检索结果-内蒙古大学图书馆

International Conference on Document Analysis and recognition

作者： Yi-Kang Zhang Heng Zhang Yong-Ge Liu Qing Yang Cheng-Lin Liu National Laboratory of Pattern Recognition Chinese Academy of Sciences Beijing P.R. China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing P.R. China School of Computer & Information Engineering Anyang Normal University Henan P.R. China Ministry of Education Key Laboratory of Oracle Bone Inscriptions Information Processing Henan P.R. China CAS Center for Excellence of Brain Science and Intelligence Technology Beijing P.R. China

Oracle character is one kind of the earliest hieroglyphics, which can be dated back to Shang Dynasty in China. Oracle character recognition is important for modern archaeology, ancient text understanding, and historical chronology, etc. To overcome the limitation and class imbalance of training data in oracle character recognition, we propose a classification method based on deep metric learning. We use a convolutional neural network (CNN) to map the character images to an Euclidean space where the distance between different samples can measure their similarities such that classification can be performed by the Nearest Neighbor (NN) rule. Because new categories are still being discovered in reality, our model enables the rejection of unseen categories and the configuration of new categories. To accelerate NN classification, we also propose a prototype pruning method with little loss of accuracy. The proposed method exceeds the state of the art on the public dataset Oracle-20K and outperforms CNN with softmax layer on a new dataset Oracle-AYNU.

关键词： Prototypes Character recognition Measurement Artificial neural networks Training Acceleration Network architecture

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to “FGPNet: A weakly supervised fine-grained 3D point clouds classification network” [pattern recognition 139 (2023) 109509]

引用

pattern recognition 2024年 151卷

作者： Huihui Shao Jing Bai Rusong Wu Jinzhe Jiang Hongbo Liang the School of Computer Science and Engineering North Minzu University Yinchuan 750021 China the Key Laboratory of Images Processing and Pattern Recognition Laboratory Commission: IPPRLab North Minzu University Yinchuan 750021 China

来源：评论

学校读者我要写书评

暂无评论

Video segmentation using multiple features based on EM algorithm

引用

Chinese Journal of Systems Engineering and Electronics 2004年第4期000卷

Object-based video segmentation is an important issue for many multimedia applications. A video segmentation method based on EM algorithm is proposed. We consider video segmentation as an unsupervised classification problem and apply EM algorithm to obtain the maximum-likelihood estimation of the Gaussian model parameters for model-based segmentation. We simultaneously combine multiple features (motion, color) within a maximum likelihood framework to obtain accurate segment results. We also use the temporal consistency among video frames to improve the speed of EM algorithm. Experimental results on typical MPEG-4 sequences and real scene sequences show that our method has an attractive accuracy and robustness.

关键词： video object segmentation maximum-likelihood estimation EM algorithm

来源：评论

学校读者我要写书评

暂无评论

Multi-granulation variable precision rough set based on limited tolerance relation

引用

UPB Scientific Bulletin, Series A: Applied Mathematics and Physics 2021年第3期83卷 63-74页

作者： Wan, Renxia Yao, Yonghong Kumar, Hussain School of Mathematics and Information Science North Minzu University Ningxia750021 China HongYang Institute for Big Data in Health Fuzhou Fujian350028 China School of Mathematical Sciences Tiangong University Tianjin300387 China The Key Laboratory of Intelligent Information and Data Processing of NingXia Province North Minzu University and Health Big Data Research Institute of North Minzu University Yinchuan750021 China Machine vision and pattern recognition lab University of Regina ReginaSKS4S0A2 Canada

In this paper, the combination of the variable precision rough set and the limited tolerance relation under multi-granularity is explored. As an extension of rough set model, Multi-granularity variable precision limited tolerance rough set model is con-structed. Properties of upper and lower approximation operator and detailed structure of object class through threshold are discussed. Theoretical proofs are given to show the rationality and superiority of the proposed model. © 2021, Politechnica University of Bucharest. All rights reserved.

关键词： Granulation

来源：评论

学校读者我要写书评

暂无评论

Pulsar/CNS integrated navigation based on federated UKF

引用

Chinese Journal of Systems Engineering and Electronics 2010年第4期000卷

作者： Jin Liu Jie Ma Jinwen Tian State Key Laboratory for Multi-spectral Information Processing Technologies Institue for Pattern Recognition and artifical IntelligenceHuazhnng University of Science and TechnologyWuhan 430074P.R.China

In order to improve the autonomous navigation capability of satellite,a pulsar/CNS(celestial navigation system)integrated navigation method based on federated unscented Kalman filter(UKF)is *** celestial navigation is a mature and stable navigation ***,its position determination performance is not satisfied due to the low accuracy of horizon *** pulsar navigation is a new navigation method,which can provide highly accurate range *** major drawback of single pulsar navigation is that the system is completely *** two methods are complementary to each other,the federated UKF is used here for fusing the navigation data from single pulsar navigation and *** to the traditional celestial navigation method and single pulsar navigation,the integrated navigation method can provide better navigation *** simulation results demonstrate the feasibility and effectiveness of the navigation method.

