检索结果-内蒙古大学图书馆

A Parallel Nonlocal Means Algorithm for Remote Sensing image Denoising on an Intel Xeon Phi Platform

IEEE ACCESS 2017年 5卷 8559-8567页

作者： Huang, Fang Lan, Bo Tao, Jian Chen, Yinjie Tan, Xicheng Feng, Jie Ma, Yan Univ Elect Sci & Technol China Sch Resources & Environm Chengdu 611731 Peoples R China Univ Elect Sci & Technol China Big Data Res Ctr Inst Remote Sensing Big Data Chengdu 611731 Peoples R China Texas A&M Univ Texas A&M Engn Expt Stn College Stn TX 77843 USA Xihua Univ Sch Construct & Management Engn Chengdu 610039 Peoples R China Wuhan Univ Int Sch Software Wuhan 430079 Peoples R China Chinese Acad Sci Inst Remote Sensing & Digital Earth Beijing 100094 Peoples R China

The nonlocal means (NLM) algorithm is one of the best image denoising algorithms because of its superior capability to retain the texture details of an image and is widely used in remote sensing (RS) image preprocessing. However, the time complexity of the algorithm is very high due to its nonlocality when searching for similar pixels. As a result, the NLM algorithm cannot satisfy the near real-time requirements of some specfic applications. To resolve this issue, a parallel NLM algorithm based on Intel Xeon Phi hardware with Intel's many integrated cores (MIC) architecture was designed and implemented in this paper. The parallel algorithm achieved satisfactory speedup, but the speedup obtained showed a step-like distribution for different image sizes. This result was not expected based on the theoretical analysis, which predicted that the speedup should be independent of input data set size. To address this problem, the parallel algorithm was further optimized by adding pretreatment approaches and cutting down the number of nested loops in the MIC. Finally, experiments using the standard and optimized versions were carried out using the RS images of different sizes. Several conclusions could be drawn from the experimental results: 1) the standard parallel algorithm can obtain better speedup with only one MIC card and 2) the optimized parallel algorithm can completely eliminate the step distribution of the speedup and can also accelerate RS image processing significantly.

关键词： Parallel computing MIC remote sensing image processing OpenMP

来源：评论

学校读者我要写书评

暂无评论

Detecting dings and dents on specular car body surfaces based on optical flow

引用

JOURNAL OF MANUFACTURING systems 2017年 45卷 306-321页

作者： Arnal, Laura Solanes, J. Ernesto Molina, Jaime Tornero, Josep Univ Politecn Valencia Inst Design & Mfg Cami Vera S-N E-46022 Valencia Spain

This paper introduces a new approach to detect defects cataloged as dings and dents on car body surfaces, which is currently one of the most important issues facing quality control in the automotive industry. Using well-known optical flow algorithms and the deflectometry principle, the method proposed in this work is able to detect all kind of anomalies on specular surfaces. Hence, our method consists of two main steps: first, in the pre-processing step, light patterns projected on the body surface sweep uniformly the area of inspection, whilst a new image fusion law, based on optical flow, is used to obtain a resulting fused image holding the information of all variations suffered by the projected patterns during the sweeping process, indicating the presence of anomalies;second, a new post-processing step is proposed that avoids the need of using pre-computed reference backgrounds in order to differentiate defects from other body features such as style-lines. To that end, the image background of the resulting fused image is estimated in the first place through a method based on blurring the image according to the direction of each pixel. Afterwards, the estimated image background is used in a new subtraction law through which defects are well differentiated from other surface deformations, allowing the detection of defects in the entire illuminated area. In addition, since our approach, together with the system used, computes defects in less than 15 s, it satisfies the assembly plants time requirements. Experimental results presented in this paper are obtained from the industrial automatic quality control system QEyeTunnel employed in the production line at the Mercedes-Benz factory in Vitoria, Spain. A complete analysis of the algorithm performance will be shown here, together with several tests proving the robustness and reliability of our proposal. (c) 2017 The Society of Manufacturing Engineers. Published by Elsevier Ltd. All rights reserved.

