prediction 10th

Reversible Data Hiding for 3D Mesh Model Based on Block Modu...

引用

10th International Conference of Pioneering Computer Scientists, Engineers and Educators, ICPCSEE 2024

作者： Fu, Zihao Gao, Yang Lyu, Wanli Key Lab of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei230601 China

ISBN: (纸本)9789819787456

Reversible data hiding in encrypted domain (RDH-ED) fortifies data security and privacy safeguards while upholding the original data’s integrity and accessibility. Current research on RDH-ED focuses on 2D images, while research on 3D mesh models is still immature. This paper introduces an RDH-ED method using block modulus encryption and multi-MSB prediction. Initially, the original mesh model is partitioned into non-overlapping subblocks of equal size, and then the vertices in each subblock are encrypted with the same key for additive modulus encryption, ensuring that the spatial correlation present in the original mesh subblocks remains preserved within the encrypted subblocks. Subsequently, the subblocks are disrupted one by one using the 3D Arnold Transform to enhance security. The vertices in each embeddable subblock are divided into a reference vertex and several embeddable vertices, where the multi-MSB prediction strategy is employed to allocate embedding room for each embeddable vertex. Finally, the secret information is embedded into the allocated room. Since the proposed method almost completely preserves the spatial correlation within each subblock, the achieved embedding rate surpasses that of all previous outstanding methods that rely on vacating room after encryption (VRAE). The experimental findings demonstrate that the proposed approach achieves an average embedding rate of 45.55 bits per vertex (bpv), surpassing the state-of-the-art method that achieves 25.63 bpv. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised geometric mean of Kullback-Leibler divergences for subspace selection

Semi-supervised geometric mean of Kullback-Leibler divergenc...

引用

2011 8th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2011, Jointly with the 2011 7th International Conference on Natural Computation, ICNC'11

作者： Chen, Si-Bao Wang, Hai-Xian Zhang, Xing-Yi Luo, Bin Key Lab of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei 230039 China

ISBN: (纸本)9781612841816

Subspace selection is widely adopted in many areas of pattern recognition. A recent result, named maximizing the geometric mean of Kullback-Leibler (KL) divergences of class pairs (MGMD), is a successful method for subspace selection, which can significantly reduce the class separation problem. However, in many applications, labeled data are very limited while unlabeled data can be easily obtained. The estimation of divergences of class pairs is unstable using inadequate labeled data. To take advantage of unlabeled data for subspace selection, semi-supervised MGMD (SSMGMD) is proposed using graph Laplacian as normalization. Quasi-Newton method is adopted to solve the optimization problem. Experiments on synthetic data and real image data show the validity of SSMGMD. © 2011 IEEE.

关键词： Newton-Raphson method

来源：评论

学校读者我要写书评

暂无评论

Adversarial Example Generation Method Based on Probability Histogram Equalization 42

Adversarial Example Generation Method Based on Probability H...

引用

42nd Chinese Control Conference, CCC 2023

作者： Fang, Youqing Jia, Jingwen Yang, Yuhai Lyu, Wan-Li School of Computer Science and Technology Key Lab of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei230601 China

ISBN: (纸本)9789887581543

CNNs (Convolutional Neural Networks) have a good performance on most classification tasks, but they are vulnerable when meeting adversarial examples. Research and design of highly aggressive adversarial examples can help enhance the security and robustness of CNNs. The transferability of adversarial examples is still low in black-box settings. Therefore, an adversarial example method based on probability histogram equalization, namely HE-MI-FGSM (Histogram Equalization Momentum Iterative Fast Gradient Sign Method) is proposed. In each iteration of the adversarial example generation process, the original input image is randomly histogram equalized, and then the gradient is calculated to generate adversarial perturbations to mitigate overfitting in the adversarial example. The effectiveness of the method is verified on the ImageNet dataset. Compared with the advanced method I-FGSM (Iterative Fast Gradient Sign Method) and MI-FGSM (Momentum I-FGSM), the attack success rate in the adversarial training network increased by 27.9% and 7.7% on average, respectively. © 2023 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

The classification of gene expression profile based on the adjacency matrix spectral decomposition

The classification of gene expression profile based on the a...

引用

International Conference on Computer Application and System Modeling

作者： Su, Liangliang Wang, Nian Tang, Jun Chen, Le Wang, Ruiping Education Ministry Key Laboratory of Intelligent Computing and Signal Processing Anhui University Hefei Anhui 230039 China

ISBN: (纸本)9781424472369

In the process of disease diagnosis, determining the types of disease is very important. With the development of DNA microarray technology, the research on huge gene expression profile has become the focus of disease classification. This paper presents a method of classification of gene expression profile based on the adjacency matrix spectral decomposition. First, samples are mapped to a high-dimensional space of points to construct an adjacency matrix, and we can obtain eigenvectors describing the feature of the samples by decomposing the matrix. Finally, use eigenvectors as inputs of the SVM (Support Vector Machine) and KNN (K nearest neighbor) classifiers to classify gene expression profile. In this way sample information can be completely preserved, which enables an approach to making gene expression profile from one without structural information to one with structural information. The validity of this method is verified by comparative experiments. © 2010 IEEE.

