检索结果-内蒙古大学图书馆

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Jiang Li Huai Chen Fang Zhu Chen Wen Huiwen Chen Lisheng Wang Department of Automation Shanghai Jiao Tong University Institute of Image Processing and Pattern Recognition Shanghai China Department of Cardiothoracic Surgery Shanghai Children’s Medical Center Shanghai Jiaotong University School of Medicine Shanghai China

ISBN: (数字)9781728119908

ISBN: (纸本)9781728119915

Accurate segmentation of pulmonary vein (PV) and left atrium (LA) is essential for the preoperative evaluation and planning of total anomalous pulmonary venous connection (TAPVC), which is a rare but mortal congenital heart disease of children. However, manual segmentation is time-consuming and insipid. To free radiologists from the repetitive work, we propose an automatic deep learning method to segment PV and LA from Low-Dose CT images. In the method, attention mechanism is incorporated into the widely used V-Net and a novel grouped attention module is applied to enforce the segmentation performance of the V-Net. We evaluate our method on 68 3D Low-Dose CT images scanned from patients with TAPVC. The experiment result shows that our method outperforms the popular 3D-UNet and V-Net, with mean dice similarity coefficient (DSC) of 0.795 and 0.834 for the PV and LA *** relevance-We proposed a CNNs-based method for the automatic segmentation of PV and LA with good accuracy, which can be used for the preoperative evaluation and planning of TAPVC. Our method can improve the efficiency and reduce the workloads of radiologists (400 milliseconds vs. 2-3 hours per-case).

关键词： image segmentation Computed tomography Three-dimensional displays Convolution Task analysis Predictive models Solid modeling

来源：评论

学校读者我要写书评

暂无评论

Realization of Detection Algorithms for Key Parts of Unmanned Aerial Vehicle Based on Deep Learning

Realization of Detection Algorithms for Key Parts of Unmanne...

引用

International Conference on Wireless Communications and Signal processing (WCSP)

作者： Guangya Wang Hanyu Hong Yaozong Zhang Jinmeng Wu Yunfei Wang Shiyang Li Hubei Key Laboratory of Optical Information and Pattern Recognition School of Electrical and Information Engineering Wuhan Institute of Technology Wuhan China Hubei Engineering Research Center of Video Image and HD Projection

ISBN: (数字)9781728172361

ISBN: (纸本)9781728172378

Fixed-point attack on the key parts of small aerial vehicles is one of the important means of UAV (Unmanned Aerial Vehicle) countermeasure. Fixed-wing aircraft flying in the air has two characteristics: fast speed and fast attitude change of aircraft. However, the traditional detection method of key parts of fixed-wing aircraft in infrared images is not only slow in speed but also low in accuracy. This paper presents an improved target detection and motion tracking algorithm based on deep learning method. The algorithm uses a deeper neural network to enhance the feature extraction capabilities of CNN and obtain richer feature information. The detection algorithm obtains the position and motion direction of the key points of the target. Experimental results show that the detection algorithm proposed in this paper is up to 30 frame/s, with an average accuracy of 91.5%/. The method achieved good results in the experiment.

关键词： Feature extraction Aircraft Unmanned aerial vehicles Convolution Target recognition Prediction algorithms Object detection

来源：评论

学校读者我要写书评

暂无评论

Trainable Spectrally Initializable Matrix Transformations in Convolutional Neural Networks

Trainable Spectrally Initializable Matrix Transformations in...

引用

International Conference on pattern recognition

作者： Michele Alberti Angela Botros Narayan Schutz Rolf Ingold Marcus Liwicki Mathias Seuret Document Image and Voice Analysis Group (DIVA) University of Fribourg Switzerland V7 Ltd London United Kingdom ARTORG Center for Biomedical Engineering Research University of Bern Switzerland EISLAB Machine Learning Luleå University of Technology Sweden Pattern Recognition Lab Friedrich-Alexander-Universität Erlangen-Nürnberg Germany

In this work, we introduce a new architectural component to Neural Network (NN), i.e., trainable and spectrally initializable matrix transformations on feature maps. While previous literature has already demonstrated the possibility of adding static spectral transformations as feature processors, our focus is on more general trainable transforms. We study the transforms in various architectural configurations on four datasets of different nature: from medical (ColorectalHist, HAM10000) and natural (Flowers) images to historical documents (CB55). With rigorous experiments that control for the number of parameters and randomness, we show that networks utilizing the introduced matrix transformations outperform vanilla neural networks. The observed accuracy increases appreciably across all datasets. In addition, we show that the benefit of spectral initialization leads to significantly faster convergence, as opposed to randomly initialized matrix transformations. The transformations are implemented as auto-differentiable PyTorch modules that can be incorporated into any neural network architecture. The entire code base is open-source.

