检索结果-内蒙古大学图书馆

1st International Conference on Intelligent Networks and Intelligent Systems, ICINIS 2008

作者： Qiu, Wu Ding, Mingyue Yuchi, Ming Institute for Pattern Recognition and Artificial Intelligence Image Processing and Intelligence Control Key Laboratory of Education Ministry of China Huazhong University of Science and Technology Wuhan Hubei China Department of Biomedical Engineering School of Life Science and Technology Huazhong University of Science and Technology Wuhan Hubei China

ISBN: (纸本)9780769533919

A quick 3D needle segmentation algorithm for 3D US data is described in this paper. The algorithm includes the 3D Quick Randomized Hough Transform (3DGHT), which is based on the 3D Randomized Hough Transform and coarse-fine searching strategy. We tested it with water phantom. The results show that our algorithm works well in 3D US images with angular deviation less than 1 and position deviation less than 1mm, and the computational time of segmentation with 35MB data is within 1s. © 2008 IEEE.

关键词： Hough transforms

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Brain Tumor Segmentation Network Based on 3D Inverted Residual Modules 22

A Lightweight Brain Tumor Segmentation Network Based on 3D I...

引用

Proceedings of the 2022 11th International Conference on Computing and pattern recognition

作者： Yuchao Liu Xia Du Da-Han Wang Shunzhi Zhu Fujian Key Laboratory of Pattern Recognition and Image Understanding Xiamen University of Technology China

ISBN: (纸本)9781450397056

Semantic segmentation technology based on deep learning has played an important role for doctors in identifying brain tumor regions and formulating treatment plans. Popular automated segmentation methods for brain tumors include 2D and 3D convolution networks. The 3D networks give better results but lead to a significant increase in parameters and computational cost. In this paper, we propose a lightweight brain tumor segmentation network composed of 3D inverted residual modules, which can significantly reduce the computational complexity of 3D models. Based on a lightweight depthwise separable convolution, our 3D inverted residual module extracts high-dimensional brain tumor features through an intermediate expansion layer, thus improving performance. On the brain tumor dataset BraTS 2018, our network achieves dice scores of 80.8%, 90.7%, and 84.3% (for ET, WT, and TC, respectively) with only 0.68M parameters and 51.46G FLOPs. The results show that our method can significantly reduce the complexity of the 3D model and achieve very competitive performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Combining Attention Mechanism and Local-Global Features Association Network for Vehicle Re-identification 22

Combining Attention Mechanism and Local-Global Features Asso...

引用

Proceedings of the 2022 11th International Conference on Computing and pattern recognition

作者： Cai-Xia Li Xia Du Yun Wu Da-Han Wang Fujian Key Laboratory of Pattern Recognition and Image Understanding Xiamen University of Technology China

ISBN: (纸本)9781450397056

Vehicle re-identification (Re-ID) aims to retrieve the target vehicle from a large dataset composed of vehicle images captured by multiple cameras. Most vehicles are difficult to recognize in the environment of low resolution, occlusion, and viewpoint change, which brings challenges to vehicle Re-ID. Existing work usually uses additional attribute information to distinguish different vehicles, such as color, viewpoint, and model. However, this requires expensive manual annotation. Therefore, we propose a three-branch network based on attention mechanism and local-global feature association (AM-LGFA) to improve the accuracy of vehicle Re-ID. In the global branch, the global features of the vehicle are extracted. A multi-scale channel attention module is introduced into the attention branch to suppress irrelevant information and extract important channel features. The features extracted from the backbone are divided into different stripe features in the horizontal direction in the local branch. Then connect each stripe feature with the global information to enhance the context between features. Finally, the features extracted from the three branches are concatenated as the feature representation of the test phase. The experimental results show that the features extracted by the AM-LGFA network are complementary. The effectiveness of this method is verified on two challenging public datasets, VehicleID and VeRi-776.

关键词： Attention mechanism Vehicle re-identification Local-global feature association

来源：评论

学校读者我要写书评

暂无评论

Person re-identification across multi-camera system based on local descriptors

Person re-identification across multi-camera system based on...

引用

ACM/IEEE International Conference on Distributed Smart Cameras, ICDSC

作者： Qiao Huang Jie Yang Yu Qiao Institute of Image Processing and Pattern Recognition and Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Jiao Tong University Shanghai China

Tracking the same person across multiple cameras is an important task in multi-camera systems. It is also desirable to re-identify the individuals who have been previously seen with a single-camera. This paper addresses this problem by the re-identification of the same individual in two different datasets, which are both challenging situations from video surveillance system. In this paper, local descriptors are introduced for image description, and support vector machines are employed for high classification performance and so an efficient Bag of Features approach for image presentation. In this way, robustness against low resolution, occlusion and pose, viewpoint and illumination changes is achieved in a very fast way. We get promising results from the evaluation with situations where a number of individuals vary continuously from a multi-camera system.

