检索结果-内蒙古大学图书馆

2012 International conference on Computer Science and Information processing, CSIP 2012

作者： Liu, Weihao Cai, Xuan Mei, Lin Third Research Institute of Ministry of Public Security Shanghai China

ISBN: (纸本)9781467314114

Ordinary Lucy-Richardson (LR) restoration algorithms are used to restore high SNR degraded images including astronomical images and achieve good results. The algorithms are very sensitive to noises and use the assumptionnoises observe the Possion distribution. However, there are always Gaussian noises in natural images. In this paper, we propose a regularization LR-algorithm based on the Gaussian noises model. Our algorithm involves two regularization methods. One gives regularization restriction to the residual signal of the restored image. The other gives regularization restriction to the sparse gradient of the restored image, which is different with the conventional gratitude restriction. They can efficiently suppress the amplification of noises and preserve the details of images. Finally, we show the advancement of our algorithm using some experiment data. © 2012 IEEE.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Research on Detection Algorithm Based on YOLO and Lightweight Network EfficientNet 2

Research on Detection Algorithm Based on YOLO and Lightweigh...

引用

2nd International conference on image processing and Media Computing, ICIPMC 2023

作者： Zhang, Yang Chen, Zhongxiao Zhang, Jingyu Zhao, Yifan Xi'An Technological University School of Electronic Information Engineering Xi'an China Xi'An Technological University School of Mechatronic Engineering Xi'an China

ISBN: (纸本)9798350326611

Deep learning based object detection algorithms have been applied in various fields of life. As a representative of one-stage detection algorithms, YOLO series algorithms are highly favored for their fast *** resolve the existing issues with complex network architecture and weak real-time performance. YOLOv3 and YOLOv4 are improved by adding the lightweight network EfficientNet, using deep separable convolution rather than regular convolution, reducing a significant number of network parameters, using transfer learning to speed up the model's training speed, and speeding up the model's convergence. Finally, the accuracy, number of parameters, and detection rate of the network structure before as well as after improvement are compared to ensure that the model is successful. According to the experimental findings, the number of parameters for E-YOLOv3 and E-YOLOv4 are only 1/9 and 1/7 of what they were before the enhancement, and the detection rate has increased by 4 and 3 frames/second, respectively. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Novel medical image enhancement algorithms

Novel medical image enhancement algorithms

引用

conference on image processing - algorithms and systems VIII

作者： Agaian, Sos McClendon, Stephen A. Univ Texas San Antonio Ctr Simulat Visualizat & Real Time Predict Dept Elect & Comp Engn Multimedia & Mobile Signals Proc Lab San Antonio TX 78249 USA

ISBN: (纸本)9780819479259

In this paper, we present two novel medical image enhancement algorithms. The first, a global image enhancement algorithm, utilizes an alpha-trimmed mean filter as its backbone to sharpen images. The second algorithm uses a cascaded unsharp masking technique to separate the high frequency components of an image in order for them to be enhanced using a modified adaptive contrast enhancement algorithm. Experimental results from enhancing electron microscopy, radiological, CT scan and MRI scan images, using the MATLAB environment, are then compared to the original images as well as other enhancement methods, such as histogram equalization and two forms of adaptive contrast enhancement. An image processing scheme for electron microscopy images of Purkinje cells will also be implemented and utilized as a comparison tool to evaluate the performance of our algorithm.

关键词： Medical image Enhancement Global image Enhancement Adaptive Contrast Enhancement Global Sharpening Enhancement Algorithm Cascaded Unsharp Masking Purkinje Cell image processing Scheme

来源：评论

学校读者我要写书评

暂无评论

Fast multiresolution contour completion

Fast multiresolution contour completion

引用

conference on image processing - algorithms and systems VI

作者： Papari, G. Petkov, N. Univ Groningen Inst Math & Comp Sci NL-9700 AK Groningen Netherlands

ISBN: (纸本)9780819469847

We consider the problem of improving contour detection by filling gaps between collinear contour pieces. A fast algorithm is proposed which takes into account local edge orientation and local curvature. Each edge point is replaced by a curved elongated patch, whose orientation and curvature match the local edge orientation and edge. The proposed contour completion algorithm is integrated in a multiresolution framework for contour detection. Experimental results show the superiority of the proposed method to other well-established approaches.

