检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

1,528 篇 会议
50 册 图书
18 篇 期刊文献

馆藏范围

1,596 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,241 篇 工学
- 830 篇 计算机科学与技术...
- 551 篇 软件工程
- 237 篇 光学工程
- 234 篇 电气工程
- 223 篇 信息与通信工程
- 142 篇 测绘科学与技术
- 99 篇 电子科学与技术（可...
- 82 篇 生物医学工程（可授...
- 72 篇 生物工程
- 65 篇 控制科学与工程
- 60 篇 仪器科学与技术
- 55 篇 化学工程与技术
- 50 篇 机械工程
- 45 篇 建筑学
- 45 篇 土木工程
- 41 篇 材料科学与工程（可...
- 26 篇 航空宇航科学与技...
- 24 篇 交通运输工程
989 篇 理学
- 634 篇 物理学
- 347 篇 数学
- 90 篇 统计学（可授理学、...
- 83 篇 生物学
- 53 篇 化学
- 39 篇 系统科学
332 篇 医学
- 309 篇 临床医学
- 25 篇 基础医学(可授医学...
- 20 篇 药学(可授医学、理...
- 20 篇 特种医学
157 篇 管理学
- 114 篇 图书情报与档案管...
- 51 篇 管理科学与工程(可...
18 篇 农学
15 篇 法学
14 篇 军事学
4 篇 经济学
3 篇 教育学
2 篇 文学
2 篇 艺术学

主题

136 篇 pattern recognit...
136 篇 image processing
96 篇 image segmentati...
52 篇 feature extracti...
47 篇 image fusion
46 篇 image enhancemen...
37 篇 image analysis
35 篇 image processing...
34 篇 image coding
32 篇 artificial intel...
29 篇 face recognition
29 篇 image recognitio...
27 篇 deep learning
26 篇 image registrati...
24 篇 neural networks
24 篇 image reconstruc...
23 篇 image compressio...
20 篇 computer vision
19 篇 support vector m...
18 篇 object detection

机构

24 篇 institute for pa...
15 篇 wuhan inst techn...
15 篇 wuhan inst techn...
14 篇 huazhong univ sc...
14 篇 center for image...
13 篇 huazhong univ sc...
13 篇 school of artifi...
12 篇 national key lab...
10 篇 wuhan inst techn...
10 篇 xidian univ inst...
9 篇 international in...
9 篇 hubei key labora...
9 篇 hubei engineerin...
9 篇 wuhan inst techn...
9 篇 huazhong univ sc...
8 篇 school of electr...
8 篇 key laboratory o...
7 篇 huazhong univ sc...
7 篇 state key lab. o...
7 篇 state key labora...

作者

43 篇 jiao licheng
34 篇 zhang tianxu
28 篇 hong hanyu
26 篇 tian jinwen
22 篇 sang nong
19 篇 ding mingyue
17 篇 zhang xinyu
15 篇 zhang xiuhua
14 篇 cao zhiguo
12 篇 cai chao
12 篇 liu jianguo
11 篇 shi yu
10 篇 huang zhenghua
10 篇 hua xia
9 篇 chen zhong
9 篇 wang yuehuan
9 篇 zhou chengping
9 篇 jiang hong
8 篇 tan yihua
8 篇 liu ying

语言

1,587 篇 英文
7 篇 其他
2 篇 中文

检索条件"任意字段=5th International Symposium on Multispectral Image Processing and Pattern Recognition"

共 1596 条记录，以下是1551-1560 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

A Robust BPCS-Steganography against the Visual Attack

A Robust BPCS-Steganography against the Visual Attack

引用

international Conference on Information, Communications and Signal processing

作者： M. Niimi H. Noda B. Segee Department of Systems Innovation and Informatics Kyushu Institute of Technology Lizuka Japan Electrical & Computer Engineering Department University of Maine Orono ME USA

this paper discusses a visual attack to BPCS-Steganography (Bit-Plane Complexity Segmentation-Steganography) and presents a countermeasure. BPCS categorizes each small block within cover images into either a "noise-like region" or an "informative region" by means of the binary-image feature called complexity and replaces noisy blocks with the binary patterns mapped from the bit sequences of secret data. the binary patterns must be complex because it is replacing complex regions. If the binary patterns to be inserted are simple, then the logical operation called conjugate operation is applied that transforms a simple pattern to a complex pattern. We need to keep, for each block, the flag called a conjugation flag representing whether or not conjugation had been applied to correctly extract the embedded information. In the case where the conjugation flags must be embedded within cover images, we are unable to use the complexity thresholding for the embedding of the flags. thus the flags must be embedded into a fixed area. To this effect it is easy to recognize unnatural patterns on the LSB plane of stego-images. It can be used as a signature or a distinguishing mark between natural images and images with information embedded by BPCS. We propose secure BPCS which is robust against the visual attack. It is realized by assigning the meaning of the conjugation flag to a pixel of each block and making the specific rule to embed and extract it

