检索结果-内蒙古大学图书馆

International conference on pattern recognition

作者： Jiayong Zhang Xiaoqing Ding Changsong Liu OCR Laboratory Department of Electronic Engineering Tsinghua University China

ISBN: (纸本)0769507506

Both efficient representation and robust classification are essential to high-performance cursive offline handwritten chinese character recognition. A novel multi-scale feature extraction method is presented based on the information entropy theory. Feature detection and compression are thus combined into an integrated optimization process. A series of optimal feature-spaces are constructed at varying values of the scale parameter and the best one is obtained with the maximum LDA criterion over the scale interval. For more robust classification, we introduce a structure into the Mahalanobis distance classifier and strike the balance between machine capacity and the performance on the training data in light of the ideas of structural risk minimization. A high accuracy recognition system is developed based on the new methods and for the first time, 4 widely different databases ranging from regular to completely unconstrained with several structural distortions and stroke connections are fully tested. the accuracies of 99.S% on regular database and 88.4% on cursive one at the speed of over 40 characters/s are achieved.

关键词： Feature extraction Robustness Databases Character recognition Information entropy computer vision Linear discriminant analysis Training data Risk management System testing

来源：评论

学校读者我要写书评

暂无评论

Robust Augmentations for Small Object Detection of Aerial Images

Robust Augmentations for Small Object Detection of Aerial Im...

引用

IEEE International conference on Network Infrastructure and Digital Content (IC-NIDC)

作者： Weiyu Xiong Zhanyu Ma Yi-Zhe Song Pattern Recognition and Intelligent Systems Lab School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing China Beijing Academy of Artificial Intelligence Beijing China SketchX CVSSP University of Surrey London United Kingdom

ISBN: (纸本)9781665405836

Object detection is one of the most fundamental but important computer vision tasks. However, small object detection remains an unsolved challenge due to insufficient detailed appearances and additional noises. Meanwhile, aerial images and intelligent transportation systems are under the restriction of difficulties such as dense object arrangement, a large number of small objects, and different perspectives, compared with natural images. To deal with these problems, an adversarial-like data augmentation training is proposed in this paper to narrow the data gap between remote sensing images and natural ones. the difficulty of the remote sensing object detection is verified and analyzed firstly by the classic single-stage anchor-based detector RetinaNet. then, the multi-scale and data augmentations are introduced to alleviate the mismatch between general detector training and aerial images based on the anchor-free state-of-the-art (SOTA) model FCOS. Experiments on the remote sensing dataset, NWPU VHR10, demonstrate the quasi-antagonism data augmentation method improves the both anchor-based and anchor-free SOTA detectors for natural images with significant margins and shows the effectiveness on aerial images, especially small objects.

关键词： Training Image resolution conferences Object detection Detectors Data models Noise measurement

来源：评论

学校读者我要写书评

暂无评论

Face Detection in Complex Background Based on Gaussian Models and Neural Networks

Face Detection in Complex Background Based on Gaussian Model...

引用

2006 8th International conference on Signal Processing

作者： Qi Li Hongbing Ji School of Electronic Engineering Xidian University

Face detection is a valuable topic in the fields of pattern recognition and computer vision.A Gaussian model and neural network based human face detection method is proposed for color images in complex ***,Gaussian models are used for the fast extraction of skin-color and lip-color ***, the face candidates are rotated in image plane to be ***,a neural network determines whether a candidate area is a human face or *** experimental results illustrate the effectiveness of the method.

关键词： Gaussian image Face Detection in Complex Background Based on Gaussian Models and Neural Networks

来源：评论

学校读者我要写书评

暂无评论

An Interactive Color Harmony Design System Based on Color vision Law

An Interactive Color Harmony Design System Based on Color Vi...

引用

the 7th International conference on computer-Aided Industrial Design and Conceptual Design (CAID&CD’2006)

作者： Zhang Quan, Lu Changde, Yu Mingjiu Industrial Design Department, Northwestern Polytechnical University, China

Following color vision law is a good method for color harmony design. But there are two questions in dire need of resolve. First, the color models such as L*a*b*, RGB and HSV in actual CAD system are not uniform in vision;second there are short of harmony control techniques. In this article, a visual perceptual color model, i.e. HVC model is established based on artificial neural network (ANN). the ANN training data come from the Munsell system and chinese color system. And the comparison between the HVC model and the L*a*b* model in Photoshop software is presented. then, a set of harmony control algorithms are discussed in detail. Lastly, an interactive color harmony design system (ICHDS) is developed based on the HVC model and the harmony algorithms. Application testified that ICHDS provides effective color harmony design tools.

