检索结果-内蒙古大学图书馆

1992 ieee-SP International symposium on Time-Frequency and Time-Scale Analysis

作者： Shi, J.Y. Tsui, H.T. Li, J.G. Dept. of Electron. Eng. Chinese Univ. of Hong Kong Shatin N.T. Hong Kong Image Processing Institute Jiao Tong University Shanghai200030 China

ISBN: (纸本)0780308050

The first processing stage in computational vision is to analyze the information content of an image in different scales by Marr's computational vision theory [1]. Multiscale signal decomposition is thus needed. There exist many ways for this decomposition such as Mallat's wavelet representation [Z], Burt's pyramid, Marr's primal sketch and Shi's morphologic primal sketch. But none of them claimed success in organizing information extracted from an image in different scales. In this paper we introduce a new way for multiscale signal decomposition named as Fejér filtering because it uses the FejCr kernel in the classical Fourier analysis. It is built on a diffraction imaging model from the perspective of Fourier optics based on the uncertainty principle and the argument that a real signal should be bandlimited 131. It is the first part of our work toward a well-organized multiscale representation in computational vision. © 1992 ieee.

关键词： Fourier analysis

来源：评论

学校读者我要写书评

暂无评论

Dynamic 3D shape from multi-viewpoint images using deformable mesh model 3

Dynamic 3D shape from multi-viewpoint images using deformabl...

引用

3rd International symposium on image and signal processing and Analysis (ISPA)

作者： Nobuhara, S Matsuyama, T Kyoto Univ Grad Sch Informat Sakyo Ku Kyoto 6068501 Japan

ISBN: (纸本)953184061X

This paper presents a framework for dynamic 3D shape reconstruction from multi-viewpoint images using a deformable mesh model. With our method, we can obtain 3D shape and 3D motion of the object simultaneously. We represent the shape by a surface mesh model and the motion by translations of its vertices, i.e., deformation. Thus global and local topological structure of the mesh are preserved from frame to frame. This helps us to analyse the motion of the object, to compress the 3D data, and so on. Our model deforms its shape so as to satisfy several constraints. This constraint-based deformation provides a computational framework to integrate several reconstruction cues such as surface texture, silhouette, and motion flow observed in multi-viewpoint images.

关键词： Deformable models Humans image motion analysis image reconstruction Informatics Motion analysis Photometry Shape Surface reconstruction Surface texture

来源：评论

学校读者我要写书评

暂无评论

Target reaching by using visual information and Q-learning controllers

引用

AUTONOMOUS ROBOTS 2000年第1期9卷 41-50页

作者： Distante, C Anglani, A Taurisano, F Univ Lecce Dipartimento Ingn Innovaz I-73100 Lecce Italy CNR Signal & Image Processing Inst IESI I-70126 Bari Italy

This paper presents a solution to the problem of manipulation control: target identification and grasping. The proposed controller is designed for a real platform in combination with a monocular vision system. The objective of the controller is to learn an optimal policy to reach and to grasp a spherical object of known size, randomly placed in the environment. In order to accomplish this, the task has been treated as a reinforcement problem, in which the controller learns by a trial and error approach the situation-action mapping. The optimal policy is found by using the Q-Learning algorithm, a model free reinforcement learning technique, that rewards actions that move the arm closer to the target. The vision system uses geometrical computation to simplify the segmentation of the moving target (a spherical object) and determines an estimate of the target parameters. To speed-up the learning time, the simulated knowledge has been ported on the real platform, an industrial robot manipulator PUMA 560. Experimental results demonstrate the effectiveness of the adaptive controller that does not require an explicit global target position using direct perception of the environment.