关键词： Program processors Discrete Fourier transforms Transforms Documentation pattern recognition Discrete cosine transforms Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Automatic Docking Design of Flange Pipe Based on Spatial Information

Automatic Docking Design of Flange Pipe Based on Spatial Inf...

引用

International Conference on Information Science and Control Engineering (ICISCE)

作者： Xingxun Li Xiuhua Zhang Jinmeng Wu Jian Huang Pianpian Chen Hubei Key Laboratory of Optical Information and Pattern Recognition Wuhan Institute of Technology Wuhan China Hubei Engineering Research Center of Video Image and HD Projection Wuhan Institute of Technology Wuhan China

With the development of ship industry, pipeline system has been more and more widely used. However, the pipeline site space is narrow. Mechanical and electrical equipments are of all kinds. The pipeline cable is densely distributed. All problems mentioned above seriously affects the pipeline construction. In order to solve the problem of pipeline docking, the method of making model and comprehensive lofting is usually adopted. However, this method is technically backward. The operation is inconvenient due to the narrow onsite space. The required period is long. With low information utilization and accuracy, the method of making model and comprehensive lofting has a great influence on the development cycle and design quality. In order to solve these problems, this paper presents a design method and system of flange pipe docking. A binocular camera is used to obtain the image of the pipe joint. The center position of the flange surface and array holes on the flange surface are extracted from the image, which is bias of subsequent work. First, the path of the intermediate connecting pipe is calculated. Then, according to the pipe standards of intermediate connection pipe and production specification of enterprise, the model of intermediate connecting pipe is automatically generated by using secondary development technology of CAD. In this paper, the binocular vision technology is combined with pipeline docking design, which significantly improves the utilization rate of field space information and design efficiency, and solves the problems of inconvenient operation and safety risk of traditional profiling method.

关键词： Industries Solid modeling Design methodology Pipelines Production Flanges Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A correction method for aero-optics thermal radiation effects based on gradient distribution and dark channel

引用

Optoelectronics Letters 2019年第5期15卷 374-380页

作者： HONG Han-yu SHI Yu ZHANG Tian-xu LIU Zhao Hubei Key Laboratory of Optical Information and Pattern Recognition Hubei Research Centre of Video Image and High Definition Projection School of Electrical and Information Engineering Wuhan Institute of Technology Wuhan 430074 China National Key Laboratory of Science and Technology on Multi-Spectral Information Processing School of Automation Huazhong University of Science and Technology Wuhan 430074 China

In this paper, a new algorithm is proposed to remove the effects of aerodynamic optical thermal radiation from a single infrared image. In this method, the joint probability model of gradient distribution is introduced by studying the "global smoothing and local fluctuation" characteristics of the bias field. A prior L0 norm of dark channel is introduced to constrain the latent clear image. Finally, the split Bregman method is used to solve the optimization problem. The effectiveness of the proposed method is verified by a series of experiments, and the results are compared with the results of the existing methods for the correction of thermal radiation effects.

