检索结果-内蒙古大学图书馆

A generalization theory based on independent and task-identically distributed assumption

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Zheng, Guanhua Sang, Jitao Li, Houqiang Yu, Jian Xu, Changsheng University of Science and Technology of China School of Computer and Information Technology Beijing Key Laboratory of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing100044 China Chinese Academy of Sciences Key Laboratory of Technology in Geo-Spatial Information Processing and Application System Hefei230026 China National Lab of Pattern Recognition Institute of Automation CAS Beijing100190 China University of Chinese Academy of Sciences

—Existing generalization theories analyze the generalization performance mainly based on the model complexity and training process. The ignorance of the task properties, which results from the widely used IID assumption, makes these theories fail to interpret many generalization phenomena or guide practical learning tasks. In this paper, we propose a new Independent and Task-Identically Distributed (ITID) assumption, to consider the task properties into the data generating process. The derived generalization bound based on the ITID assumption identifies the significance of hypothesis invariance in guaranteeing generalization performance. Based on the new bound, we introduce a practical invariance enhancement algorithm from the perspective of modifying data distributions. Finally, we verify the algorithm and theorems in the context of image classification task on both toy and real-world datasets. The experimental results demonstrate the reasonableness of the ITID assumption and the effectiveness of new generalization theory in improving practical generalization performance. Copyright © 2019, The Authors. All rights reserved.

关键词： Classification (of information)

Relationship between pulmonary nodule malignancy and surrounding pleurae, airways and vessels: a quantitative study using the public LIDC-IDRI dataset

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Qin, Yulei Gu, Yun Zhang, Hanxiao Yang, Jie Wang, Lihui Wang, Zhexin Yao, Feng Zhu, Yue-Min Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai200240 China Institute of Medical Robotics Shanghai Jiao Tong University Shanghai200240 China CREATIS INSA Lyon CNRS UMR 5220 INSERM U1206 Université de Lyon Villeurbanne69621 France Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province School of Computer Science and Technology Guizhou University Guiyang550025 China Department of Thoracic Surgery Shanghai Chest Hospital Shanghai Jiao Tong University Shanghai200025 China

Objectives: To investigate whether the pleurae, airways and vessels surrounding a nodule on non-contrast computed tomography (CT) can discriminate benign and malignant pulmonary nodules. Materials and Methods: The LIDC-IDRI dataset, one of the largest publicly available CT database, was exploited for study. A total of 1556 nodules from 694 patients were involved in statistical analysis, where nodules with average scorings 3 were respectively denoted as benign and malignant. Besides, 339 nodules from 113 patients with diagnosis ground-truth were independently evaluated. Computer algorithms were developed to segment pulmonary structures and quantify the distances to pleural surface, airways and vessels, as well as the counting number and normalized volume of airways and vessels near a nodule. Odds ratio (OR) and Chi-square (χ2) testing were performed to assess the correlation between features of surrounding structures and nodule malignancy. A non-parametric receiver operating characteristic (ROC) analysis was conducted in logistic regression to evaluate discrimination ability of each structure. Results: For the benign and malignant groups, the average distances from nodules to pleural surface, airways and vessels are respectively (6.56, 5.19), (37.08, 26.43) and (1.42, 1.07) mm. The correlation between nodules and the counting number of airways and vessels that contact or project towards nodules are respectively (OR=22.96, χ2=105.04) and (OR=7.06, χ2=290.11). The correlation between nodules and the volume of airways and vessels are (OR=9.19, χ2=159.02) and (OR=2.29, χ2=55.89). The areas-under-curves (AUCs) for pleurae, airways and vessels are respectively 0.5202, 0.6943 and 0.6529. Conclusion: Our results show that malignant nodules are often surrounded by more pulmonary structures compared with benign ones, suggesting that features of these structures could be viewed as lung cancer biomarkers. © 2021, CC BY.