关键词： reinforcement learning behavior based robotic manipulator visual servoing Hough transform

来源：评论

学校读者我要写书评

暂无评论

Genetic lips extraction method for varying shape

Genetic lips extraction method for varying shape

引用

ieee International symposium on computational intelligence in Robotics and Automation

作者： Akashi, T Mitsukura, Y Fukumi, M Akamatsu, N Univ Tokushima Grad Sch Engn Tokushima 770 Japan

ISBN: (纸本)0780378660

In this paper, a lips extraction method that can extract lips region from varying lips shape at the moment of speech by using only one template image is described. The method that is proposed in this paper, has invariance for an open and closed mouth, showing or not showing any teeth, and has high speed and high extraction accuracy in consideration for characteristics of the lips by using a genetic method. This method uses the template matching using a genetic algorithm. Furthermore, colour of lips and characteristics of the lips shape variances at the moment of speech in this system are utilized. The effectiveness of this method is demonstrated with only one template for each person being tested and a search object, that is, the varying lips shape at the moment of speech of vowels by means of computer simulations. These computer simulations indicate that this method can extract the varying lips shape at the moment of speech by using only one template. Moreover, in the extraction processing of every vowel, a high speed and high extraction accuracy can be obtained.

关键词： template matching genetic algorithm lips image

来源：评论

学校读者我要写书评

暂无评论

MCTE: MARRYING CONVOLUTION AND TRANSFORMER EFFICIENTLY FOR END-TO-END MEDICAL image SEGMENTATION 30

MCTE: MARRYING CONVOLUTION AND TRANSFORMER EFFICIENTLY FOR E...

引用

30th ieee International Conference on image processing (ICIP)

作者： Li, Jiuqiang Southwest Jiaotong Univ Sch Comp & Artificial Intelligence Chengdu Peoples R China

ISBN: (纸本)9781728198354

The purpose of the medical image segmentation task is to delineate different organs or lesion regions in the image, which is an important aid for intelligent clinical medical diagnosis. Recent approaches suffer from the inability to obtain reliable attention, are computationally intensive, and do not exploit the relationships between different samples. We marry convolution and Transformer effectively to establish MCTE for medical image segmentation. The proposed MCTE is an end-to-end network based on U-Net with a parallel learning of three types of attention, namely local attention learning with channel and spatial dimensional convolution, global attention learning with smaller computational effort of swin transformer, and external attention learning with two shared memory storing all medical image information. Extensive experimental results on the ACDC and Synapse dataset, which are widely used for the evaluation of medical image segmentation methods, demonstrate that our proposed method exceeds the compared baseline.

关键词： Medical image Segmentation Transformer Convolution Attention Mechanism

来源：评论

学校读者我要写书评

暂无评论

Chaldene: Towards Visual Programming image processing in Jupyter Notebooks

Chaldene: Towards Visual Programming Image Processing in Jup...

引用

2022 ieee symposium on Visual Languages and Human-Centric Computing

作者： Chen, Fei Slusallek, Philipp Mueller, Martin Dahmen, Tim German Res Ctr Artificial Intelligence DFKI Saarbrucken Germany Saarland Univ Saarbrucken Germany

ISBN: (纸本)9781665442152;9781665442145

Jupyter Notebook [1] is an open source, interactive computing platform widely used in the scientific computing and artificial intelligence community [2], [3], [4], [5]. The popularity of the platform is a consequence of the generated single notebook document combining source code, markdown, and visualizations (Fig.1). This makes the platform ideal for tasks such as data analysis and scientific image processing, where repeatability and transparency of analysis tasks are just as important as functionality and performance. However, the obligatory use of code is an obstacle to acceptance of the platform in scientific communities where programming is not generally taught in the curriculum. Consequently, many experimental communities rely on manual image processing using graphical user interfaces [6], [7], [8]. The obvious disadvantages are the lack of repeatability, transparency, and precision in image processing and data analysis tasks. To solve these issues, we propose to extend Jupyter Notebook with visual programming cells. In each visual programming cell, users can create the program by assembling graphical nodes that represent computational instructions, and the textual program is automatically generated and executed by the environment. Cells will support version control aware serialization and deserialization. The core innovation of our proposed work lies in a change of workflow and the adaption of a jupyter-based workflow in experimental communities that have no culture of working with source code. The system can be adapted to multiple applications and domains by integrating new node types. We hereby present an early version of the system and provide one use case from microscopy image processing to demonstrate the integration of existing non-Python software.