关键词： aero-optics thermal radiation effects gradient distribution dark channel

来源：评论

学校读者我要写书评

暂无评论

A Recent Survey of Vision Transformers for Medical image Segmentation

arXiv

引用

arXiv 2023年

作者： Khan, Asifullah Rauf, Zunaira Khan, Abdul Rehman Rathore, Saima Khan, Saddam Hussain Shah, Sahar Farooq, Umair Asif, Hifsa Asif, Aqsa Zahoora, Umme Khalil, Rafi Ullah Qamar, Suleman Asif, Umme Hani Khan, Faiza Babar Majid, Abdul Gwak, Jeonghwan Pattern Recognition Lab Department of Computer & Information Sciences Pakistan Institute of Engineering & Applied Sciences Nilore Islamabad45650 Pakistan Pakistan Institute of Engineering & Applied Sciences Nilore Islamabad45650 Pakistan Center for Mathematical Sciences Pakistan Institute of Engineering & Applied Sciences Nilore Islamabad45650 Pakistan Avid Radio pharmaceuticals PhiladelphiaPA United States Eli Lilly and Company IndianapolisIN United States Swat Pakistan Air University E-9 Islamabad44230 Pakistan Digital Image Processing Lab Department of Computer Science Islamia College Peshawar Pakistan Pakistan Institute of Engineering & Applied Sciences Nilore Islamabad45650 Pakistan Department of Software Korea National University of Transportation Chungju27469 Korea Republic of

Medical image segmentation plays a crucial role in various healthcare applications, enabling accurate diagnosis, treatment planning, and disease monitoring. In recent years, Vision Transformers (ViTs) have emerged as a promising technique for addressing the challenges in medical image segmentation. In medical images, structures are usually highly interconnected and globally distributed. ViTs utilize their multi-scale attention mechanism to model the long-range relationships in the images. However, they do lack image-related inductive bias and translational invariance, potentially impacting their performance. Recently, researchers have come up with various ViT-based approaches that incorporate CNNs in their architectures, known as Hybrid Vision Transformers (HVTs) to capture local correlation in addition to the globa l information in the images. This survey paper provides a detailed review of the recent advancements in ViTs and HVTs for medical image segmentation. Along with the categorization of ViT and HVT-based medical image segmentation approaches we also present a detailed overview of their real-time applications in several medical image modalities. This survey may serve as a valuable resource for researchers, healthcare practitioners, and students in understanding the state-of-the-art approaches for ViT-based medical image segmentation. Copyright © 2023, The Authors. All rights reserved.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

The Intelligent Preparation of Scene Matching Guidance Reference Map Based on Prior Knowledge

The Intelligent Preparation of Scene Matching Guidance Refer...

引用

International Conference on Wireless Communications and Signal processing (WCSP)

作者： Pan Chen Yaozong Zhang Jinmeng Wu Xingxun Li School of Electrical Information Wuhan Institute of Technology Wuhan China Hubei Engineering Research Center of Video Image and HD Projection Wuhan China Hubei Key Laboratory of Optical Information and Pattern Recognition Wuhan China

ISBN: (数字)9781728172361

ISBN: (纸本)9781728172378

Aiming at the problem that the automatic processing level of reference map preparation in image matching guidance is not high enough, our work proposes a novel reference map preparation based on the prior knowledge such as infrared imaging conditions and trajectory information. In the image preprocessing stage, the deep convolution network is used to extract the regions of interest automatically and meanwhile, combined with the analysis of connected region, the ROI extraction results can be optimized; Then, the natural scene is classified by texture of material, and the periodic temperature change of the feature is automatically mapped to the gray level, which conforms to the actual imaging characteristics and reduces the artificial gray level error. Next, combined with trajectory information and perspective transformation, multi-scale and multi-view scene images can be automatically obtained, which can avoid the situation that the manually selected target or landmark is not obvious or does not exist in the actual imaging. With comprehensive analysis from three aspects of reliability, stability and uniqueness, the best matching area is automatically determined, which improves the accuracy of matching algorithm and the time performance of reference map preparation system.

关键词： Temperature Convolution Target recognition Real-time systems Surface treatment Knowledge engineering Atmospheric modeling

来源：评论

学校读者我要写书评

暂无评论

Identification and Extraction of Circular Markers in 3D Reconstruction

Identification and Extraction of Circular Markers in 3D Reco...