关键词： Robustness Steganography Data mining image segmentation Technological innovation Informatics pattern recognition Art Digital images Humans

来源：评论

学校读者我要写书评

暂无评论

A Model robustness optimization method based on adversarial sample detection 5

A Model robustness optimization method based on adversarial ...

引用

5th international Conference on Artificial Intelligence and pattern recognition, AIPR 2022

作者： Sun, Jiaze Long, Siyuan Ma, Xianyan Tang, Yanmei Xi'an University of Posts and Telecommunications Shaanxi Provincial Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an Key Laboratory of Big Data and Intelligent Computing Xi'an710121 China Xi'an University of Posts and Telecommunications Xi'an710121 China

ISBN: (纸本)9781450396899

Deep neural networks are extremely vulnerable due to the existence of adversarial samples. It is a challenging problem to optimize the robustness of the model to protect deep neural networks from the threat of adversarial samples. To improve the model robustness, an integrated detection model of adversarial samples is designed to detect the existence of adversarial samples, which consists of a multi-classification detector and five single-classification detectors to perform double-layer detection of adversarial samples and intercept the adversarial samples finally sent to the image classification model. the detection experiments were conducted on the CIFAR-10 dataset for the adversarial samples generated by five attack algorithms: FGSM, BIM, DeepFool, JSMA, and C&W, and the detection success rate for all types of adversarial samples reached over 98.96%. After that, secondary attack experiments were conducted on the model, and the detection success rate of the model for the second attack adversarial samples reached over 92.36%. It provides an efficient and robust optimization method for deep neural network models in adversarial environments. © 2022 ACM.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Acoustic emission potential in intelligent manufacturing: a sample problem

Acoustic emission potential in intelligent manufacturing: a ...

引用

IEEE international symposium on Intelligent Control (ISIC)

作者： D.M. Granata W.R. Scott E.U. Lee J. Davis Advanced Metallic & Ceramic Materials Branch Naval Air Development Center Warminster PA USA Laser & Magnetic Systems Branch Naval Air Development Center Warminster PA USA

the potential of acoustic emission (AE) as a method of intelligent process monitoring is explored. It is shown that a number of tools are available to the user of acoustic emission, making it possible to apply the technique to a variety of problems. By way of example, the authors discuss a laboratory study in which acoustic emission events from a fatigue test are monitored and a large number of selected signals are digitally recorded. the event trends and signals are analyzed in order to discriminate between acoustic events associated with material defects and those produced by other benign sources. By the use of both physical arguments and pattern recognition techniques which are empirical or statistical in nature, these results are related to the failure processes taking place within the specimen.< >

关键词： Acoustic emission Manufacturing Acoustic sensors Acoustic materials Acoustic noise Signal processing Condition monitoring Intelligent sensors Frequency Magnetic materials

来源：评论

学校读者我要写书评

暂无评论

Facial Features based recognition System using LBPH and AdaBoost

Facial Features based Recognition System using LBPH and AdaB...

引用

Smart Electronics and Communication (ICOSEC), international Conference on

作者： Mayank Srivastava Kalash Khatiyan Pratibha Dixit Department of Computer Engineering & Applications GLA University Mathura UP India

ISBN: (数字)9798331504403

ISBN: (纸本)9798331504410

Face recognition stands as a pivotal domain within computer vision, boasting myriad applications in security, identification, and biometrics. this research study proposes a face recognition system using image processing techniques with the combination of two algorithms, Local Binary pattern Histogram (LBPH) and AdaBoost. the LBPH algorithm was used to extract features from the images and create a feature vector for each face. the AdaBoost algorithm was then used to train a classifier on the feature vectors and classify new faces. After testing on the Face recognition Database, the results reveal that the fusion of LBPH and AdaBoost algorithms achieves an impressive accuracy rate of 96.15% which is better as compared to other similar algorithms. the proposed algorithm is implemented in Python to recognize faces in a dataset of images.