关键词： VPL visual programming language graphical programming Jupyter Notebook image processing

来源：评论

学校读者我要写书评

暂无评论

2013 ieee International Conference on computational intelligence and Computing Research, ieee ICCIC 2013

2013 IEEE International Conference on Computational Intellig...

引用

2013 4th ieee International Conference on computational intelligence and Computing Research, ieee ICCIC 2013

ISBN: (纸本)9781479915972

The proceedings contain 186 papers. The topics discussed include: a cloud-based architecture for big-data analytics in smart grid: a proposal;optical character recognition for scene text detection, mining and recognition;domain knowledge enriched framework for restricted domain question answering system;a novel approach to link semantic gap between images and tags via probabilistic ranking;web based security with LOPass user authentication protocol in mobile application;double ended speech enabled system in Indian travel & tourism industry;particle swarm optimization based parameter optimization technique in medical information hiding;application of image processing for a bubble column reactor;a modern avatar of Julius Ceasar and Vigenere cipher;parallel image segmentation using multi-threading and k-means algorithm;an ICMP based secondary cache approach for the detection and prevention of ARP poisoning;and digital image watermarking using fractional Fourier transform via image compression.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Robust designs for templates of directional extraction cellular neural network with application

Robust designs for templates of directional extraction cellu...

引用

International Conference on computational intelligence and Security

作者： Liu, Jinzhu Min, Lequan Univ Sci & Technol Beijing Sch Informat Engn Beijing 100083 Peoples R China Univ Sci & Technol Beijing Sch Appl Sci & Informat Engn Beijing 100083 Peoples R China

ISBN: (纸本)9780769530734

The cellular neural/nonlinear network (CNN) is a powerful tool for image and video signal processing, robotic and biological visions. In this paper, the Selected Objects Extraction (SOE) CNN was generated to Directional Extraction (DE) CNN which enhance the capabilities of CNNs and improve their efficiency. Based on analytical approach, a theorem of designing robust templates for DE CNNs was established, which provides parameter inequalities to determine parameter intervals for implementing the corresponding functions. Several examples are provided to illustrate the effectiveness of the theorem for extracting selected objects directionally in binary images.

关键词： Video signal processing

来源：评论

学校读者我要写书评

暂无评论

INCORPORATING image DEGENERATION MODELING WITH MULTITASK LEARNING FOR image SUPER-RESOLUTION

INCORPORATING IMAGE DEGENERATION MODELING WITH MULTITASK LEA...

引用

ieee International Conference on image processing (ICIP)

作者： Liang, Yudong Wang, Jinjun Zhang, Shizhou Gong, Yihong Xi An Jiao Tong Univ Inst Artificial Intelligence & Robot 28 West Xianning Rd Xian 710049 Shaanxi Peoples R China

ISBN: (纸本)9781479983391

Learning the non-linear image upscaling process has previously been considered as a simple regression process, where various models have been utilized to describe the correlations between high-resolution (HR) and low-resolution (LR) images/patches. In this paper, we present a multitask learning framework based on deep neural network for image super-resolution, where we jointly consider the image super resolution process and the image degeneration process. By sharing parameters between the two highly relevant tasks, the proposed framework could effectively improve the obtained neural network based mapping model between HR and LR image patches. Experimental results have demonstrated clear visual improvement and high computational efficiency, especially with large magnification factors.

关键词： super-resolution multitask learning autoencoder degeneration modeling

来源：评论

学校读者我要写书评

暂无评论

Striping removal in multi-beam passive millimeter wave image

Striping removal in multi-beam passive millimeter wave image

引用

International symposium on intelligence Information processing and Trusted Computing

作者： Ye, Hongyi Li, Liangchao Yang, Jianyu School of Electronics Engineering University of Electronic Science and Technology of China Chengdu 611731 China

ISBN: (纸本)9780769541969

The usage of multi-beam antenna in passive millimeter wave imaging system reduces the time of imaging, but this system structure leads to striping in the image acquired. By analyzing the characteristics of passive millimeter wave image and the spectrum distribution of striping noise, use a modified Butterworth low pass filter to remove striping in frequency domain. Confirm the cut-off frequency of the filter with the point spread function (PSF), which is estimated by using the antenna pattern data. The simulation shows that this method is effective in striping removal. © 2010 ieee.

关键词： Optical transfer function

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：