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

1,444 篇 会议
30 篇 期刊文献
16 册 图书

馆藏范围

1,490 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,167 篇 工学
- 933 篇 计算机科学与技术...
- 396 篇 软件工程
- 164 篇 电气工程
- 137 篇 光学工程
- 121 篇 信息与通信工程
- 96 篇 生物医学工程（可授...
- 91 篇 控制科学与工程
- 90 篇 生物工程
- 70 篇 机械工程
- 69 篇 仪器科学与技术
- 44 篇 电子科学与技术（可...
- 35 篇 化学工程与技术
- 32 篇 材料科学与工程（可...
- 15 篇 土木工程
- 14 篇 力学（可授工学、理...
- 13 篇 建筑学
394 篇 理学
- 220 篇 数学
- 181 篇 物理学
- 103 篇 生物学
- 74 篇 统计学（可授理学、...
- 37 篇 化学
- 13 篇 系统科学
330 篇 医学
- 323 篇 临床医学
- 33 篇 基础医学(可授医学...
- 25 篇 药学(可授医学、理...
107 篇 管理学
- 69 篇 图书情报与档案管...
- 42 篇 管理科学与工程(可...
37 篇 艺术学
- 37 篇 设计学（可授艺术学...
15 篇 农学
- 12 篇 作物学
10 篇 法学
- 10 篇 社会学
5 篇 教育学
3 篇 经济学
2 篇 军事学

主题

142 篇 pattern recognit...
110 篇 image segmentati...
94 篇 feature extracti...
83 篇 image processing
63 篇 image analysis
56 篇 image color anal...
41 篇 principal compon...
40 篇 face recognition
38 篇 image recognitio...
31 篇 support vector m...
30 篇 deep learning
30 篇 local binary pat...
30 篇 image reconstruc...
29 篇 computer vision
29 篇 shape
27 篇 image classifica...
26 篇 image enhancemen...
26 篇 pattern matching
25 篇 training
24 篇 neural networks

机构

7 篇 institute of aut...
5 篇 inesc tec porto
5 篇 univ porto fac e...
4 篇 guangdong univer...
4 篇 univ porto fac c...
4 篇 south china univ...
4 篇 microsoft resear...
4 篇 king fahd univer...
4 篇 shanghai jiao to...
3 篇 córdoba
3 篇 comp vis ctr bar...
3 篇 department of co...
3 篇 tarbiat modares ...
3 篇 univ porto fac e...
3 篇 inst res fundame...
3 篇 chitkara univers...
3 篇 universidade de ...
3 篇 harvard univ sch...
3 篇 ryerson univ dep...
3 篇 univ alicante ui...

作者

11 篇 cardoso jaime s.
9 篇 vidal enrique
8 篇 calvo-zaragoza j...
8 篇 oliveira helder ...
6 篇 lee seong-whan
6 篇 suen c.y.
5 篇 casacuberta fran...
5 篇 marques jorge s.
5 篇 pina pedro
4 篇 shengli xie
4 篇 pietikainen matt...
4 篇 bioucas-dias jos...
4 篇 dongbin zhao
4 篇 c.y. suen
4 篇 forero manuel g.
4 篇 yuanqing li
4 篇 el-sayed m. el-a...
4 篇 derong liu
4 篇 weickert joachim
4 篇 singh s

语言

1,454 篇 英文
33 篇 其他
6 篇 中文
1 篇 日文

检索条件"任意字段=3rd Iberian Conference on Pattern Recognition and Image Analysis"

共 1490 条记录，以下是281-290 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：

3D Non-rigid Registration of Deformable Object Using GPU 9th

3D Non-rigid Registration of Deformable Object Using GPU

引用

9th iberian conference on pattern recognition and image analysis (IbPRIA)

作者： Lee, Junesuk Kim, Eung-su Park, Soon-Yong Kyungpook Natl Univ Sch Comp Sci & Engn Daegu South Korea Kyungpook Natl Univ Sch Elect Engn Daegu South Korea