关键词： Deflectometry Optical flow image fusion Specular surfaces Painted surfaces Car body inspection

来源：评论

学校读者我要写书评

暂无评论

image Vignetting Reduction via a Maximization of Fuzzy Entropy

Image Vignetting Reduction via a Maximization of Fuzzy Entro...

引用

IEEE International Conference on Fuzzy systems (FUZZ-IEEE)

作者： Lopez-Fuentes, Laura Massanet, Sebastia Gonzalez-Hidalgo, Manuel Univ Balear Islands UIB Dept Math & Comp Sci SCOPIA Res Grp E-07122 Palma De Mallorca Spain AnsuR Technol Martin Linges Vei 25 N-1364 Fornebu Norway Autonomous Univ Barcelona UAB CVC Campus UAB Barcelona 08193 Spain

ISBN: (纸本)9781509060344

In many computer vision applications, vignetting is an undesirable effect which must be removed in a pre-processing step. Recently, an algorithm for image vignetting correction has been presented by means of a minimization of log-intensity entropy. This method relies on an increase of the entropy of the image when it is affected with vignetting. In this paper, we propose a novel algorithm to reduce image vignetting via a maximization of the fuzzy entropy of the image. Fuzzy entropy quantifies the fuzziness degree of a fuzzy set and its value is also modified by the presence of vignetting. The experimental results show that this novel algorithm outperforms in most cases the algorithm based on the minimization of log-intensity entropy both from the qualitative and the quantitative point of view.

关键词： Estimation Field programmable gate arrays OFDM Modulation Filtration Clocks Signal processing algorithms

来源：评论

学校读者我要写书评

暂无评论

Infrared image Enhancement Using Adaptive Histogram Partition and Brightness Correction

引用

REMOTE SENSING 2018年第5期10卷 682-682页

作者： Wan, Minjie Gu, Guohua Qian, Weixian Ren, Kan Chen, Qian Maldague, Xavier Nanjing Univ Sci & Technol Sch Elect & Opt Engn Nanjing 210094 Jiangsu Peoples R China Laval Univ Dept Elect & Comp Engn Comp Vis & Syst Lab 1065 Ave Med Quebec City PQ G1V 0A6 Canada Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China

Infrared image enhancement is a crucial pre-processing technique in intelligent urban surveillance systems for Smart City applications. Existing grayscale mapping-based algorithms always suffer from over-enhancement of the background, noise amplification, and brightness distortion. To cope with these problems, an infrared image enhancement method based on adaptive histogram partition and brightness correction is proposed. First, the grayscale histogram is adaptively segmented into several sub-histograms by a locally weighted scatter plot smoothing algorithm and local minima examination. Then, the fore-and background sub-histograms are distinguished according to a proposed metric called grayscale density. The foreground sub-histograms are equalized using a local contrast weighted distribution for the purpose of enhancing the local details, while the background sub-histograms maintain the corresponding proportions of the whole dynamic range in order to avoid over-enhancement. Meanwhile, a visual correction factor considering the property of human vision is designed to reduce the effect of noise during the procedure of grayscale re-mapping. Lastly, particle swarm optimization is used to correct the mean brightness of the output by virtue of a reference image. Both qualitative and quantitative evaluations implemented on real infrared images demonstrate the superiority of our method when compared with other conventional methods.

关键词： infrared image enhancement adaptive histogram partition local contrast weighted distribution brightness correction Smart City

来源：评论

学校读者我要写书评

暂无评论

Artifact Elimination in Neurosciences 2nd

引用

2nd International Conference on Advanced Intelligent systems and Informatics (AISI)

作者： Raduentz, Thea Tahoun, Mohamed A. A-Megeed, Mohammed Meffert, Beate Fed Inst Occupat Safety & Hlth Unit Mental Hlth & Cognit Capac 34 Noldnerstr 40-42 D-10317 Berlin Germany Suez Canal Univ Fac Comp & Informat Ismailia Egypt Ain Shams Univ Fac Comp & Informat Sci Cairo 1156 Egypt Humboldt Univ Dept Comp Sci Rudower Chaussee 25 D-12489 Berlin Germany