关键词： Artificial neural network (ANN), Color harmony design, Color vision law, Munsell system

来源：评论

学校读者我要写书评

暂无评论

Graph Structured Network for Image-Text Matching

Graph Structured Network for Image-Text Matching

引用

conference on computer vision and pattern recognition (CVPR)

作者： Chunxiao Liu Zhendong Mao Tianzhu Zhang Hongtao Xie Bin Wang Yongdong Zhang Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China University of Science and Technology of China Hefei China Xiaomi AI Lab Beijing China

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

Image-text matching has received growing interest since it bridges vision and language. the key challenge lies in how to learn correspondence between image and text. Existing works learn coarse correspondence based on object co-occurrence statistics, while failing to learn fine-grained phrase correspondence. In this paper, we present a novel Graph Structured Matching Network (GSMN) to learn fine-grained correspondence. the GSMN explicitly models object, relation and attribute as a structured phrase, which not only allows to learn correspondence of object, relation and attribute separately, but also benefits to learn fine-grained correspondence of structured phrase. this is achieved by node-level matching and structure-level matching. the node-level matching associates each node with its relevant nodes from another modality, where the node can be object, relation or attribute. the associated nodes then jointly infer fine-grained correspondence by fusing neighborhood associations at structure-level matching. Comprehensive experiments show that GSMN outperforms state-of-the-art methods on benchmarks, with relative Recall@1 improvements of nearly 7% and 2% on Flickr30K and MSCOCO, respectively. Code will be released at: https://***/CrossmodalGroup/GSMN.

关键词： Visualization Dogs Semantics Sparse matrices Image edge detection Learning systems Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Power Flow Analysis and Visualization in Smart Grid 8

引用

FTRA 8th International conference on Multimedia and Ubiquitous Engineering (MUE)

作者： Wu, Dan Wu, Rundong Chen, Zhijian Xie, Wenyan Huang, Xiang Sheng, Bin Liu, Dawei Shanghai Jiao Tong Univ Dept Comp Sci & Engn Shanghai 200030 Peoples R China Guangdong Elect Power Design Inst Network & Informat Branch Guangzhou Guangdong Peoples R China Chinese Acad Sci Inst Software State Key Lab Comp Sci Beijing Peoples R China Xian Jiaotong Liverpool Univ Dept Comp Sci & Software Engn Suzhou Peoples R China

ISBN: (纸本)9783642549007;9783642548994

With the development of society, the requirement for security and economy in power grid is increasing. Hence, the concept of smart grid has been proposed. Smart grid is a new power network, which integrates the technology of advanced sensor measuring, network, communication, calculation and intelligent control. the application of visualization is a significant part in smart grid. On the other hand, the analysis of power flow in power grid is a traditional part in power system. this paper combines power flow analysis with visualization technology in one platform through C programming language. A detailed explanation is given on how to achieve power flow analysis through the classic Newton-Raphson algorithm and model the power grid with OpenGL programming method in computer. the platform can achieve the function of modeling a power system and dynamic effect in the line.

关键词： Smart grid power flow analysis visualization Newton-Raphson algorithm OpenGL

来源：评论

学校读者我要写书评

暂无评论

Multi-view anal fistula disease diagnosis based on local enhancement and global fusion via MRI

Multi-view anal fistula disease diagnosis based on local enh...

引用

7th International conference on vision, Image and Signal Processing (ICVISP 2023)

作者： C. Tan L. Tian H. Chen P. Liao College of Intelligent Medicine Chengdu University of Traditional Chinese Medicine Chengdu 611137 People's Republic of China School of Electronic Engineering and Computer Science Queen Mary University of London E1 4NS UK National Key Laboratory of Fundamental Science on Synthetic Vision Sichuan University Chengdu 610065 People's Republic of China The Sixth People's Hospital of Chengdu Chengdu 610051 People's Republic of China

Anal fistulas often result from cryptoglandular infections or complications of conditions like Crohn's disease. Patients typically present with symptoms such as recurrent perianal abscesses, discharge, and occasional fecal incontinence. Accurate diagnosis is crucial for determining the type of fistula and planning appropriate treatment. Usually, Magnetic Resonance Imaging (MRI) is used for diagnosis. However, depending on a single perspective can become progressively obstructed, and potentially resulting in erroneous conclusions and miscarriages of justice. thus, a deep learning method for multi-view anal fistula MRI image fusion, combining convolutional neural networks (CNN) and Transformers is proposed. this model extracts feature from different angles of anal fistula MRI, achieving initial feature extraction through CNN modules. It models the local semantic relationship between the two views using a joint crossattention mechanism, exploring multi-view feature connections for local regions, and enhancing feature interaction across views. Additionally, a consistency loss is introduced by computing the cosine similarity between features from two views, maximizing the similarity between features, to constrain the feature distances, ensuring global feature consistency calculation across different views, enhancing the feature representation of single-view images. Experimental validation demonstrates that the method proposed outperforms other mainstream models and can achieve precise identification of anal fistula.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Landmark-RxR: solving vision-and-language navigation with fine-grained alignment supervision 21

Landmark-RxR: solving vision-and-language navigation with fi...