ISBN: (纸本)9783030313326;9783030313319

We propose a method to quickly process non-rigid registration between 3D deformable data using a GPU-based non-rigid ICP(Iterative Closest Point) algorithm. In this paper, we sequentially acquire whole-body model data of a person moving dynamically from a single RGBD camera. We use Dense Optical Flow algorithm to find the corresponding pixels between two consecutive frames. Next, we select nodes to estimate 3D deformation matrices by uniform sampling algorithm. We use a GPU-based non-rigid ICP algorithm to estimate the 3D transformation matrices of each node at high speed. We use non-linear optimization algorithm methods in the non-rigid ICP algorithm. We define energy functions for an estimate the exact 3D transformation matrices. We use a proposed GPU-based method because it takes a lot of computation time to calculate the 3D transformation matrices of all nodes. We apply a 3D transformation to all points with a weight-based affine transformation algorithm. We demonstrate the high accuracy of non-rigid registration and the fast runtime of the non-rigid ICP algorithm through experimental results.

关键词： 3D reconstruction Non-rigid registration Non-rigid ICP Deformable registration GPU

来源：评论

学校读者我要写书评

暂无评论

A Pedestrian Detection Method Combining I-HOG and Sobel-ULBP Features 3

A Pedestrian Detection Method Combining I-HOG and Sobel-ULBP...

引用

3rd International conference on E-Business, Information Management and Computer Science, EBIMCS 2020

作者： Huang, Xiaoyong Zhang, Yi Zheng, Jing Wang, Zhenmei Cai, Xiaogang College of Information Science and Engineering Guilin University of Technology Guilin Guangxi541006 China

ISBN: (纸本)9781450389099

The previous Histogram of Oriented Gradient (HOG) and Local Binary pattern (LBP) feature fusion pedestrian detection method has disadvantages such as sensitivity to noise, serious spectral information loss, high feature dimension and much redundant information, etc. This paper proposes a pedestrian detection method based on the feature fusion of Improved Histogram of Oriented Gradient (I-HOG) and Sobel Uniform pattern LBP (Sobel-ULBP). By inserting Gaussian filtering algorithm to complete the pre-processing of the image to be extracted, the image transition is uniform and smooth, details are eliminated, and the noise generated by compression and transmission is removed. Subsequently, Sobel edge detection is performed on the image to reduce the influence of pedestrian background and clothing texture and other information, and highlight the pedestrian silhouette. Because the optimized I-HOG features and Sobel-ULBP texture feature obtained by calculation have higher feature dimensions. Therefore, the principal component analysis algorithm (PCA) is used to reduce the dimensions of the two features, and then the two features are fused in series, and finally the fused features are sent to the support vector machine (SVM) for training to obtain a pedestrian classifier. A simulation experiment was carried out on the INRIA pedestrian database, and the results show that the method has improved recall rate and pedestrian recognition rate. © 2020 ACM.

关键词： Local binary pattern

来源：评论

学校读者我要写书评

暂无评论

Cleaning assessment in endoscopic esophageal images using U-Net and a classification model 3

Cleaning assessment in endoscopic esophageal images using U-...

引用

3rd International conference on Multimedia analysis and pattern recognition, MAPR 2020

作者： Ha, Van Kien Manh, Xuan Huy Dao, Viet Hang Nguyen, Phuc Binh Hoang, Bao Long Vu, Hai International Research Institute Mica Hanoi University of Science and Technology Viet Nam Hanoi Medicine University Internal Medicine Faculty Viet Nam Inst. of Gastroenterology and Hepatology Hanoi Viet Nam

ISBN: (纸本)9781728165554

The presence of water bubbles, foam, mucus or residual food in the gastrointestinal tract is a common problem during Upper gastrointestinal endoscopy (UGIE). This condition could cause difficulties to detect lesions as well as perform interventions if required for medical doctors. In every medical center all over the world, analyzing endoscopic images with bubbles is becoming a vital practical issue. In this paper, we propose an automatic scheme to segment regions of water bubbles thanks to the recent advantages of a deep neural network - U-net. Based on the segmentation results, we construct a classification model to evaluate the cleaning level of the current examined images. The classification model utilizes features which directly extracted from the segmented areas such as the number of the water bubbles, their concentrating distribution or scattering in the current view. The proposed method is evaluated on a testing dataset validated by the endoscopists. Accuracy of the quality assessment by the proposed techniques achieves the rate of 90%. Therefore, the proposed method presents a feasible tool for automatically eliminating of unclean UGIE images. © 2020 IEEE.