ISBN: (纸本)9783319483085;9783319483078

Artifact elimination is a central issue in neurosciences. A method that has established itself as an important part of EEG analysis is the application of independent component analysis (ICA). It decomposes the multi-channel EEG into linearly independent components (ICs) that then can be classified as artifact or EEG signal component. However, classification of the ICs still requires visual, time-intensive inspection by experts. In order to develop an automated artifact elimination method, we apply several classification algorithms on feature vectors extracted from ICA components via image processing algorithms. We compare their performance with the ratings of experts and identify range filtering as a feature extraction method with great potential. Range images classified with artificial neuronal networks yield accuracy rates of 95.5%. The results are very promising regarding automated IC artifact recognition. Compared to existing automated solutions the proposed method has the main advantage that it is not limited to a specific number or type of artifact. Furthermore, it is an automatic, real-time capable, and practical tool that reduces the time-intensive manual selection of ICs for artifact removal.

关键词： Electroencephalogram (EEG) Signal processing image processing Pattern recognition Classification

来源：评论

学校读者我要写书评

暂无评论

An Iterative Algorithm for image Inpainting Using Aggregation Functions 17

An Iterative Algorithm for Image Inpainting Using Aggregatio...

引用

Joint 17th World Congress of International-Fuzzy-systems-Association / 9th International Conference on Soft Computing and Intelligent systems (IFSA-SCIS)

作者： Gonzalez-Hidalgo, Manuel Massanet, Sebastia Mir, Amau Ruiz-Aguilera, Daniel Univ Balearic Isl SCOPIA Res Grp Dept Math & Comp Sci Cira ValldemossaKm 7-5 E-07122 Palma De Mallorca Balearic Island Spain

ISBN: (纸本)9781509049172

image inpainting is a prolific line of research due to its applications in restoration of missing or damaged areas of the image. In this paper, a novel iterative algorithm for image inpainting based on aggregation functions and penalty-based functions is presented. The algorithm combines diffusion-based and patch-based techniques. In each iteration of the algorithm, the level of consensus among the known pixels in a neighbourhood of each pixel is computed. If a minimum value of consensus is reached, the pixel is recovered by means of an aggregation of the known pixels of the neighbourhood through aggregation functions and penalty-based functions. Otherwise, a non-local search of similar patches is performed and then a similar aggregation but now of the centre pixels of those patches more similar to the region we must recover is carried out. Experiments on synthetic and natural images show the potential of this algorithm both from the qualitative and the quantitative points of view in comparison to other classical inpainting algorithms.

关键词： Estimation Field programmable gate arrays OFDM Modulation Filtration Clocks Signal processing algorithms

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Texture image Retrieval in Curvelet, Contourlet, and Local Ternary Pattern Using DNN and ELM Classifiers for MRI Brain Tumor images

引用

1st International Conference on Computer Vision and image processing (CVIP)

作者： Pandian, A. Anbarasa Balasubramanian, R. Manonmaniam Sundaranar Univ Dept Comp Sci & Engn Tirunelveli India

ISBN: (纸本)9789811021046;9789811021039

The problem of searching a digital image in a very huge database is called content-based image retrieval (CBIR). Texture represents spatial or statistical repetition in pixel intensity and orientation. When abnormal cells form within the brain is called brain tumor. In this paper, we have developed a texture feature extraction of MRI brain tumor image retrieval. There are two parts, namely feature extraction process and classification. First, the texture features are extracted using techniques like curvelet transform, contourlet transform, and Local Ternary Pattern (LTP). Second, the supervised learning algorithms like Deep Neural Network (DNN) and Extreme Learning Machine (ELM) are used to classify the brain tumor images. The experiment is performed on a collection of 1000 brain tumor images with different modalities and orientations. Experimental results reveal that contourlet transform technique provides better than curvelet transform and local ternary pattern.

