检索结果-内蒙古大学图书馆

MIPPR 2009 - Remote Sensing and GIS Data processing and Other Applications: 6th International Symposium on Multispectral image processing and pattern recognition

作者： Li, Shidong Ding, Mingyue Cai, Chao Institute for Pattern Recognition and Artificial Intelligence National Lab. for Multi-spectral Information Processing Technologies Huazhong University of Science and Technology Wuhan 430074 China Hubei University for Nationalities Enshi Hubei 445000 China College of Life Science and Technology Image Processing and Intelligent Control Key Laboratory of Education Ministry of China Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)9780819478092

It is difficult to meet both direction and curvature constraints for traditional Fast Marching (FM) method in path planning. Based on adjusting the cost function in Eiknoal equation-the control equation for FM, a new model for computing the integrated cost function was presented in this paper. A relationship formula about curvature radius was obtained and three kinds of adjusting strategies were given;two of them were used to modify the route to meet with the requires of turning constraint in this paper. Experiments showed that the improved model can be used to plan the path with FMM for agent such as unmanned aerial vehicle (UAV) or robot, which is limited to pass through the scene matching areas. And our preliminary experiments demonstrated that the strategies are feasible and efficient to obtain path with certain curvature radius. The model can also be used to represent the problem such as an aircraft flying in a flow field. © 2009 Copyright SPIE - The International Society for Optical Engineering.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Fast algorithm of discrete Walsta-Haar transformation

Fast algorithm of discrete Walsta-Haar transformation

引用

International Conference on Space Information Technology

作者： Lu, Li Shi, Baochang Tian, Jinwen Liu, Jian State Education Commission Key Lab for Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan Hubei 430074 China Inst. for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan Hubei 430074 China Department of Mathematics Huazhong University of Science and Technology Wuhan Hubei 430074 China

Walsh-Haar function system that was first intruoduced by us is a new kind of function systems, and has a good global/local property. This function system is called Walsh ordering function system since its generation kernel functions belong to Walsh ordering Walsh function system. We worked out a recursive property of the matrix WHKRm+1 corresponding to the first KR m+1 Walsh-Haar functions in Walsh-Haar function system, and we also proved that Walsh-Haar function system is perfect and orthogonal similar to Walsh function system and Haar function system. Thus, discrete Walsh-Haar transformation (DW-HT) is an orthogonal transformation that can be widely used in signal processing. In this paper, using the recursive property of the matrix WHKRm+1 and the fast algorithm of discrete Walsh transformation (DWT) in Walsh ordering, we have designed a fast algorithm of Walsh ordering DW-HT based on the bisection technique. The idea and method used in this paper can be used for designing fast algorithms of other ordering DW-HTs and other discrete orthogonal transformations.

关键词： Mathematical transformations

来源：评论

学校读者我要写书评

暂无评论

Multiple objects segmentation based on Maximum-likelihood Estimation and Optimum Entropy-distribution(MLE-OED)

Proceedings - International Conference on Pattern Recognitio...

引用

Proceedings - International Conference on pattern recognition 2002年第1期16卷 707-710页

作者： Jun, Xie Tsui, H.T. Deshen, Xia Image Processing and Computer Vision Lab Department of Electronic Engineering Chinese University of Hong Kong Hong Kong Pattern Recognition Lab Department of Computer Science Nanjing University of Sci. and Tech. China

A new method based on MLE-OED is proposed for unsupervised image segmentation of multiple objects which have fuzzy edges. It adjusts the parameters of a mixture of Gaussian distributions via minimizing a new loss function proposed to implement image segmentation based on the image's local spatial information and global intensity distribution properties . The loss function consists of two terms: a local content fitting term, which optimizes the entropy distribution, and a global statistical fitting term, which maximizes the likelihood of the parameters for the given data. The proposed segmentation method was validated by simulated and real examples. Its performance in the experiments is better than those of two popular methods. © 2002 IEEE.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Data consistent artifact reduction for limited angle tomography with deep learning prior

arXiv

引用

arXiv 2019年

作者： Huang, Yixing Preuhs, Alexander Lauritsch, Günter Manhart, Michael Huang, Xiaolin Maier, Andreas Pattern Recognition Lab Friedrich-Alexander-Universitt Erlangen-Nrnberg Erlangen91058 Germany Siemens Healthcare GmbH Forchheim91301 Germany Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai200240 China Erlangen91058 Germany

