检索结果-内蒙古大学图书馆

Electronics System-Integration Technology Conference, ESTC

作者： K. Baishya G.M Zhang D.M. Harvey D.R. Braden General Engineering Research Institute Liverpool John Moores University Liverpool United Kingdom Delphi Electronics & Safety Kirkby Liverpool United Kingdom

ISBN: (纸本)9781509014033

A signal processing toolbox has been realized to enhance the acoustic signal processing of manufactured electronic systems. The toolbox contains a range of signal processing algorithms to help better differentiate the 3D scanned acoustic signals acquired from manufactured parts. The processing has been used to assess the through-life reliability of systems by non-destructively sampling systems during extended reliability tests. The algorithms are based on a variety of novel signal processing methods such as wavelet, time frequency domain imaging, dictionaries and Fast Fourier Transform (FFT) for comparison. The paper will explore how the various algorithms can be tuned to test samples using the designed toolbox. The toolbox has a graphical user interface (GUI) designed in MATLAB. It can control the processing and display of 3D image data “cubes” acquired from an array of A-Scans of a sample obtained by an acoustic microscope. In this case a Sonoscan Gen6 C-SAM acoustic microscope has been used, but if the data format is known the toolbox can be applied to any 3D cube of data. The data sizes can be large, so processing times can be of the order of minutes for 1k × 1k × 1k array. Recently the execution times have been speeded up considerably by employing parallel algorithms and multicore processing. Some routines now only take seconds which is a very significant speed-up.

关键词： Acoustics Three-dimensional displays Matching pursuit algorithms Two dimensional displays MATLAB Flip-chip devices image processing

来源：评论

学校读者我要写书评

暂无评论

Efficient GPU Computing Framework of Cloud Filtering in Remotely Sensed image processing

Efficient GPU Computing Framework of Cloud Filtering in Remo...

引用

Proceedings of the Digital image Computing: Technqiues and Applications (DICTA)

作者： Jing Ke Arcot Sowmya Yi Guo Tomasz Bednarz Michael Buckley School of Computer Science and Engineering UNSW / DATA61 CSIRO Sydney Australia School of Computer Science and Engineering UNSW Sydney Australia Mathematics Western Sydney University Sydney Australia DATA61 CSIRO Brisbane Australia DATA61 CSIRO Sydney Australia

For optical remote sensing images, an effective method to reduce or eliminate the impact of clouds is important. With big data input and real-time processing demands, efficient parallelization strategies are essential for high performance computing on multi-core systems. This paper proposes an efficient high performance parallel computing framework for cloud filtering and smoothing. A comparison and benchmarking of two parallel algorithms for cloud filtering that incorporates spatial smoothing solved by two-dimensional dynamic programming is implemented. The experiments were carried out on an NVIDIA GPU accelerator with evaluations of approximation, parallelism and performance. The test results show significant performance improvements with high accuracy compared with sequential CPU implementation, and can be applied to other multi-core systems.

关键词： Graphics processing units Smoothing methods Dynamic programming Indexes Instruction sets Heuristic algorithms Parallel processing

来源：评论

学校读者我要写书评

暂无评论

Parallel image processing on the Sunway Many-Core Processor

Parallel Image Processing on the Sunway Many-Core Processor

引用

IEEE International Conference on High Performance Computing and Communications (HPCC)

作者： Meiting Zhao Rui Liu Yi Liu Kaida Song Depei Qian State Key Lab of Mathematical Engineering and Advanced Computing Wuxi China Sino-German Joint Software Institute Beihang University Beijing China

ISBN: (纸本)9781509042982

Many image processing algorithms have been parallelized successfully on many-core processors, such as GPU and Intel Xeon Phi. In this paper, we choose the Sunway many-core processor SW26010, which is a new processor designed and made in China that constitutes the current NO.1 supercomputer Sunway TaihuLight. This paper firstly introduces the architecture of Sunway SW26010 processor and two representative image processing algorithms: local binary pattern (LBP) and histogram of oriented gradient (HOG). Furthermore we propose a method of parallel implementation, and the experimental results of this method show that the speedup can be up to 170 for LBP and 33 for HOG. Then two optimized methods are brought forward based on this parallel implementation, including the optimization of program and parallel design. We optimize the program by using the method that combined step transmission and software prefetching. From the experiment results of the first optimization we can know that the maximum speedup can reach 310 for LBP with processing high-resolution images and 83 for HOG. Then we optimize the parallel design by using a coarse grained parallel method, and the experimental results show that the speedup can be up to 370 for LBP and 95 for HOG when processing low-resolution images. Finally, we investigate the scalability of our parallelism on the Sunway TaihuLight with different number of processor nodes, and the experiment results prove that the two algorithms' parallel design and implementation have better expansibility.

关键词： Algorithm design and analysis image processing Supercomputers Computer architecture Clustering algorithms Optimization Parallel algorithms

来源：评论

学校读者我要写书评

暂无评论

BACKGROUND PRIOR AND BOUNDARY WEIGHT-BASED PEDESTRIAN SEGMENTATION IN INFRARED imageS

BACKGROUND PRIOR AND BOUNDARY WEIGHT-BASED PEDESTRIAN SEGMEN...