关键词： Vocabulary Cameras Histograms Feature extraction image color analysis Support vector machine classification Kernel

来源：评论

学校读者我要写书评

暂无评论

Maintaining imbalance highly dependent medical data using dirichlet process data generation

Maintaining imbalance highly dependent medical data using di...

引用

International Conference on Digital Information Management (ICDIM)

作者： Tieta Antaresti Mohamad Ivan Fanany Aniati Murni Arymurthy Pattern Recognition Image Processing and Content-Based Image Retrieval Laboratory Faculty of Computer Science Universitas Indonesia Depok Indonesia

The existence of imbalanced data between one class and another class is an important issue to be considered in a classification problem. One of the well-known data balancing technique is the artificial oversampling, which increase the size of datasets. In this research, multinomial classification was applied to classify some recorded features obtained from a single ECG (electrocardiograph) sensor. Therefore, a Dirichlet process, a dirichlet distribution of cumulative distribution function of each data partition, was needed to model the distribution of the new generated data by also considering the statistical properties of the previous data. Data balancing process had given the result of 77.21% classification accuracy (CA), and 90.9% area under ROC curve (AUC).

关键词： Electrocardiography Accuracy Diseases Data models Bayesian methods Sleep apnea Machine learning

来源：评论

学校读者我要写书评

暂无评论

ResAsapp: An Effective Convolution to Distinguish Adjacent Pixels For Scene Text Detection 22

ResAsapp: An Effective Convolution to Distinguish Adjacent P...

引用

Proceedings of the 2022 11th International Conference on Computing and pattern recognition

作者： Kangming Weng Xia Du Kunze Chen Dahan Wang Shunzhi Zhu Fujian Key Laboratory of Pattern Recognition and Image Understanding Xiamen University of Technology China

ISBN: (纸本)9781450397056

The segmentation-based approach is an essential direction of scene text detection, and it can detect arbitrary or curved text, which has attracted the increasing attention of many researchers. However, extensive research has shown that the segmentation-based method will be disturbed by adjoining pixels and cannot effectively identify the text boundaries. To tackle this problem, we proposed a ResAsapp Conv based on the PSE algorithm. This convolution structure can provide different scale visual fields about the object and make it effectively recognize the boundary of texts. The method's effectiveness is validated on three benchmark datasets, CTW1500, Total-Text, and ICDAR2015 datasets. In particular, on the CTW1500 dataset, a dataset full of long curve text in all kinds of scenes, which is hard to distinguish, our network achieves an F-measure of 81.2%.

关键词： Pixel Interference Scene Text Detection Curved Text

来源：评论

学校读者我要写书评

暂无评论

Swin Transformer with Multi-Scale Residual Attention for Semantic Segmentation of Remote Sensing images 22

Swin Transformer with Multi-Scale Residual Attention for Sem...

引用

Proceedings of the 2022 11th International Conference on Computing and pattern recognition

作者： Yuanyang Lin Da-han Wang Yun Wu Shunzhi Zhu Fujian Key Laboratory of Pattern Recognition and Image Understanding Xiamen University of Technology China

ISBN: (纸本)9781450397056

Semantic segmentation of remote sensing images usually faces the problems of unbalanced foreground-background, large variation of object scales, and significant similarity of different classes. The FCN-based fully convolutional encoder-decoder architecture seems to have become the standard for semantic segmentation, and this architecture is also prevalent in remote sensing images. However, because of the limitations of CNN, the encoder cannot obtain global contextual information, which is extraordinarily important to the semantic segmentation of remote sensing images. By contrast, in this paper, the CNN-based encoder is replaced by Swin Transformer to obtain rich global contextual information. Besides, for the CNN-based decoder, we propose a multi-level connection module (MLCM) to fuse high-level and low-level semantic information to help feature maps obtain more semantic information and use a multi-scale upsample module (MSUM) to join the upsampling process to recover the resolution of images better to get segmentation results preferably. The experimental results on the ISPRS Vaihingen and Potsdam datasets demonstrate the effectiveness of our proposed method.