关键词： Computerized tomography

A comprehensive survey of oracle character recognition: challenges, benchmarks, and beyond

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Jing Chi, Xueke Wang, Qiufeng Huang, Kaizhu Wang, Da-Han Liu, Yongge Liu, Cheng-Lin College of Science & Technology Ningbo University Ningbo China School of Advanced Technology Xi’an Jiaotong-Liverpool University Suzhou China Duke Kunshan University Suzhou China Fujian Key Laboratory of Pattern Recognition and Image Understanding School of Computer and Information Engineering Xiamen University of Technology Xiamen China Anyang Normal University Anyang China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China

Oracle character recognition—an analysis of ancient Chinese inscriptions found on oracle bones—has become a pivotal field intersecting archaeology, paleography, and historical cultural studies. Traditional methods of oracle character recognition have relied heavily on manual interpretation by experts, which is not only labor-intensive but also limits broader accessibility to the general public. With recent breakthroughs in pattern recognition and deep learning, there is a growing movement towards the automation of oracle character recognition (OrCR), showing considerable promise in tackling the challenges inherent to these ancient scripts. However, a comprehensive understanding of OrCR still remains elusive. Therefore, this paper presents a systematic and structured survey of the current landscape of OrCR research. We commence by identifying and analyzing the key challenges of OrCR. Then, we provide an overview of the primary benchmark datasets and digital resources available for OrCR. A review of contemporary research methodologies follows, in which their respective efficacies, limitations, and applicability to the complex nature of oracle characters are critically highlighted and examined. Additionally, our review extends to ancillary tasks associated with OrCR across diverse disciplines, providing a broad-spectrum analysis of its applications. We conclude with a forward-looking perspective, proposing potential avenues for future investigations that could yield significant advancements in the field. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep learning

Rotation equivariant feature image pyramid network for object detection in optical remote sensing imagery

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Shamsolmoali, Pourya Zareapoor, Masoumeh Chanussot, Jocelyn Zhou, Huiyu Yang, Jie The Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai200240 China The GIPSA-Lab Université Grenoble Alpes CNRS Grenoble INP Grenoble38000 France The Faculty of Electrical and Computer Engineering University of Iceland Reykjavik101 Iceland The School of Informatics University of Leicester LeicesterLE1 7RH United Kingdom

To read the paper please go to IEEE Transactions on Geoscience and Remote Sensing on IEEE Xplore. Detection of objects is extremely important in various aerial vision-based applications. Over the last few years, the methods based on convolution neural networks have made substantial progress. However, because of the large variety of object scales, densities, and arbitrary orientations, the current detectors struggle with the extraction of semantically strong features for small-scale objects by a predefined convolution kernel. To address this problem, we propose the rotation equivariant feature image pyramid network (REFIPN), an image pyramid network based on rotation equivariance convolution. The proposed model adopts single-shot detector in parallel with a lightweight image pyramid module to extract representative features and generate regions of interest in an optimization approach. The proposed network extracts feature in a wide range of scales and orientations by using novel convolution filters. These features are used to generate vector fields and determine the weight and angle of the highest-scoring orientation for all spatial locations on an image. By this approach, the performance for small-sized object detection is enhanced without sacrificing the performance for large-sized object detection. The performance of the proposed model is validated on two commonly used aerial benchmarks and the results show our proposed model can achieve state-of-the-art performance with satisfactory efficiency. Copyright © 2021, The Authors. All rights reserved.