关键词： Eigenvalues and eigenfunctions

来源：评论

学校读者我要写书评

暂无评论

Novel algorithm for hand vein recognition based on Retinex method and SIFT feature analysis

Novel algorithm for hand vein recognition based on Retinex m...

引用

2011 International Conference on Electric and Electronics, EEIC 2011

作者： Wang, Hua-Bin Tao, Liang Hu, Xue-You Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei Anhui 230039 China

ISBN: (纸本)9783642217463

Based on the Retinex method and the SIFT feature analysis, this paper presents a novel algorithm for hand vein recognition. First of all, the principle of the near-infrared hand vein image acquisition is introduced. Secondly, the Retinex method is used to normalize hand vein images, and the adaptive smoothing method is selected to estimate the illumination. Then gray cosine transform is used to enhance the discrimination of the skin and the vein in hand vein images. Thirdly, the SIFT feature analysis algorithm is used to extract the feature of hand vein. Finally, the match method of two hand vein images based on SIFT is given. A hand vein recognition system in Microsoft VC6.0 is also developed and the experimental results demonstrate the high efficiency of the proposed algorithm in runtime and correct recognition rate. © Springer-Verlag Berlin Heidelberg 2011.

关键词： Cosine transforms

来源：评论

学校读者我要写书评

暂无评论

VIPLFaceNet： an open source deep face recognition SDK

引用

Frontiers of Computer Science 2017年第2期11卷 208-218页

作者： Xin LIU Meina KAN Wanglong WU Shiguang SHAN Xilin CHEN Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing 100190 China University of Chinese Academy of Sciences Beijing 100049 China

Robust face representation is imperative to highly accurate face recognition. In this work, we propose an open source face recognition method with deep representation named as VIPLFaceNet, which is a lO-layer deep convolu- tional neural network with seven convolutional layers and three fully-connected layers. Compared with the well-known AlexNet, our VIPLFaceNet takes only 20% training time and 60% testing time, but achieves 40% drop in error rate on the real-world face recognition benchmark LFW. Our VIPLFaceNet achieves 98.60% mean accuracy on LFW us- ing one single network. An open-source C＋＋ SDK based on VIPLFaceNet is released under BSD license. The SDK takes about 150ms to process one face image in a single thread on an i7 desktop CPU. VIPLFaceNet provides a state-of-the-art start point for both academic and industrial face recognition applications.

关键词： deep learning face recognition open source,VIPLFaceNet

来源：评论

学校读者我要写书评

暂无评论

Multiplicative reconstruction based on the transport of intensity equation 4

Multiplicative reconstruction based on the transport of inte...

引用

4th International Conference on Fuzzy Systems and Data Mining, FSDM 2018

作者： Cheng, Hong Wang, Jincheng Shen, Chuan Zhang, Cheng Zhang, Fen Bao, Wenxia Education Ministry Key Laboratory of Intelligent Computing and Signal Processing Anhui University HefeiAnhui230039 China

ISBN: (纸本)9781614999270

In order to effectively recover the phase information of the object and reconstruct the three-dimensional shape of the object, a multiplicative reconstruction based on the transport of intensity equation (TIE) is proposed. Firstly, combining with the relationship between the light field moment imaging and the TIE, the phase information and the first moments of the light field are solved between the two differently focused intensity images, and the phase perspective can be recovered. In this way, the phase can be observed from different slight angles, and the three-dimensional shape of the phase of the object is reconstructed in combination with the multiplicative technique . At the same time, the object is rotated at different angles for the purpose of reconstructing the three-dimensional shape of the object phase under these angles. Finally, the correctness and effectiveness of the algorithm are verified by experimental results. © 2018 The authors and IOS Press. All rights reserved.

关键词： Fuzzy systems

来源：评论

学校读者我要写书评

暂无评论

A Survey of Commonsense Knowledge Acquisition

引用

Journal of Computer Science & Technology 2013年第4期28卷 689-719页

作者：臧良俊曹聪曹亚男吴昱明曹存根 Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences University of the Chinese Academy of Sciences The Second Lab Institute of Information Engineering Chinese Academy of Sciences

Collecting massive commonsense knowledge （CSK） for commonsense reasoning has been a long time standing challenge within artificial intelligence research. Numerous methods and systems for acquiring CSK have been developed to overcome the knowledge acquisition bottleneck. Although some specific commonsense reasoning tasks have been presented to allow researchers to measure and compare the performance of their CSK systems, we compare them at a higher level from the following aspects： CSK acquisition task （what CSK is acquired from where）, technique used （how can CSK be acquired）, and CSK evaluation methods （how to evaluate the acquired CSK）. In this survey, we first present a categorization of CSK acquisition systems and the great challenges in the field. Then, we review and compare the CSK acquisition systems in detail. Finally, we conclude the current progress in this field and explore some promising future research issues.

关键词： commonsense knowledge knowledge acquisition knowledge representation and reasoning

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：