Robustness of deep learning methods for limited angle tomography is challenged by two major factors: a) due to insufficient training data the network may not generalize well to unseen data;b) deep learning methods are sensitive to noise. Thus, generating reconstructed images directly from a neural network appears inadequate. We propose to constrain the reconstructed images to be consistent with the measured projection data, while the unmeasured information is complemented by learning based methods. For this purpose, a data consistent artifact reduction (DCAR) method is introduced: First, a prior image is generated from an initial limited angle reconstruction via deep learning as a substitute for missing information. Afterwards, a conventional iterative reconstruction algorithm is applied, integrating the data consistency in the measured angular range and the prior information in the missing angular range. This ensures data integrity in the measured area, while inaccuracies incorporated by the deep learning prior lie only in areas where no information is acquired. The proposed DCAR method achieves significant image quality improvement: for 120° cone-beam limited angle tomography more than 10% RMSE reduction in noise-free case and more than 24% RMSE reduction in noisy case compared with a state-of-the-art U-Net based method. Copyright © 2019, The Authors. All rights reserved.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Leveraging Open Knowledge for Advancing Task Expertise in Large Language Models

arXiv

引用

arXiv 2024年

作者： Yang, Yuncheng Qin, Yulei Wu, Tong Xu, Zihan Li, Gang Guo, Pengcheng Shao, Hang Shi, Yuchen Li, Ke Sun, Xing Yang, Jie Gu, Yun Institute of Image Processing and Pattern Recognition Institute of Medical Robotics Shanghai Jiao Tong University Shanghai200240 China Tencent YouTu Lab Shanghai200233 China

The cultivation of expertise for large language models (LLMs) to solve tasks of specific areas often requires special-purpose tuning with calibrated behaviors on the expected stable outputs. To avoid huge cost brought by manual preparation of instruction datasets and training resources up to hundreds of hours, the exploitation of open knowledge including a wealth of low rank adaptation (LoRA) models and instruction datasets serves as a good starting point. However, existing methods on model and data selection focus on the performance of general-purpose capabilities while neglecting the knowledge gap exposed in domain-specific deployment. In the present study, we propose to bridge such gap by introducing few human-annotated samples (i.e., K-shot) for advancing task expertise of LLMs with open knowledge. Specifically, we develop an efficient and scalable pipeline to cost-efficiently produce task experts where K-shot data intervene in selecting the most promising expert candidates and the task-relevant instructions. A mixture-of-expert (MoE) system is built to make the best use of individual-yet-complementary knowledge between multiple experts. We unveil the two keys to the success of a MoE system, 1) the abidance by K-shot, and 2) the insistence on diversity. For the former, we ensure that models that truly possess problem-solving abilities on K-shot are selected rather than those blind guessers. Besides, during data selection, instructions that share task-relevant contexts with K-shot are prioritized. For the latter, we highlight the diversity of constituting experts and that of the fine-tuning instructions throughout the model and data selection process. Extensive experimental results confirm the superiority of our approach over existing methods on utilization of open knowledge across various tasks. Our codes will be available at https://***/Yaphabates/Rocket. © 2024, CC BY.

关键词： Pipeline codes

来源：评论

学校读者我要写书评

暂无评论

Multifeature distance map based detection of small infrared targets with low contrast in image sequences

Multifeature distance map based detection of small infrared ...

引用

International Conference on Space Information Technology

作者： Wang, Zhicheng Gao, Chenqiang Tian, Jinwen Liu, Jian Chen, Xiangping State Education Commission Key Lab for Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan Hubei 430074 China Inst. for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan Hubei 430074 China Electronic and Engineering Department Huazhong University of Science and Technology Wuhan Hubei 430074 China

Target detection techniques play an important role in automatic target recognition (ATR) systems because overall ATR performance depends closely on detection results. In this paper, a novel method for fusion detection of infrared weak targets based on multifeature distance map (MFDM) in image sequences is proposed. As for small weak targets, there are many features, such as local entropy, average gradient strength. These features depict the characteristics of small infrared targets and can be extracted. Multifeature-based fusion techniques are applied to detect such weak targets. The problem of detecting small targets is converted to search peak values in specified feature space where multifeature vectors space (MFVS) is considered. Distance map (DM) can be derived according to feature vectors and target detection is performed in DM. In order to accumulate energy of targets deeply and suppress background and clutters to a great extent, five distance maps obtained by corresponding five consecutive frames are utilized to fuse with average weight, which results in the fact that the contrast between targets and background including clutters are enlarged and that the feature peaks of targets are obvious different from background and clutters. After these steps, a contrast segmentation method is used to extract targets from complicated background on the fused DM. Actual infrared image sequences in background of sea and sky are applied to validate the proposed approach. Experimental results demonstrate the robustness of the proposed method with high performance.

关键词： Automatic target recognition

来源：评论

学校读者我要写书评

暂无评论

Scale-space anisotropic total variation for limited angle tomography

arXiv

引用

arXiv 2017年

作者： Huang, Yixing Taubmann, Oliver Huang, Xiaolin Haase, Viktor Lauritsch, Guenter Maier, Andreas Pattern Recognition Lab Friedrich-Alexander-University Erlangen-Nuremberg Erlangen Germany Pattern Recognition Lab FriedrichAlexander-University Erlangen-Nuremberg Erlangen Germany Erlangen Germany Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China Siemens Healthcare GmbH Forchheim Germany Department of Radiology University of Utah Salt Lake CityUT United States