关键词： autonomous navigation celestial navigation system(CNS) pulsar federated unscented Kalman filter(UKF)

来源：评论

学校读者我要写书评

暂无评论

Low dose CT image denoising using a generative adversarial network with wasserstein distance and perceptual loss

arXiv

引用

arXiv 2017年

作者： Yang, Qingsong Yan, Pingkun Zhang, Yanbo Yu, Hengyong Shi, Yongyi Mou, Xuanqin Kalra, Mannudeep K. Zhang, Yi Sun, Ling Wang, Ge Department of Biomedical Engineering Rensselaer Polytechnic Institute TroyNY12180 United States Department of Electrical and Computer Engineering University of Massachusetts Lowell LowellMA01854 United States Institute of Image Processing and Pattern Recognition Xian Jiaotong University Xian Shaanxi710049 China Department of Radiology Massachusetts General Hospital Harvard Medical School BostonMA United States College of Computer Science Sichuan Universiyt Chengdu610065 China Department of Radiology West China Hospital Sichuan University Chengdu610041 China

The continuous development and extensive use of CT in medical practice has raised a public concern over the associated radiation dose to the patient. Reducing the radiation dose may lead to increased noise and artifacts, which can adversely affect the radiologists judgement and confidence. Hence, advanced image reconstruction from low-dose CT data is needed to improve the diagnostic performance, which is a challenging problem due to its ill-posed nature. Over the past years, various low-dose CT methods have produced impressive results. However, most of the algorithms developed for this application, including the recently popularized deep learning techniques, aim for minimizing the mean-squared-error (MSE) between a denoised CT image and the ground truth under generic penalties. Although the peak signal-to-noise ratio (PSNR) is improved, MSE-or weighted-MSE-based methods can compromise the visibility of important structural details after aggressive denoising. This paper introduces a new CT image denoising method based on the generative adversarial network (GAN) with Wasserstein distance and perceptual similarity. The Wasserstein distance is a key concept of the optimal transport theory, and promises to improve the performance of GAN. The perceptual loss suppresses noise by comparing the perceptual features of a denoised output against those of the ground truth in an established feature space, while the GAN focuses more on migrating the data noise distribution from strong to weak statistically. Therefore, our proposed method transfers our knowledge of visual perception to the image denoising task and is capable of not only reducing the image noise level but also trying to keep the critical information at the same time. Promising results have been obtained in our experiments with clinical CT images. Copyright © 2017, The Authors. All rights reserved.

关键词： image denoising

来源：评论

学校读者我要写书评

暂无评论

Addendum to “Hum-PLoc: A novel ensemble classifier for predicting human protein subcellular localization” [Biochem. Biophys. Res. Commun. 347 (2006) 150–157]

引用

Biochemical and Biophysical Research Communications 2006年第4期348卷 1479-1479页

作者： Kuo-Chen Chou Hong-Bin Shen Gordon Life Science Institute 13784 Torrey Del Mar Drive San Diego CA 92130 USA Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University 1954 Hua-Shan Road Shanghai 200030 China

来源：评论

学校读者我要写书评

暂无评论

Fundamental theory of natural observation method with complete reconstruction property by finite sum - Natural observation theory of normal type

引用

ELECTRONICS AND COMMUNICATIONS IN JAPAN PART III-FUNDAMENTAL ELECTRONIC SCIENCE 1996年第11期79卷 84-96页

作者： Iijima, T Iwaki, M Japan Advanced Institute of Science and Technology Ishikawa Japan 923-12 Taim Iijima received his B.E. degree in Electrical Engineering from Tokyo Institute of Technology in 1948 and joined the Electrotechnical Laboratory. He received his Ph.D. degree in 1957. He was involved in research on electromagnetic theory pattern recognition theory image processing speech recoption and OCR research development. He became Chief of Densoken Iijima Special Research Group and then Professor at Tokyo Institute of Technology in 1972. He was Professor Emeritus in 1986 Professor at Tokyo Engineering University in 1986 Professor Emeritus in 1993 Professor at the Japan Advanced Institute of Science and Technology in 1993 Vice President of the Institute in 1994 Editinghvestigation/General Affairs Secretary Inspector Councilor Chairman of Pattern Recognition Research Committee Head of Tokyo Region Vice President at I.E.I.C.E. Japan and became Honorary Member in 1993. He received the Paper Award four times Authorship Award once Achievement Award in 1976 Meritorious Award in 1989 and the Purple-Ribbon Prize in 1989.