关键词： Dilated Convolution Semantic Segmentation Remote Sensing Swin Transformer

来源：评论

学校读者我要写书评

暂无评论

Vsgnet: Visual Saliency Guided Network for Skin Lesion Segmentation

SSRN

引用

SSRN 2023年

作者： Cai, Zhefei Fan, Yingle Fang, Tao Wu, Wei Laboratory of Pattern Recognition and Image Processing Hangzhou Dianzi University Hangzhou310018 China Zhejiang Provincial Key Laboratory of Information Processing Communication and Networking Zhejiang310058 China

The accuracy of skin lesion segmentation is of great significance for the subsequent clinical diagnosis. In order to improve the segmentation accuracy, some pioneering works tried to embed multiple complex modules, or used the huge Transformer framework, but due to the limitation of computing resources, these type of large models were not suitable for the actual clinical environment. To address the coexistence challenges of precision and lightweight, we propose a visual saliency guided network (VSGNet) for skin lesion segmentation, which generates saliency images of skin lesions through the efficient attention mechanism of biological vision, and guides the network to quickly locate the target area, so as to solve the localization difficulties in the skin lesion segmentation tasks. VSGNet includes three parts: Color Constancy module, Saliency Detection module and Ultra Lightweight Multi-level Interconnection Network(ULMI-Net). Specially, ULMI-Net uses a U-shaped structure network as the skeleton, including the Adaptive Split Channel Attention (ASCA) module that simulates the parallel mechanism of biological vision dual pathway, and the Channel-Spatial Parallel Attention (CSPA) module inspired by the multi-level interconnection structure of visual cortices. Through these modules, ULMI-Net can balance the efficient extraction and multi-scale fusion of global and local features, and try to achieve the excellent segmentation results at the lowest cost of parameters and computational complexity. To validate the effectiveness and robustness of the proposed VSGNet on three publicly available skin lesion segmentation datasets (ISIC2017, ISIC2018 and PH2 datasets). The experimental results show that compared to other state-of-the-art methods, VSGNet improves the Dice and mIoU metrics by 1.84% and 3.34%, respectively, and with a 196× and 106× reduction in the number of parameters and computational complexity. This paper constructs the VSGNet integrating the biological vision m

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Minimizing the topological structure of line images 7th

引用

7th Joint IAPR International Workshop on Structural and Syntactic pattern recognition, SSPR 1998 and 2nd International Workshop on Statistical Techniques in pattern recognition, SPR 1998

作者： Kropatsch, Walter G. Burge, Mark Vienna University of Technology Institute of Automation 183/2 Pattern Recognition and Image Processing Group Treitlstr.3 WienA-1040 Austria Johannes Kepler University Institute of Systems Science Computer Vision Laboratory LinzA-4040 Austria

ISBN: (纸本)3540648585

We present a new algorithm based on Dual Graph Contraction (DGC) to transform the Run Graph into its Minimum Line Property Preserving (MLPP) form which, when implemented in parallel, requires O(log(longestcurve)) steps. A MLPP graph of a line image compliments the structural information in geometric graph representations like the run graph. Using such a graph and its dual, line image analysis systems can efficiently detect topological features like loops and holes and make use of relations like containment. © Springer-Verlag Berlin Heidelberg 1998.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Features Integration for Handwritten Mathematical Expression recognition 22

Multi-Scale Features Integration for Handwritten Mathematica...

引用

Proceedings of the 2022 11th International Conference on Computing and pattern recognition

作者： Xianghao Liu Da-Han Wang Shunzhi Zhu Fujian Key Laboratory of Pattern Recognition and Image Understanding Xiamen University of Technology China

ISBN: (纸本)9781450397056

Handwritten mathematical expression recognition (HMER) is a challenging task due to the complex two-dimensional structure of mathematical expressions and the similarity of handwritten texts. Most existing methods for HMER only consider single-scale features while ignoring multi-scale features that are very important to HMER. Few works have explored the fusion of multi-scale features in HMER, but exhibited an extra branch that brings more parameters and computation. In this paper, we propose an end-to-end method to integrate multi-scale features using a unified model. Specifically, we customized the Dense Atrous Spatial Pyramid Pooling (DenseASPP) to our backbone network to capture the multi-scale features of the input image meanwhile expanding the receptive fields. Moreover, we added a symbol classifier using focal loss to better discriminate and recognize similar symbols, to further improve the performance of HMER. Experiments on the Competition on recognition of Online Handwritten Mathematical Expressions (CROHME) 2014, 2016 and 2019 shows that the proposed method achieves superior performance to most state-of-the-art methods, demonstrating the effectiveness of the proposed method.

关键词： Multi-Scale Handwritten Mathematical Expression recognition, Dense Atrous Spatial Pyramid Pooling, Symbol Classifier

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：