关键词： Sensors Detection and tracking algorithms Binary data image analysis image processing Information visualization Logic algorithms Machine vision Mathematics

来源：评论

学校读者我要写书评

暂无评论

Super-Resolution Pre-processing of Data from Undersampled Imaging systems for Phase Diversity

Super-Resolution Pre-Processing of Data from Undersampled Im...

引用

conference on Applications of Digital image processing XXXV

作者： Shields, Eric A. Sandia Natl Labs Albuquerque NM 87185 USA

ISBN: (纸本)9780819492166

Phase diversity algorithms allow wavefront and an estimate of the scene to be reconstructed from multiple images with a known phase change between measurements. These algorithms rely on sampling requirements that are frequently not met in remote sensing imaging systems. It is demonstrated that super-resolution pre-processing of imagery from undersampled systems can effectively increase the sampling, thereby allowing application of traditional phase diversity algorithms. Experimental results are presented for both a point object and an extended scene.

关键词： Phase diversity phase retrieval super-resolution

来源：评论

学校读者我要写书评

暂无评论

Energy and Execution Time Comparison of Optical Flow algorithms on SIMD and GPU Architectures 12

Energy and Execution Time Comparison of Optical Flow Algorit...

引用

12th conference on Design and Architectures for Signal and image processing (DASIP)

作者： Petreto, Andrea Hennequin, Arthur Koehler, Thomas Romera, Thomas Fargeix, Yohan Gaillard, Boris Bouyer, Manuel Meunier, Quentin L. Lacassagne, Lionel Sorbonne Univ CNRS LIP6 F-75005 Paris France Lheritier Alcen F-95862 Cergy Pontoise France

ISBN: (纸本)9781538682371

This article presents and compares optimized implementations of two optical flow algorithms on several target boards comprising multi-core SIMD processors and GPUs. The two algorithms are Horn-Schunck (HS) and TV-L1, and have been chosen because they are both well-known, and because of their different computational complexity and accuracy. For both algorithms, we have made parallel optimized SIMD implementations, while HS has also been implemented on GPUs. For each algorithm, the comparison between the different versions and target boards is carried out in a two-dimensional fashion: in terms of computing speed-in order to achieve real-time computation-and in terms of energy consumption since we target embedded systems. The results show that for HS, the GPUs are the most efficient in both dimensions, able to process in realtime performances (25 frames per second) up to 8Mpix images for 0.35J per image, against 1.8Mpix images for 0.24J per image on CPU. The results also highlight the impact of optimizations on TV-L1: far slower than HS without optimization, it can almost match its performance after optimization on CPU, and can achieve real-time performances with 0.25J for 1.4Mpix images. We hope these results will help developers design optical flow embedded systems.

关键词： Optimization Graphics processing units Optical imaging Computer architecture Real-time systems Embedded systems Power demand

来源：评论

学校读者我要写书评

暂无评论

CONTOURLET TRANSFORM-BASED STRUCTURAL SIMILARITY FOR image QUALITY ASSESSMENT

CONTOURLET TRANSFORM-BASED STRUCTURAL SIMILARITY FOR IMAGE Q...

引用

IEEE International conference on Intelligent Computing and Intelligent systems

作者： Yang, Chun-Ling Wang, Fan xiao, Dongqin S China Univ Technol Sch Elect & Informat Engn Guangzhou 510640 Guangdong Peoples R China

ISBN: (纸本)9781424447541

The research on image presentation and image processing algorithms in Contourlet domain has been increasingly wide and deep. Combined frequency band property of different direction and the perfect coefficient features of Contourlet transform, a new method of image quality. assessment based on Structural Similarity (SSIM) and human vision system (HVS)-CT-SSIM is proposed in this paper. Theory analysis and experimental results show that the proposed CT-SSIM is more accurate and has better correlation with the subjective assessment of human beings. Also it can easily be embedded in image processing algorithms in Contourlet domain, to guide and optimize the processing algorithms.