A theory of natural observation methods was originally formulated for two complementary systems: neighboring type and equilibrium type. This paper introduces a new system, normal-type system, that is different from the forementioned two types. One characteristic feature of the normal-type natural observation method is its ability to reconstruct an original waveform from the sum of a finite number of observation values. The natural observation theory of a normal type evolves naturally under the condition that a waveform and its power component can be expressed in the sum form. These meanings are discussed by comparing a frequency response of the normal-type natural observation transform with that of a conventional filter bank. Furthermore, a criterion for determining observation parameters in order to realize the natural observation of normal type under a given tolerance of error is described. It is believed that the proposed theory offers new insights into systematization of the natural observation theory.

关键词： natural observation method neighboring type equilibrium type normal type

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Local Discrimination for Medical images

arXiv

引用

arXiv 2021年

作者： Chen, Huai Wang, Renzhen Wang, Xiuying Li, Jieyu Fang, Qu Li, Hui Bai, Jianhao Peng, Qing Meng, Deyu Wang, Lisheng Institute of Image Processing and Pattern Recognition Department of Automation Shanghai Jiao Tong University Shanghai200240 China School of Mathematics and Statistics Ministry of Education Key Lab of Intelligent Networks and Network Security Xi’an Jiaotong University Xi’an710049 China The School of Computer Science The University of Sydney SydneyNSW2006 Australia Department of Ophthalmology Shanghai Tenth People’s Hospital Tongji University Shanghai200240 China The Cooperative Medianet Innovation Center Shanghai Jiao Tong University Shanghai200240 China The Changchun GeneScience Pharmaceutical Co. LTD China

Contrastive learning, which aims to capture general representation from unlabeled images to initialize the medical analysis models, has been proven effective in alleviating the high demand for expensive annotations. Current methods mainly focus on instance-wise comparisons to learn the global discriminative features, however, pretermitting the local details to distinguish tiny anatomical structures, lesions, and tissues. To address this challenge, in this paper, we propose a general unsupervised representation learning framework, named local discrimination (LD), to learn local discriminative features for medical images by closely embedding semantically similar pixels and identifying regions of similar structures across different images. Specifically, this model is equipped with an embedding module for pixel-wise embedding and a clustering module for generating segmentation. And these two modules are unified through optimizing our novel region discrimination loss function in a mutually beneficial mechanism, which enables our model to reflect structure information as well as measure pixel-wise and region-wise similarity. Furthermore, based on LD, we propose a center-sensitive one-shot landmark localization algorithm and a shape-guided cross-modality segmentation model to foster the generalizability of our model. When transferred to downstream tasks, the learned representation by our method shows a better generalization, outperforming representation from 18 state-of-the-art (SOTA) methods and winning 9 out of all 12 downstream tasks. Especially for the challenging lesion segmentation tasks, the proposed method achieves significantly better performances. The source codes are publicly available at https://***/HuaiChen-1994/LDLearning. Copyright © 2021, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Attention-Guided Multi-scale Interaction Network for Face Super-Resolution

arXiv

引用

arXiv 2024年

作者： Wan, Xujie Li, Wenjie Gao, Guangwei Lu, Huimin Yang, Jian Lin, Chia-Wen The Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing210046 China Key Laboratory of Artificial Intelligence Ministry of Education Shanghai200240 China The Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou215006 China The Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100080 China The School of Automation Southeast University Nanjing210096 China The School of Computer Science and Technology Nanjing University of Science and Technology Nanjing210094 China The Department of Electrical Engineering National Tsing Hua University Hsinchu30013 Taiwan

Recently, CNN and Transformer hybrid networks demonstrated excellent performance in face super-resolution (FSR) tasks. Since numerous features at different scales in hybrid networks, how to fuse these multi-scale features and promote their complementarity is crucial for enhancing FSR. However, existing hybrid network-based FSR methods ignore this, only simply combining the Transformer and CNN. To address this issue, we propose an attention-guided Multi-scale interaction network (AMINet), which contains local and global feature interactions as well as encoder-decoder phases feature interactions. Specifically, we propose a Local and Global Feature Interaction Module (LGFI) to promote fusions of global features and different receptive fields' local features extracted by our Residual Depth Feature Extraction Module (RDFE). Additionally, we propose a Selective Kernel Attention Fusion Module (SKAF) to adaptively select fusions of different features within LGFI and encoder-decoder phases. Our above design allows the free flow of multi-scale features from within modules and between encoder and decoder, which can promote the complementarity of different scale features to enhance FSR. Comprehensive experiments confirm that our method consistently performs well with less computational consumption and faster inference. Copyright © 2024, The Authors. All rights reserved.

关键词： Decoding

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：