引用

Proceedings of the 35th International conference on Neural Information Processing Systems

作者： Keji He Yan Huang Qi Wu Jianhua Yang Dong An Shuanglin Sima Liang Wang Center for Research on Intelligent Perception and Computing National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences and School of Artificial Intelligence University of Chinese Academy of Sciences School of Computer Science University of Adelaide School of Artificial Intelligence Beijing University of Posts and Telecommunications Center for Research on Intelligent Perception and Computing National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences and School of Future Technology University of Chinese Academy of Sciences Center for Research on Intelligent Perception and Computing National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences and School of Artificial Intelligence University of Chinese Academy of Sciences and Center for Excellence in Brain Science and Intelligence Technology (CEBSIT) and Chinese Academy of Sciences Artificial Intelligence Research (CAS-AIR)

ISBN: (纸本)9781713845393

In vision-and-Language Navigation (VLN) task, an agent is asked to navigate inside 3D indoor environments following given instructions. Cross-modal alignment is one of the most critical challenges in VLN because the predicted trajectory needs to match the given instruction accurately. In this paper, we address the cross-modal alignment challenge from the perspective of fine-grain. Firstly, to alleviate weak cross-modal alignment supervision from coarse-grained data, we introduce a human-annotated fine-grained VLN dataset, namely Landmark-RxR. Secondly, to further enhance local cross-modal alignment under fine-grained supervision, we investigate the focal-oriented rewards with soft and hard forms, by focusing on the critical points sampled from fine-grained Landmark-RxR. Moreover, to fully evaluate the navigation process, we also propose a re-initialization mechanism that makes metrics insensitive to difficult points, which can cause the agent to deviate from the correct trajectories. Experimental results show that our agent has superior navigation performance on Landmark-RxR, en-RxR and R2R.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Region based parametric motion representation

Region based parametric motion representation

引用

International conference on pattern recognition

作者： Changbo Hu Yi Li Songde Ma Hanqing Lu National Laboratory of Pattern Recognition Institute of Automation Chinese Academy and Sciences Beijing China

ISBN: (纸本)0769507506

A region based parametric motion estimation approach is proposed. As a feature based approach, sequential images are firstly represented in a multi-scale region hierarchy, then temporally adjacent region sets are matched along scale-space by symbolic optimization of compound criteria based region similarity, so that temporal region correspondence and the parametric motion representation can be obtained. the motion of regions is represented in affine transformation and estimated in a coarse-to-fine manner so that an intrinsic topological constraint can be applied to enhance the stability of the optimization. Finally the regions are grouped to uniform motion region (UMR) by their motion consistency to realize a compact representation. Compared with classical optical flow methods, our approach shows three advantages. First, motion meaning is easy to interpret at high-level. Second, fundamental problems such as aperture problem, boundary problem, or large motion problem can be some what tackled by applying structure information. third, computation is more stable and efficient because of the symbolic feature-based methodology and the multi-scale framework.

关键词： Motion estimation Image segmentation Image reconstruction Optical sensors Image motion analysis Layout computer vision Optical noise Geophysics computing Flowcharts

来源：评论

学校读者我要写书评

暂无评论

第七届中国模式识别与计算机视觉大会

引用

智能系统学报 2024年第1期19卷 35-35页

第七届中国模式识别与计算机视觉大会(the 7th chinese conference on pattern recognition and computer vision,PRCV 2024)将于2024年10月18—20日在乌鲁木齐举办。PRCV2024由中国自动化学会、中国图象图形学学会、中国人工智能学会... 详细信息

第七届中国模式识别与计算机视觉大会(the 7th chinese conference on pattern recognition and computer vision,PRCV 2024)将于2024年10月18—20日在乌鲁木齐举办。PRCV2024由中国自动化学会、中国图象图形学学会、中国人工智能学会和中国计算机学会联合主办。

关键词：中国计算机学会中国自动化学会计算机视觉模式识别人工智能学会

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：