关键词： Object detection

学校读者我要写书评

暂无评论

基于字典学习的图像去模糊研究

基于字典学习的图像去模糊研究

第九届中国通信学会学术年会

作者： ZOU Jian-cheng 邹建成 CHE Dong-juan 车冬娟 Institute of Image Processing and Pattern Recognition North China University of TechnologyBeijing 1 北方工业大学图像处理与模式识别研究所北京 100144

图像在获取、传输等过程中会受到干扰，造成图像模糊不清。传统去模糊方法需要根据模糊原因估计出相应的点扩散函数(PSF)，然后进行反卷积估计出原始图像。本文借鉴K-SVD算法，利用对模糊图像进行训练得到自适应字典;并利用计算量相对... 详细信息

图像在获取、传输等过程中会受到干扰，造成图像模糊不清。传统去模糊方法需要根据模糊原因估计出相应的点扩散函数(PSF)，然后进行反卷积估计出原始图像。本文借鉴K-SVD算法，利用对模糊图像进行训练得到自适应字典;并利用计算量相对较小且收缩速度较快的PCD算法来求解稀疏解。实验结果表明，相对传统图像去模糊算法和固定字典算法，自适应的字典学习算法能达到更好的去模糊效果。

关键词：图像处理去模糊方法字典学习算法研究

New de-interlacing method based on adaptive weight

学校读者我要写书评

暂无评论

Chinese Journal of Systems Engineering and Electronics 2004年第2期000卷

De-interlacing is very important when converting interlaced pictures to progressive pictures in format ***-formats digital broadcast and progressive display requires the de-interlacing technique. An adaptive weight deinterlacing method is proposed. It combines motion compensation technique with directional-based spatio-temporal filter efficiently. Experiment results indicate that the method can keep edge continuity and sharpness effectively, reduce the artifacts in motion areas, and shows better visual performance when the estimated motion vectors are inaccurate.

关键词： de-interlacing motion compensation spatio-temporal filter

Optimal decoupling control system using kernel method

学校读者我要写书评

暂无评论

Chinese Journal of Systems Engineering and Electronics 2004年第3期000卷

A major difficulty in multivariable control design is the cross-coupling between inputs and outputs which obscures the effects of a specific controller on the overall behavior of the system. This paper considers the application of ker nel method in decoupling multivariable outputfeedback controllers. Simulation results are presented to show the feasibility of the proposed technique.

关键词： support vector regression kernel ridge regression decoupling multivariable control systems

Study on the Medical image Distributed Dynamic processing Method

学校读者我要写书评

暂无评论

Chinese Journal of Systems Engineering and Electronics 2003年第4期000卷

To meet the challenge of implementing rapidly advanced, time-consuming medical image processing algorithms,it is necessary to develop a medical image processing technology to process a 2D or 3D medical image dynamically on the web. But in a premier system, only static image processing can be provided with the limitation of web technology. The development of Java and CORBA (common object request broker architecture) overcomes the shortcoming of the web static application and makes the dynamic processing of medical images on the web available. To develop an open solution of distributed computing, we integrate the Java, and web with the CORBA and present a web-based medical image dynamic processing methed, which adopts Java technology as the language to program application and components of the web and utilies the CORBA architecture to cope with heterogeneous property of a complex distributed system. The method also provides a platform-independent, transparent processing architecture to implement the advanced image routines and enable users to access large dataset and resources according to the requirements of medical applications. The experiment in this paper shows that the medical image dynamic processing method implemented on the web by using Java and the CORBA is feasible.

关键词： medical image dynamic processing based on web distributed computing interoperation CORBA

Two new approaches for image registration based on spatial-temporal relationship

学校读者我要写书评

暂无评论

Journal of Systems Engineering and Electronics 2005年第2期000卷

作者： Deng Zhipeng Yang Jie Liu Xiaojun Institute of Image Processing & Pattern Recognition， Shanghai Jiaotong University， Shanghai 200030， P. R. China

How to improve the probability of registration and precision of localization is a hard problem, which is desiderated to solve. The two basic approaches (normalized cross-correlation and phase correlation) for image registration are analysed, two improved approaches based on spatial-temporal relationship are presented. This method adds the correlation matrix according to the displacements in x- cirection and y- directions, and the registration pose is searched in the added matrix. The method overcomes the shortcoming that the probability of registration decreasing with area increasing owing to geometric distortion, improves the probability and the robustness of registration.

关键词： image registration phase correlation normalized cross-correlation spatial-temporal relationship