This paper addresses streak reduction in limited angle tomography. Although the iterative reweighted total variation (wTV) algorithm reduces small streaks well, it is rather inept at eliminating large ones since total variation (TV) regularization is scale-dependent and may regard these streaks as homogeneous areas. Hence, the main purpose of this paper is to reduce streak artifacts at various scales. We propose the scale-space anisotropic total variation (ssaTV) algorithm in two different implementations. The first implementation (ssaTV-1) utilizes an anisotropic gradient-like operator which uses 2 · s neighboring pixels along the streaks' normal direction at each scale s. The second implementation (ssaTV-2) makes use of anisotropic down-sampling and up-sampling operations, similarly oriented along the streaks' normal direction, to apply TV regularization at various scales. Experiments on numerical and clinical data demonstrate that both ssaTV algorithms reduce streak artifacts more effectively and efficiently than wTV, particularly when using multiple scales. Copyright © 2017, The Authors. All rights reserved.

关键词： Anisotropy

来源：评论

学校读者我要写书评

暂无评论

NiuEM: A Nested-iterative Unsupervised Learning Model for Single-particle Cryo-EM image processing

NiuEM: A Nested-iterative Unsupervised Learning Model for Si...

引用

2020 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2020

作者： Hu, Rui Cai, Jiaming Zheng, Wangjie Yang, Yang Shen, Hong-Bin Shanghai Jiao Tong University Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Department of Computer Science and Engineering Shanghai200240 China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China Shanghai Jiao Tong University Department of Bioinformatics and Biostatistics Shanghai200240 China

ISBN: (纸本)9781728162157

Cryo-electron microscopy (cryo-EM) has become a mainstream technology for solving spatial structures of biomacromolecules, while the processing of cryo-EM images is a very challenging task. One of the great challenges is the high noise in the images. A common method is to cluster the images with close projecting angles to get mean images, which are used for 3D reconstruction. However, due to the extremely low signal-to-noise-ratio, common clustering methods often fail to obtain high-quality mean images, leading to poorly reconstructed structures. In this study, we present a new unsupervised learning framework, called NiuEM, to discriminate images captured from different angles and yield cluster-mean images. NiuEM first generates pseudo-labels and then exploits both contrastive loss and cross-entropy loss for training convolutional layers to learn feature representations. Moreover, the pseudo-labels are updated iteratively to enhance the reliability of labels. We assess the performance of NiuEM on four data sets via both visualized and quantitative experiments. Especially, two kinds of metrics are adopted to measure the performance, regarding the clustering quality and the resolution of reconstructed 3D models, respectively. The experimental results show that NiuEM achieves very competitive clustering accuracy in the comparison with the state-of-the-art image clustering methods. Moreover, the cluster mean images yielded by NiuEM lead to better initial 3D models compared with the mainstream reconstruction tools. © 2020 IEEE.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

FVC2004: Third fingerprint verification competition 1

引用

1st International Conference on Biometric Authentication, ICBA 2004

作者： Maio, Dario Maltoni, Davide Cappelli, Raffaele Wayman, Jim L. Jain, Anil K. Biometric System Lab - DEIS University of Bologna via Sacchi 3 Cesena47023 Italy Biometric Test Center College of Engineering San Jose State University San JoseCA95192 United States Pattern Recognition and Image Processing Laboratory Michigan State University East LansingMI48824 United States

ISBN: (数字)9783540259480

ISBN: (纸本)3540221468

A new technology evaluation of fingerprint verification algorithms has been organized following the approach of the previous FVC2000 and FVC2002 evaluations, with the aim of tracking the quickly evolving state-ofthe- art of fingerprint recognition systems. Three sensors have been used for data collection, including a solid state sweeping sensor, and two optical sensors of different characteristics. The competition included a new category dedicated to "light" systems, characterized by limited computational and storage resources. This paper summarizes the main activities of the FVC2004 organization and provides a first overview of the evaluation. Results will be further elaborated and officially presented at the International Conference on Biometric Authentication (Hong Kong) on July 2004. © Springer-Verlag Berlin Heidelberg 2004.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

Classification of gothic and baroque architectural elements

Classification of gothic and baroque architectural elements

引用

International Conference on Systems, Signals and image processing, IWSSIP

作者： Gayane Shalunts Yll Haxhimusa Robert Sablatnig Institute of Computer Aided Automation Computer Vision Laboratory University of Technology Vienna Austria Institute of Computer Graphics and Algorithms Pattern Recognition and Image Processing Lab University of Technology Vienna Austria

Architectural elements are the components and details of buildings. Their unique set, combination, design, construction technique form the architectural style of buildings. Building facade classification by architectural styles is viewed as a task of classifying separate architectural structural elements. In the scope of building facade architectural style classification the current paper targets the problem of classification of Gothic and Baroque architectural elements called tracery, pediment and balustrade. Since certain gradient directions dominate on the shape of each architectural element, discrimination between dominating gradients means classification of architectural elements and thus architectural styles. We use local features to describe gradient directions. Our approach is based on clustering and learning of local features and yields a high classification rate.

关键词： Shape Three dimensional displays Visualization Computer vision Histograms Windows

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：