检索结果-内蒙古大学图书馆

Rough Surface Wear Analysis Using image processing Techniques

IFAC-PapersOnLine 2016年第31期49卷 7-12页

作者： Takimoto, Rogério Yugo de Sales Guerra Tsuzuki, Marcos Ueda, Edson Kenji Sato, André Kubagawa de Castro Martins, Thiago Cousseau, Tiago Tanaka, Deniol Sinatora, Amilton Escola Politécnica da Universidade de São Paulo Mechatronics and Mechanical Systems Engineering Department Computational Geometry Laboratory São Paulo Brazil Escola Politécnica da Universidade de São Paulo Mechatronics and Mechanical Systems Engineering Department Surface Phenomema Laboratory São Paulo Brazil United States

Due to the great interest of the automotive industry to quickly and systematically evaluate low wear quantities a new approach based on image processing is presented. By comparing the captured rough surface point cloud using optical interferometry before and after wear, the proposed algorithm was able to estimate the amount of volume wear and mass loss. The proposed algorithm has two main steps. In the first step, the 3D point clouds obtained before and after wear are mapped to 2D images, and conventional edge detection algorithms are applied. Keypoints are determined using the SIFT algorithm on both images (before and after the wear), followed by the use of the RANSAC algorithm to create a good 2D registration between both 2D images. In the second step an enhanced ICP algorithm is used to perform a 3D registration. The main advantage of this method is the visualization of the wear geometry provided by the wear topography. The proposed algorithm was tested and the results are presented. © 2016

关键词： Edge detection Automotive industry image processing image registration Optical data processing Surface measurement 3D registration Edge detection algorithms image processing technique Optical interferometry Point cloud registration RANSAC algorithm SIFT SIFT algorithms

来源：评论

学校读者我要写书评

暂无评论

An analysis of Chosen image Formation algorithms for Synthetic Aperture Radar with FMCW

引用

INTERNATIONAL JOURNAL OF ELECTRONICS AND TELECOMMUNICATIONS 2016年第4期62卷 323-328页

作者： Okon-Fafara, Marta Serafin, Piotr Kawalec, Adam Mil Univ Technol Inst Radioelect Fac Elect Warsaw Poland

The modelling of FMCW SAR systems, due to long signal duration time, commonly used start-stop approximation for pulsed radars causes errors in the image. Continuous motion of the radar platform results in additional range-azimuth couplings and range walk term that should be considered in processing of signal from this type of radar. The paper presents an analysis of the following algorithms: Time Domain Correlation (TDC), Range Doppler Algorithm (RDA), and Range Migration Algorithm (RMA). The comparison of the algorithms is based on theoretical estimation of their computation complexity and the quality of images obtained on the basis of real signals of FMCW SAR systems.

关键词： signal processing synthetic aperture radar Time Domain Correlation Range Doppler Algorithm Range Migration Algorithm

来源：评论

学校读者我要写书评

暂无评论

Computational Models of Face Perception

引用

CURRENT DIRECTIONS IN PSYCHOLOGICAL SCIENCE 2017年第3期26卷 263-269页

作者： Martinez, Aleix M. Ohio State Univ Dept Elect & Comp Engn Ctr Cognit & Brain Sci Columbus OH 43210 USA Ohio State Univ Math Biosci Inst Columbus OH 43210 USA

Faces are one of the most important means of communication for humans. For example, a short glance at a person's face provides information about his or her identity and emotional state. What are the computations the brain uses to acquire this information so accurately and seemingly effortlessly? This article summarizes current research on computational modeling, a technique used to answer this question. Specifically, my research tests the hypothesis that this algorithm is tasked with solving the inverse problem of production. For example, to recognize identity, our brain needs to identify shape and shading features that are invariant to facial expression, pose, and illumination. Similarly, to recognize emotion, the brain needs to identify shape and shading features that are invariant to identity, pose, and illumination. If one defines the physics equations that render an image under different identities, expressions, poses, and illuminations, then gaining invariance to these factors can be readily resolved by computing the inverse of this rendering function. I describe our current understanding of the algorithms used by our brains to resolve this inverse problem. I also discuss how these results are driving research in computer vision to design computer systems that are as accurate, robust, and efficient as humans.

关键词： face recognition face processing affect categorization language evolution

来源：评论

学校读者我要写书评

暂无评论

Robust pose recognition using deep learning

Robust pose recognition using deep learning

引用

International Conference on Computer Vision and image processing, CVIP 2016

作者： Mohanty, Aparna Ahmed, Alfaz Goswami, Trishita Das, Arpita Vaishnavi, Pratik Sahay, Rajiv Ranjan Department of Electrical Engineering Indian Institute of Technology Kharagpur Kharagpur India Department of Computer Science and Technology Indian Institute of Engineering Science and Technology Shibpur Kolkata India Sardar Vallabhai National Institute of Technology Surat Surat India

ISBN: (纸本)9789811021060

Current pose estimation methods make unrealistic assumptions regarding the body postures. Here, we seek to propose a general scheme which does not make assumptions regarding the relative position of body parts. Practitioners of Indian classical dances such as Bharatnatyam often enact several dramatic postures called Karanas. However, several challenges such as long flowing dresses of dancers, occlusions, change of camera viewpoint, poor lighting etc. affect the performance of state of- the-art pose estimation algorithms [1, 2] adversely. Body postures enacted by practitioners performing Yoga also violate the assumptions used in current techniques for estimating pose. In this work, we adopt an image recognition approach to tackle this problem. We propose a dataset consisting of 864 images of 12 Karanas captured under controlled laboratory conditions and 1260 real-world images of 14 Karanas obtained from Youtube videos for Bharatnatyam. We also created a new dataset consisting of 400 real-world images of 8 Yoga postures. We use two deep learning methodologies, namely, convolutional neural network (CNN) and stacked auto encoder (SAE) and demonstrate that both these techniques achieve high recognition rates on the proposed datasets. © Springer Science+Business Media Singapore 2017.