关键词： Contourlet Transform (CT) structural similarity (SSIM) human visual system (HVS) Contourlet Transform based Structural Similarity (CT-SSIM)

来源：评论

学校读者我要写书评

暂无评论

Solving Optimization Problems Through Fully Convolutional Networks: An Application to the Traveling Salesman Problem

引用

IEEE TRANSACTIONS ON systems MAN CYBERNETICS-systems 2021年第12期51卷 7475-7485页

作者： Ling, Zhengxuan Tao, xinyu Zhang, Yu Chen, xi Zhejiang Univ Coll Control Sci & Engn Hangzhou 310027 Peoples R China Zhejiang Univ Coll Control Sci & Engn Key Lab Ind Control Technol Hangzhou 310027 Peoples R China

In the new wave of artificial intelligence, deep learning is impacting various industries. As a closely related area, optimization algorithms greatly contribute to the development of deep learning. But the reverse applications are still insufficient. Is there any efficient way to solve certain optimization problem through deep learning? The key is to convert the optimization to a representation suitable for deep learning. In this article, a traveling salesman problem (TSP) is studied. Considering that deep learning is good at image processing, an image representation method is proposed to transfer a TSP to an image. Based on samples of a ten city TSP, a fully convolutional network (FCN) is used to learn the mapping from a feasible region to an optimal solution. The training process is analyzed and interpreted through stages. A visualization method is presented to show how an FCN can understand the training task of a TSP. Once the training is completed, no significant effort is required to solve a new TSP and the prediction is obtained on the scale of milliseconds. The results show good performance in finding the global optimal solution. Moreover, the developed FCN model has been demonstrated on TSP's with different city numbers, proving excellent generalization performance.

关键词： Urban areas Optimization Deep learning Neural networks Feature extraction image resolution Heuristic algorithms Deep learning fully convolutional network (FCN) mapping optimization traveling salesman

来源：评论

学校读者我要写书评

暂无评论

Implementation of fractal image coding for GPGPU systems and its power-aware evaluation

Implementation of fractal image coding for GPGPU systems and...

引用

6th IEEE International systems conference (SYS CON)

作者： Wakatani, Akiyoshi Konan Univ Fac Intelligence & Informat Higashinada Ku Kobe Hyogo 6588501 Japan

ISBN: (纸本)9781467307499

GPGPU (General Purpose computing on Graphic processing Unit) systems attract a great deal of attention, which are used for general-purpose computations like numerical calculations as well as graphic processing, but the peak power consumption of the GPU is relatively high. On the other hand, fractal image coding is one of the most prominent compression technologies. It can be also used for industrial applications like image indexing methods and image retrieval methods. In this paper, we implement parallel programs for the fractal image coding algorithms on GPGPU systems by using CUDA (Compute Unified Device Architecture) and discuss the power-aware evaluation of the application. We also consider the availability of the GPU from the point of view of the green computing.

关键词： multithread parallel processing GPU image coding multicore processor CUDA

来源：评论

学校读者我要写书评

暂无评论

An Online System for Algorithm Benchmarking 5

An Online System for Algorithm Benchmarking

引用

5th IEEE International conference on Cognitive Infocommunications (CogInfoCom)

作者： Toth, Janos Kovacs, Laszlo Harangi, Balazs Kiss, Csaba Mohacsi, Andras Orosz, Zoltan Hajdu, Andras Univ Debrecen Inst Math POB 12 H-4010 Debrecen Hungary Univ Debrecen Fac Informat H-4010 Debrecen Hungary

We present a platform that will aid researchers in developing algorithms for specific (primarily image processing) tasks by providing training data sets with ground truth and with providing evaluation of the outputs o... 详细信息

ISBN: (纸本)9781479972807

关键词： image processing online algorithm benchmarking system training data sets Benchmark testing Classification algorithms Educational institutions image processing Retinopathy Standards Training data image processing Benchmark testing Training data Sorting algorithm Educational institutions Retinopathy Online systems Dataset

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：