关键词： Histograms Accuracy image recognition Law enforcement Face recognition Feature extraction Vectors Real-time systems Classification algorithms Testing

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based image Analysis for Classification of Foot and Mouth Disease in Cattle

Deep Learning Based Image Analysis for Classification of Foo...

引用

international Conference on Inventive Research in Computing Applications (ICIRCA)

作者： R. Newlin Shebiah S. Arivazhagan Department of Electronics and Communication Engineering Centre for Image Processing and Pattern Recognition Mepco Schlenk Engineering College Sivakasi Tamilnadu India

Foot and mouth disease (FMD) poses a substantial threat to the global cattle industry, as it is a highly contagious viral infection. Timely detection and precise classification of FMD in cattle are essential for effective disease management and control. the proposed method harnesses the power of convolutional neural networks (CNNs) to automatically extract distinguishing features from cattle images and classify whether the cattle is diseased or not. Furthermore, a pre-trained architecture such as MobileNetV2 is employed and fine-tuned for FMD classification. Experiments were performed to assess the effectiveness of the proposed approach, taking into account metrics such as accuracy, precision, recall, and F1-score. the experimental results demonstrate the efficacy of proposed deep learning-based classification approach, achieving impressive accuracy rates in differentiating between healthy and FMD-infected cattle.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Post image acquisition mitigation of excitation light leakage in patterned illumination based NIR fluorescence tomography

Post image acquisition mitigation of excitation light leakag...

引用

IEEE international symposium on Biomedical Imaging

作者： M. Bartels A. Joshi J.C. Rasmussen W. Bangerth E.M. Sevick-Muraca Department of Radiology Baylor University College of Medicine Houston TX USA Department of Mathematics Texas A and M University College Station TX USA

Excitation light leakage through fluorescence filters limits the sensitivity of fluorescence tomography. We demonstrate an image processing approach for suppressing the effects of excitation light leakage from NIR fluorescence images. Multiple excitation and fluorescence emission wavelength images of a fluorescence target buried in 1 % Liposyn solution were acquired by scanning an intensity modulated and line shaped NIR excitation source over the illumination/detection surface of the tissue phantom. Excitation images were used to identify the NIR source pattern and multiple global and local filters were designed to mitigate excitation light leakage in the fluorescence images. the image correction approaches were assessed by comparing the processed fluorescence images with the output of an adaptive finite element based photon diffusion model. the results show that localized error modeling based on the median reduces leakage effects by about 44 % compared to uncorrected data.

关键词： Lighting Fluorescence Tomography Optical filters Laser excitation Lymph nodes Biomedical optical imaging Optical sensors Frequency domain analysis Imaging phantoms

来源：评论

学校读者我要写书评

暂无评论

Manifold based Morphometry applied to schizophrenia

Manifold based Morphometry applied to schizophrenia

引用

IEEE international symposium on Biomedical Imaging

作者： Ragini Verma Parmeshwar Khurd James Loughead Raquel Gur Ruben Gur Christos Davatzikos Section of Biomedical Image Analysis Department of Radiollogy University of Pennsylvania USA Section of Biomedical Image Analysis Department of Radiology Department of Neuropsychiatry University of Pennsylvania USA

the growing clinical importance of diffusion tensor imaging (DTI) in disease investigation has prompted large population studies that require computational neuroanatomic techniques for tensor processing, as conventional analysis of scalar maps of DTI does not identify the full impact of pathology. In this paper we propose a comprehensive framework called manifold based morphometry (MBM) for the computational and statistical analysis of DTI datasets, consisting of spatial normalization to a template, followed by voxel-based analysis based on embedding the tensors to a linear submanifold using kernel-based manifold learning and applying statistics in this embedded space. Regions of significant difference are identified and compared with those found with conventional voxel-based analysis of scalar maps of anisotropy and diffusivity. MBM has then been applied to the group-based statistical analysis of dataset of schizophrenia patients and controls. the comparison yields that MBM consisting of the full tensor DTI analysis reveals regions of difference that encompass regions identified by the analysis of scalar maps thereby reinforcing the comprehensive nature of the designed framework.