引用

IEEE International Conference on image processing

作者： Lu Li Yu Zheng Xiangzhi Bai Fugen Zhou Image Processing Center Beihang University 100191 Beijing China

ISBN: (纸本)9781467399623

Pedestrian segmentation in infrared images is a difficult problem for the defects of low SNR and inhomogeneous luminance distribution. In this paper, we propose a method which aims to obtain the accurate pedestrian segmentation through a background prior and boundary weight-based saliency. Background likelihood is firstly calculated as background prior to get an abstract representation for infrared pedestrian. Then, by considering the object-center prior, the object-biased Gaussian model is applied to derive the probability density estimation for pedestrians. Finally, the above two results are integrated with the boundary weight to obtain the final saliency map for infrared image, based on which pedestrians can be easily segmented. Experimental results on real infrared images captured by intelligent transportation systems demonstrate the effectiveness of the proposed approach against the state-of-the-art algorithms.

关键词： Decision support systems Indexes Field-flow fractionation field flow fractionation Pedestrians Infrared imaging decision support systems Infrared radiation Luminance distribution low SNR Intelligent transportation systems segmentation Segmentation Boundary boundary layer

来源：评论

学校读者我要写书评

暂无评论

Primer Defects Detection on Military Cartridge Cases

Primer Defects Detection on Military Cartridge Cases

引用

Nicograph International (NicoInt)

作者： Refik Samet Anar Bayram Serhat Tural Semra Aydin Computer Engineering Department Ankara University Ankara Turkey Institute of Informatics Gazi University Ankara Turkey

ISBN: (纸本)9781509023066

The military cartridge includes four elements, the case, the capsule, the ammunition and the powder. Defects may occur in the case during manufacturing. Defective cartridges must be detected and separated. Defects could occur in the parts of the mouth, the cylindrical surface and the primer of the case. This article proposes algorithms that involve the inspection of the defects of the primer parts of the cases with image processing techniques. The proposed algorithms were implemented on real images, and the obtained results showed that the fire hole and the tab defects occurred on the primer part of the case, and these are detected with high accuracy.

关键词： Fires Calibration Surface treatment image processing Real-time systems Inspection Detection algorithms

来源：评论

学校读者我要写书评

暂无评论

High speed vedic multiplier for image processing using FPGA

High speed vedic multiplier for image processing using FPGA

引用

International Conference on (ISCO) Intelligent systems and Control

作者： S. Jayakumar S. Sumathi Department of EIE Adhiyamaan College of Engineering Hosur

ISBN: (纸本)9781467378086

Vedic multiplier is based on the ancient algorithms (sutras) followed in INDIA for multiplication. This work is based on one of the sutras called “Nikhilam Sutra”. This sutra is meant for faster mental calculation. Though faster when implemented in hardware, it consumes more power than the conventional ones. This paper presents a technique to modify the architecture of the Vedic multiplier by using some existing methods in order to reduce power and improve image processing applicatio. The 32 × 32 Vedic multiplier is coded in Verilog HDL and Synthesized using Synopsys Design Compiler. The performance is compared in terms of area, data arrival time and power with earlier existing architecture of Vedic multiplier. Filtering involves lots of multiplications which consumes time. Time required increases with the increase in the number of pixels. This paper proposes an approach for image filtering using Vedic Mathematic which performs faster multiplication compared to the conventional algorithms namely Booth and Array Multiplication Algorithm thus reducing the time required for filtering of images. Time required by the algorithms for filtering are then compared using the experimental results.

关键词： DH-HEMTs

来源：评论

学校读者我要写书评

暂无评论

Towards an efficient high-level modeling of heterogeneous image processing systems

Towards an efficient high-level modeling of heterogeneous im...

引用

Theory of Modeling and Simulation (TMS-DEVS)

作者： Anna Deitsch Vitali Schneider Jennifer Kane Winfried Dulz Reinhard German Department of Computer Science 7 Friedrich-Alexander-University of Erlangen-Nuremberg Erlangen Germany

ISBN: (纸本)9781538618561

High-level formal modeling is a beneficial method for assisting system architects in early performance evaluations of desired hardware/software architectures and for coping with the continuously increasing complexity of heterogeneous systems. Modeling languages like UML allow expressive and concise specifications of algorithms, platforms, and infrastructure artifacts for different domains. Techniques are already available for deriving implementations but also executable simulations from UML-based specification models. We use such derived simulations for early investigation and validation of the behavior of the designed system. However, building specification models is often a very complex and time-consuming process, which highly depends on the designer's knowledge, used development process and modeling languages. In this paper, we introduce a holistic top-down modeling methodology developed for enabling an efficient design of heterogeneous image processing architectures using the standardized UML modeling language. Particularly, the suggested methodology focuses on improving user guidance with clear modeling workflows to achieve a less error-prone model design process and to reduce the system development effort. Moreover, we demonstrate how the specific domain knowledge can be captured directly in a UML conform modeling library and that this library enables us to express image processing algorithms in an efficient manner.