引用

International Conference on Wireless Communications and Signal processing (WCSP)

作者： Yunfei Wang Hanyu Hong Jinmeng Wu Guangya Wang Shiyang Li Hubei Key Laboratory of Optical Information and Pattern Recognition Wuhan China Hubei Engineering Research Center of Video Image and HD Projection Wuhan China School of Electrical and Information Engineering Wuhan Institute of Technology Wuhan China

ISBN: (数字)9781728172361

ISBN: (纸本)9781728172378

This paper presents a method for the identification and location of circular markers in 3D reconstruction. The input image is processed with gray scale and gaussian filter to remove noise interference and improve the accuracy of edge detection. The size and direction of the gradient of the image were calculated to obtain the edge features of the circular marker, and the circle degree of the closed edge was judged, and the center of the marker was obtained by fitting the edge features with the ellipse of the least square method. Hu moment similarity of each marker was obtained, and the non-marker was deleted and the real marker was retained by similarity judgment. Experiments show that the algorithm has good robustness, high precision, can effectively reduce the probability of false detection, and has high accuracy in complex environments.

关键词： image edge detection Transforms Three-dimensional displays Fitting Feature extraction Cameras Least mean squares methods

来源：评论

学校读者我要写书评

暂无评论

Random features for kernel approximation: A survey on algorithms, theory, and beyond

arXiv

引用

arXiv 2020年

作者： Liu, Fanghui Huang, Xiaolin Chen, Yudong Suykens, Johan A.K. KU Leuven LeuvenB-3001 Belgium Institute of Image Processing and Pattern Recognition Institute of Medical Robotics Shanghai Jiao Tong University Shanghai200240 China School of Operations Research and Information Engineering Cornell University IthacaNY14850 United States

The class of random features is one of the most popular techniques to speed up kernel methods in large-scale problems. Related works have been recognized by the NeurIPS Test-of-Time award in 2017 and the ICML Best Paper Finalist in 2019. The body of work on random features has grown rapidly, and hence it is desirable to have a comprehensive overview on this topic explaining the connections among various algorithms and theoretical results. In this survey, we systematically review the work on random features from the past ten years. First, the motivations, characteristics and contributions of representative random features based algorithms are summarized according to their sampling schemes, learning procedures, variance reduction properties and how they exploit training data. Second, we review theoretical results that center around the following key question: how many random features are needed to ensure a high approximation quality or no loss in the empirical/expected risks of the learned estimator. Third, we provide a comprehensive evaluation of popular random features based algorithms on several large-scale benchmark datasets and discuss their approximation quality and prediction performance for classification. Last, we discuss the relationship between random features and modern over-parameterized deep neural networks (DNNs), including the use of high dimensional random features in the analysis of DNNs as well as the gaps between current theoretical and empirical results. This survey may serve as a gentle introduction to this topic, and as a users' guide for practitioners interested in applying the representative algorithms and understanding theoretical results under various technical assumptions. We hope that this survey will facilitate discussion on the open problems in this topic, and more importantly, shed light on future research directions. Copyright © 2020, The Authors. All rights reserved.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

CASIA-Face-Africa: A large-scale African face image database

arXiv

引用

arXiv 2021年

作者： Muhammad, Jawad Wang, Yunlong Wang, Caiyong Zhang, Kunbo Sun, Zhenan The School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China The Center for Research on Intelligent Perception and Computing National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China The School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture Beijing100044 China Beijing Key Laboratory of Intelligent Processing for Building Big Data Beijing100044 China

Face recognition is a popular and well-studied area with wide applications in our society. However, racial bias had been proven to be inherent in most State Of The Art (SOTA) face recognition systems. Many investigative studies on face recognition algorithms have reported higher false positive rates of African subjects cohorts than the other cohorts. Lack of large-scale African face image databases in public domain is one of the main restrictions in studying the racial bias problem of face recognition. To this end, we collect a face image database namely CASIA-Face-Africa which contains 38,546 images of 1,183 African subjects. Multi-spectral cameras are utilized to capture the face images under various illumination settings. Demographic attributes and facial expressions of the subjects are also carefully recorded. For landmark detection, each face image in the database is manually labeled with 68 facial keypoints. A group of evaluation protocols are constructed according to different applications, tasks, partitions and scenarios. The performances of SOTA face recognition algorithms without retraining are reported as baselines. The proposed database along with its face landmark annotations, evaluation protocols and preliminary results form a good benchmark to study the essential aspects of face biometrics for African subjects, especially face image preprocessing, face feature analysis and matching, facial expression recognition, sex/age estimation, ethnic classification, face image generation, etc. The database can be downloaded from our website* Copyright © 2021, The Authors. All rights reserved.

关键词： Face recognition

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：