关键词： image classification

来源：评论

学校读者我要写书评

暂无评论

Estimation of Sulfonamides Concentration in Water Based on Digital Colourimetry 9th

Estimation of Sulfonamides Concentration in Water Based on D...

引用

9th iberian conference on pattern recognition and image analysis (IbPRIA)

作者： Carvalho, Pedro H. Bessa, Silvia Silva, Ana Rosa M. Peixoto, Patricia S. Segundo, Marcela A. Oliveira, Helder P. INESC TEC Inst Syst & Comp Engn Technol & Sci Porto Portugal Univ Porto Fac Sci Porto Portugal Univ Porto Fac Pharm LAQV REQUIMTE Porto Portugal

ISBN: (纸本)9783030313326;9783030313319

Overuse of antibiotics is causing the environment to become polluted with them. This is a major threat to global health, with bacteria developing resistance to antibiotics because of it. To monitor this threat, multiple antibiotic detection methods have been developed;however, they are normally complex and costly. In this work, an affordable, easy to use alternative based on digital colourimetry is proposed. Photographs of samples next to a colour reference target were acquired to build a dataset. The algorithm proposed detects the reference target, based on binarisation algorithms, in order to standardise the collected images using a colour correction matrix converting from RGB to XYZ, providing a necessary colour constancy between photographs from different devices. Afterwards, the sample is extracted through edge detection and Hough transform algorithms. Finally, the sulfonamide concentration is estimated resorting to an experimentally designed calibration curve, which correlates the concentration and colour information. Best performance was obtained using Hue colour, achieving a relative standard deviation value of less than 3.5%.

关键词： Digital colourimetry Colour correction image Segmentation

来源：评论

学校读者我要写书评

暂无评论

Sampling-Free Variational Inference for Neural Networks with Multiplicative Activation Noise 43rd

Sampling-Free Variational Inference for Neural Networks with...

引用

43rd DAGM German conference on pattern recognition, DAGM GCPR 2021

作者： Schmitt, Jannik Roth, Stefan Department of Computer Science TU Darmstadt Darmstadt Germany hessian.AI Darmstadt Germany

ISBN: (纸本)9783030926588

To adopt neural networks in safety critical domains, knowing whether we can trust their predictions is crucial. Bayesian neural networks (BNNs) provide uncertainty estimates by averaging predictions with respect to the posterior weight distribution. Variational inference methods for BNNs approximate the intractable weight posterior with a tractable distribution, yet mostly rely on sampling from the variational distribution during training and inference. Recent sampling-free approaches offer an alternative, but incur a significant parameter overhead. We here propose a more efficient parameterization of the posterior approximation for sampling-free variational inference that relies on the distribution induced by multiplicative Gaussian activation noise. This allows us to combine parameter efficiency with the benefits of sampling-free variational inference. Our approach yields competitive results for standard regression problems and scales well to large-scale image classification tasks, e.g. imageNet. © 2021, Springer Nature Switzerland AG.

关键词： Uncertainty analysis

来源：评论

学校读者我要写书评

暂无评论

Infrared Small Target Detection Based on Prior Constraint Network and Efficient Patch-Tensor Model 3rd

Infrared Small Target Detection Based on Prior Constraint Ne...