关键词： Unified modeling language Computational modeling image processing Analytical models Algorithm design and analysis Computer architecture Complexity theory

来源：评论

学校读者我要写书评

暂无评论

Comprative Study with Analysis of OCR algorithms and Invention Analysis of Character Recognition Approched Methodologies

Comprative Study with Analysis of OCR Algorithms and Inventi...

引用

International Conference on Power Electronics, Intelligent Control and Energy systems

作者： Santosh Kumar Henge B. Rama Department of Computer Science Kakatiya University Warangal Telangana State India

ISBN: (纸本)9781467385886

OCR is the most active, interesting evaluation invention of text cum character processing recognition and pattern based image recognition. In present life OCR has been successfully using in finance, legal, banking, health care and home need appliances. The OCR consists the different levels of processing methods like as image Pre Acquisition, Classification, Post-Acquisition, Pre-Level processing, Segmented processing, Post-Level processing, Feature Extraction. The many researchers are proposed various levels of different methodologies and approaches in different versions of languages with help of modern and traditional technologies. This paper expressed the detail study and analysis of various character recognition methods and approaches: in details like as flow and type of approached methodology was used, type of algorithm has built with support of technology has implemented background of the proposed methodology and invention best outcomes flow for the each methodology. This paper and also expressed the main objectives and ideology of various OCR algorithms, like as neural networks algorithm, structural algorithm, support vector algorithm, statistical algorithm, template matching algorithm along with how they classified, identified, rule formed, inferred for recognition of characters and symbols.

关键词： Support Vector Machine (SVM) Optical Character Recognition (OCR) Artificial Neural Network (ANN) Pattern Matching algorithms (PMA) Stastical Algorithm (SstA) Strctural Algorithm (SA) Freeman Chain Code (FCC) Digitized-Retrievable Rorm (DRF) Feedforwardneural Network (FfNN) Feedback-neural Network (FbNN) Top-down-hierarchical-histogram (THH) Mirror image Learning (MIL)

来源：评论

学校读者我要写书评

暂无评论

Acceleration of image reconstruction in 3D Electrical Capacitance Tomography in heterogeneous, multi-GPU system using sparse matrix computations and Finite Element Method

Acceleration of image reconstruction in 3D Electrical Capaci...

引用

Federated Conference on Computer Science and Information systems (FedCSIS)

作者： Paweł Kapusta Michał Majchrowicz Dominik Sankowski Lidia Jackowska-Strumiłło Lodz University of Technology Institute of Applied Computer Science Poland

3D Electrical Capacitance Tomography provides a lot of challenging computational issues that have been reported in the past by many researchers. image reconstruction using deterministic methods requires execution of many basic operations of linear algebra. Due to significant sizes of matrices used in ECT for image reconstruction and the fact that best image quality is achieved by using algorithms of which significant part is FEM and which are hard to parallelize or distribute. In order to solve these issues a new set of algorithms had to be developed.

关键词： image reconstruction Sparse matrices Finite element analysis Three-dimensional displays Algorithm design and analysis Graphics processing units Electrodes

来源：评论

学校读者我要写书评

暂无评论

结合暗原色优先和Gamma校正的红外交通图像增强算法

引用

交通运输工程学报 2016年第6期16卷 149-158页

作者：顾明郑林涛刘中华清华大学精密仪器系北京100084 河南科技大学信息工程学院河南洛阳471023 悉尼科技大学量子计算与智能系统中心

为了有效提高智能交通监控设备采集到的红外交通图像的视觉质量,将可见光图像去雾的方法引入红外交通图像的增强处理过程中,提出一种结合暗原色优先和Gamma校正的红外交通图像增强新算法,首先采用暗原色优先算法对原始降质红外交通图像... 详细信息

为了有效提高智能交通监控设备采集到的红外交通图像的视觉质量,将可见光图像去雾的方法引入红外交通图像的增强处理过程中,提出一种结合暗原色优先和Gamma校正的红外交通图像增强新算法,首先采用暗原色优先算法对原始降质红外交通图像进行处理而得到初步增强的图像,然后使用Gamma校正算法对初步增强的图像亮度进行调节,并将新算法与其他常见的红外图像增强算法进行图像增强效果的对比分析。试验结果表明:两幅原始红外交通图像的信息熵分别为4.71、5.07,经过新算法处理后信息熵分别增加到6.45、5.92;两幅原始红外交通图像的灰度标准差分别为6.90、19.14,经过新算法处理后灰度标准差分别增加到31.17、32.35;新算法的信息熵计算值大于他他算法的计算值。可见,新算法的增强效果优于其他常见的红外图像增强算法,它能显著改善红外交通图像的视觉效果,为图像的后续处理与分析奠定良好的基础。

关键词：图像处理红外交通图像图像去雾图像增强暗原色优先 Gamma校正

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：