关键词： Diffusion tensor imaging Tensile stress Statistical analysis image analysis Pathology Diseases Data analysis Anisotropic magnetoresistance Statistical distributions pattern analysis

来源：评论

学校读者我要写书评

暂无评论

5D Imaging

5D Imaging

引用

2013第二届分析大会暨展览会

作者： Shuo Li GE Healthcare

Five-dimensional (5D) image processing has become a major challenge within the field of medical imaging. 5D images, i.e dynamic 3D images (4D) that are acquired at multiple times. A typical example would include dynamic cardiac CT scans and/or gated cardiac MRI acquired at 3-monthly intervals and dynamic cell growth and shape change in weekly intervals. 4D images provide research a great assistance on analysis of the deformation and motion. the pattern of this deformation and motion can be used for recognition and diagnosis when another dimension is added. Another dimension usually comes from atlas, template, historical data and etc. the correlations in 5th dimension (e.g. the pattern of deformation for dynamic cardiac CT) can be extracted for recognition, tracking and diagnosis. the correlation in the 5th dimension can be widely used in objects tracking and recognition using radar image, cell and sub-cell particle monitoring using microscopic image and medical diagnosis using dynamic CT or MRI.

关键词： Imaging

来源：评论

学校读者我要写书评

暂无评论

Fingerprint orientation modeling by sparse coding

Fingerprint orientation modeling by sparse coding

引用

IAPR international Conference on Biometrics (ICB)

作者： Shuxin Liu Manhua Liu Department of Educational Science and Technique Zhangzhou Normal University China Department of Instrument Science and Engineering Shanghai Jiaotong University China

Local ridge orientation field describes well the topological pattern of fingerprint ridge-valley flows. It is a rich information resource for fingerprint image processing and feature extraction in automatic fingerprint recognition algorithm. But reliable estimation of orientation field is still challenging for fingerprint images of poor quality. In this paper, we propose a method for modeling fingerprint orientation field using sparse coding. the basis functions of discrete cosine transform (DCT) are used to build the basis atoms for the representation of orientation field and l1-norm regularized optimization is used for the sparse coding of DCT atoms. Finally, orientation field is reconstructed by linear combination of sparse coefficients and DCT atoms. the proposed orientation model does not need any prior information such as the locations of singular points and it is easy to implement. More importantly, the effect of noise can be significantly reduced by sparse coding. Experimental results and comparison are presented to show the effectiveness of the proposed method for modeling orientation fields of fingerprints, especially the poor quality fingerprints.

关键词： Discrete cosine transforms Vectors image coding Mathematical model Encoding Noise image reconstruction

来源：评论

学校读者我要写书评

暂无评论

the dynamics of land cover change pattern and landscape fragmentation in Jiuzhaigou Nature Reserve, China

The dynamics of land cover change pattern and landscape frag...

引用

MIPPR 2009 - Remote Sensing and GIS Data processing and Other Applications: 6th international symposium on multispectral image processing and pattern recognition

作者： Hao, Yunqing Wang, Jinxi Jiang, Hong International Institute for Earth System Science Nanjing University Nanjing China Sichuan Academy of Forestry Chengdu China International Research Center of Spatial Ecology and Ecosystem Ecology Zhejiang Forestry University Hangzhou China

ISBN: (纸本)9780819478092

Nature reserves are facing a very challenging conflict between conservation and development today. the protection effect of Jiuzhaigou Nature Reserve has received considerable attention, especially in view of its stimulating tourism after the 1990s. Remote sensing data from 1974, 1994 and 2002 were chosen for the analysis of this reserve, since they closely represented the vegetation situation before and after felling, as well as the disturbance from the flush of tourism. We find that the quality and quantity of the forest in Jiuzhaigou Nature Reserve continues to decline, owing to the conifer area and whole forest area constantly shrinking, as well as the landscape fragmentation increasing. the rate of loss of forest in the second period (1994-2002) had showed down much than that in the first period (1974-1994), due to nature protection. Shrubland area continued to increase throughout the two periods, with an increased speed in the second period which was about 3.5 times that in the first period. the treeline was consistently retreating, contributing a total of 467.96 ha of conifer forest lost. However, the causes involved in tree mortality and the resulting regression of the treeline are not clear. In any case, under the general background of global warming, human impact undoubtedly should have direct or indirect cause dramatic consequences for the forest in this very sensitive zone, while there are many uncertainties in the behaviour of high mountain ecosystems. © 2009 Copyright SPIE - the international Society for Optical Engineering.

关键词： Global warming

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共160页 << < 151 152 153 154 155 156 157 158 159 160 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：