引用

3rd Chinese conference on pattern recognition and Computer Vision (PRCV)

作者： Nie, Chang Wang, Huan Lu, Ali Nanjing Univ Sci & Technol 200 Xiaolingwei Nanjing Peoples R China Nanjing Inst Technol Dept Comp Engn Lab Multimedia Nanjing Peoples R China

ISBN: (纸本)9783030606381;9783030606398

Infrared small target detection (ISTD) is a key technology in the field of infrared detection and has been widely used in infrared search and tracking systems. In this paper, a novel ISTD approach based on a prior constraint network (PCN) and an efficient patch-tensor model (EPT) is proposed. Firstly, the PCN trained by numerous synthetic image patches is employed to obtain the preliminary segmentation result of small targets, which is later used as a prior constraint. Then the EPT model deals with the target detection problem by solving an optimization problem of recovering low-rank and sparse tensor. Next, the prior constraint is further applied to the target component of the EPT model as a regularization. Finally, the joint PCN-EPT model can be solved efficiently by the Alternating Direction Multiplier Method, and the targets are obtained by applying a simple adaptive threshold segmentation to the obtained target component from the PCN-EPT. Experimental results on multiple real datasets show that the proposed model outperforms the state-of-the-art.

关键词： Infrared small target detection Prior constraint network Robust principal component analysis Low-rank and sparse decomposition

来源：评论

学校读者我要写书评

暂无评论

VH3D-LSFM: Video-Based Human 3D Pose Estimation with Long-Term and Short-Term Pose Fusion Mechanism 3rd

VH3D-LSFM: Video-Based Human 3D Pose Estimation with Long-Te...

引用

3rd Chinese conference on pattern recognition and Computer Vision (PRCV)

作者： Deng, Wenjin Zheng, Yinglin Li, Hui Wang, Xianwei Wu, Zizhao Zeng, Ming Xiamen Univ Sch Informat Xiamen Peoples R China Hangzhou Dianzi Univ Hangzhou Peoples R China

ISBN: (纸本)9783030606329;9783030606336

Following the success of 2D human pose estimation from a single image, a lot of work focus on video-based 3D human pose estimation by exploiting temporal information. In this scenario, several recent works have achieved significant advances via Temporal Convolution Network (TCN). However, the current TCN fashion suffers from lacking local coherence caused by excessive dependence on local frames and limited local dynamic range, failing to estimate poses correctly in real scenes, especially that with high-speed motions. To tackle this problem, we design a Long-term Bank to select and collect candidate key poses, and further provide a LSFM (Long-term and Short-term pose Fusion Mechanism) to integrate long-term pose information into the short-term convolution window, thus to enhance the temporal coherence of local neighbor frames. Experimental results and ablation studies demonstrate that the proposed approach significantly promotes the accuracy and robustness of the state-of-the-art method.

关键词： 3D human pose estimation Video analysis

来源：评论

学校读者我要写书评

暂无评论

Hand detection and segmentation using multimodal information from Kinect 3

Hand detection and segmentation using multimodal information...

引用

3rd International conference on Multimedia analysis and pattern recognition, MAPR 2020

作者： Pham, Van-Tien Le, Thi-Lan Tran, Thanh-Hai Nguyen, Thanh Phuong Modelling and Simulation Centre Viettel High Technology Industries Corporation Viet Nam School of Electronics and Telecommunications Hanoi University of Science and Technology Viet Nam International Research Institute Mica Hanoi University of Science and Technology Viet Nam University of Toulon Aix Marseille University Cnrs Lis Marseille France