关键词： CBIR Texture Brain tumor DNN and ELM

来源：评论

学校读者我要写书评

暂无评论

Utilizing High-Performance Embedded Computing, Agile Condor, for Intelligent processing An Artificial Intelligence Platform for Remotely Piloted Aircraft

Utilizing High-Performance Embedded Computing, Agile Condor,...

引用

Intelligent systems Conference (IntelliSys)

作者： Barnell, Mark Raymond, Courtney Isereau, Darrek Capraro, Christopher Cote, Eric AFRL Informat Directorate Griffiss AFB NY 13441 USA SRC Inc North Syracuse NY 13212 USA

ISBN: (纸本)9781509064359

A newly invented, high performance, pod-based computer architecture, called Agile Condor (patent pending), has been designed and developed. Agile Condor is supporting autonomous operations by providing a platform for the innovative use of artificial intelligence, machine learning, and decision making algorithms upstream, near the information source, where the data is collected. In September 2016, experimental tests successfully demonstrated the ability to implement advanced neural networks and deep learning techniques on Agile Condor. We continue to use this new processing architecture, algorithms and bio-inspired computing methods to demonstrate existing, refine emerging and invent new artificial intelligence techniques that are highly applicable and needed for sensor platforms. For the first time ever, and in real-time, the system demonstrated: image processing, video processing and pattern recognition through the use of deep convolutional neural networks. Because of Agile Condor's modular architecture and performance characteristics, the system is providing flexible computational resources that will continue to bring new artificial intelligence (AI) capabilities closer to sensor platforms.

关键词： Artificial intelligence platform machine learning platform autonomous operations high-performance embedded computing information processing big data massive analytics

来源：评论

学校读者我要写书评

暂无评论

Proceedings of International Conference on Cognition and Recognition: ICCR 2016

引用

2017年

作者： Devanur S Guru T Vasudev H K Chethan Y H Sharath Kumar

ISBN: (纸本)9789811051456

The book covers a comprehensive overview of the theory, methods, applications and tools of cognition and recognition. The book is a collection of best selected papers presented in the International Conferenceon Cognition and Recognition 2016 (ICCR 2016) and helpful for scientists and researchers in the field of image processing, pattern recognition and computer vision for advance studies. Nowadays, researchers are working in interdisciplinary areas and the proceedings of ICCR 2016 plays a major role to accumulate those significant works at one place. The chapters included in the proceedings inculcates both theoretical as well as practical aspects of different areas like nature inspired algorithms, fuzzy systems, data mining, signal processing, image processing, text processing, wireless sensor networks, network security and cellular automata.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Application of One-Class Classifier Based on CNN in image Defect Detection

The Application of One-Class Classifier Based on CNN in Imag...

引用

Complex Adaptive systems Conference on Engineering Cyber Physical systems (CAS)

作者： Zhang, Mei Wu, Jinglan Lin, Huifeng Yuan, Peng Song, Yanan South China Univ Technol Sch Automat Guangzhou 510640 Guangdong Peoples R China Guangdong Univ Technol Coll Automat Guangzhou 510006 Guangdong Peoples R China

In the field of defect detection, image processing algorithms and feature extraction algorithms have some limitations, owing to their necessity for extracting a large number of different features of diverse products images. Meanwhile, the images of defective products are less and various. Aiming at these problems, we presented a One-Class classifier based on deep convolution neural network to detect the defect images in this paper. We design a loss function with the penalty term based on Euclidean distance to train the deep convolution neural network model. A hypersphere is used as classification decision surface after setting an appropriate hypersphere radius according to the inspection accuracy. It maps the non-defective products into a hypersphere in a high dimensional feature space, while the defect images are mapped somewhere far from the center of hypersphere. Thus, a One-Class classifier based on convolutional neural network(CNN) model is proposed to detect the defects. Experiments show that the proposed method, with less number of iteration, help build the classifier for image defect detection with high generalization ability and high detection precision. (C) 2017 The Authors. Published by Elsevier B.V.

关键词： One-Class classifier CNN image defect detection Hypersphere

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：