ISBN: (数字)9781728165554

ISBN: (纸本)9781728165554

Nowadays, hand gestures are becoming one of the most natural and intuitive ways of communication between human and computer. To this end, a complex process including hand gesture acquisition, hand detection, gesture representation and recognition must be carried out. This paper presents a method that detects hand and segments hand regions from images captured by a Kinect sensor. As Kinect sensor provides not only RGB images as conventional camera, but also depth and skeleton, in our work, we incorporate multi-modal data from Kinect to deal with hand detection and segmentation. Specifically, we use skeleton to approximately determine hand palm. Then a skin based detector will be applied to discard non-skin pixels from the region of interest. Using depth data helps to limit the human body regions and remove false positive regions from the previous steps. Finally, morphological operations will be applied to fill holes in the hand region. The main advantage of this method is very easy to implement and it performs in real-time on an ordinary computer. We evaluate the proposed method on a dataset of hand gestures captured from different viewpoints. Experiment shows that it provides reasonable accuracy at very high frame rate. It also produces comparable performance in comparison with deep learning based methods. © 2020 IEEE.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Wilms' Tumor in Childhood: Can pattern recognition Help for Classification? 23rd

Wilms' Tumor in Childhood: Can Pattern Recognition Help for ...

引用

23rd conference on Medical image Understanding and analysis (MIUA)

作者： Muller, Sabine Weickert, Joachim Graf, Norbert Saarland Univ Dept Pediat Oncol & Hematol Med Ctr Homburg Germany Saarland Univ Math Image Anal Grp Campus E1-7 Saarbrucken Germany

ISBN: (纸本)9783030393434;9783030393427

Wilms' tumor or nephroblastoma is a kidney tumor and the most common renal malignancy in childhood. Clinicians assume that these tumors develop from embryonic renal precursor cells - sometimes via nephrogenic rests or nephroblastomatosis. In Europe, chemotherapy is carried out prior to surgery, which downstages the tumor. This results in various pathological subtypes with differences in their prognosis and treatment. First, we demonstrate that the classical distinction between nephroblastoma and its precursor lesion is error prone with an accuracy of 0.824. We tackle this issue with appropriate texture features and improve the classification accuracy to 0.932. Second, we are the first to predict the development of nephroblastoma under chemotherapy. We use a bag of visual model and show that visual clues are present that help to approximate the developing subtype. Last but not least, we provide our data set of 54 kidneys with nephroblastomatosis in conjunction with 148 Wilms' tumors.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

Automatic Data Generation for Deep Learning Model Training of image Classification used for Augmented Reality on Pre-school Books 3

Automatic Data Generation for Deep Learning Model Training o...

引用

3rd International conference on Multimedia analysis and pattern recognition, MAPR 2020

作者： Le, Huy Nguyen, Minh Nguyen, Quan Nguyen, Hoa Yan, Wei Qi School of Engineering Computer and Mathematical Sciences Auckland University of Technology New Zealand

ISBN: (数字)9781728165554

ISBN: (纸本)9781728165554

Nowadays, Augmented Reality (AR) has rightfully been taking as one of the leading position. Still, there are many different AR markers with different encryption and decryption methods which provide the users with an excellent capability to augment computer graphics generated virtual information onto real-world objects (e.g. text-book pictures or diagrams). However, the users need to choose which marker provider that matches their needs and create suitable markers based on the chosen provider's requirements. 'Is it worth to re-print the entire existing books in-order to add AR functions?'. In this paper, we describe a new architecture to set up and present AR experiences by applying the benefit of deep learning (DL), the power of smart devices, and the flexibility of the Client-Server Architecture of the Internet. To set up, photos of pages in a textbook (but not limited to all pages) are uploaded to our server. For each page, the server will automatically generate different 3D views (thousands with different light conditions and perspectives) of the pages to form a sufficiently large enough dataset. They are then trained with a chosen convolutional neural network such as Alexnet, GoogleNet, VGG, GoogLeNet, or ResNet. The obtained model is then stored and can be loaded back to the client to serve as a classification process on a web browser using ***, to recognise pages of the book. *** is capable of running on smart devices with their built-in cameras;the recognised page will be used to specify which 3D graphics is displaying on top the page. This novel AR marker generating method is not only capable of keeping the original images of the books but also believed to achieve a higher detection accuracy. Thus, it is a promising, low-cost AR approach to be used in many areas, including education and training. © 2020 IEEE.

关键词： Augmented reality

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149页 << < 25 26 27 28 29 30 31 32 33 34 > >>

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：