关键词： image recognition

来源：评论

学校读者我要写书评

暂无评论

Dataflow object detection system for FPGA-based smart camera

引用

IET CIRCUITS DEVICES & systems 2016年第4期10卷 280-291页

作者： Bourrasset, Cedric Maggiani, Luca Serot, Jocelyn Berry, Francois Univ Blaise Pascal Inst Pascal Clermont Ferrand France Scuola Super Sant Anna TeCIP Inst Pisa Italy

Embedded computer vision based smart systems raise challenging issues in many research fields, including real-time vision processing, communication protocols or distributed algorithms. The amount of data generated by cameras using high resolution image sensors requires powerful computing systems to be processed at digital video frame rates. Consequently, the design of efficient and flexible smart cameras, with on-board processing capabilities, has become a key issue for the expansion of smart vision systems relying on decentralised processing at the image sensor node level. In this context, field programmable gate arrays (FPGA)-based platforms, supporting massive data parallelism, offer large opportunities to match real-time processing constraints compared with platforms based on general purpose processors. In this study, the authors describe the implementation, on such a platform, of a configurable object detection application, reformulated according to the dataflow model of computation. The application relies on the computation of the histogram of oriented gradients and a linear SVM-based classification. It is described using the CAPH programming language, allowing efficient hardware descriptions to be generated automatically from high level dataflow specifications without prior knowledge of hardware description languages such as VHDL or Verilog. Results show that the performance of the generated code does not suffer from a significant overhead compared with handwritten HDL code.

关键词： object detection field programmable gate arrays cameras computer vision image sensors real-time systems support vector machines programming languages data flow analysis FPGA-based smart camera field programmable gate arrays dataflow object detection system embedded computer vision real-time vision processing communication protocols distributed algorithms high resolution image sensors digital video frame rates flexible smart cameras on-board processing smart vision systems massive data parallelism real-time processing constraints configurable object detection oriented gradients linear SVM-based classification CAPH programming language hardware descriptions high level dataflow specifications generated code

来源：评论

学校读者我要写书评

暂无评论

Optimization of interval type-2 fuzzy systems for image edge detection

引用

APPLIED SOFT COMPUTING 2016年第0期47卷 631-643页

作者： Gonzalez, Claudia I. Melin, Patricia Castro, Juan R. Castillo, Oscar Mendoza, Olivia Univ Autonoma Baja California Tijuana Mexico Tijuana Inst Technol Tijuana Mexico

This paper presents the optimization of a fuzzy edge detector based on the traditional Sobel technique combined with interval type-2 fuzzy logic. The goal of using interval type-2 fuzzy logic in edge detection methods is to provide them with the ability to handle uncertainty in processing real world images. However, the optimal design of fuzzy systems is a difficult task and for this reason the use of meta heuristic optimization techniques is also considered in this paper. For the optimization of the fuzzy inference systems, the Cuckoo Search (CS) and Genetic algorithms (GAs) are applied. Simulation results show that using an optimal interval type-2 fuzzy system in conjunction with the Sobel technique provides a powerful edge detection method that outperforms its type-1 counterparts and the pure original Sobel technique. (C) 2014 Elsevier B.V. All rights reserved.

关键词： Interval type-2 fuzzy logic Edge detection image processing Cuckoo Search algorithms

来源：评论

学校读者我要写书评

暂无评论

Flexible image processing in Embedded systems using Multi-agents systems

Flexible image processing in Embedded Systems using Multi-ag...

引用

14th IFAC Conference on Programmable Devices and Embedded systems (PDES)

作者： Inguere, Tifaine Carlier, Florent Renault, Valerie Univ Maine CREN Le Mans France STMicroelectronics Le Mans France

Efficient image processing can lead to complex algorithms. In resources are limited and the approach of linear algorithm does not allow to decrease complexity regarding the variations of these resources availability. Agents are autonomous entities brought together into systems. They interact between them and with their environment to perform tasks. interactions allow them to share knowledge and capacities in order to adapt themselves to a changing context. In this paper we propose to use Multi-agents systems algorithms to perform flexible image processing in an Embedded context. We will introduce our hardware context and the architecture choices made to adapt Multi -agents systems to the Embedded field. We will then present an experiment focusing on pixel interpolation process to study the flexibility of our solution. (C) 2016, IFAC (International Fedaration of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.

关键词： Embedded systems Resource allocation Management systems Multi-agents systems image processing

来源：评论

学校读者我要写书评

暂无评论

Soft Computing Applications: Proceedings of the 7th International Workshop Soft Computing Applications (SOFA 2016), Volume 2

引用

2017年

作者： Valentina Emilia Balas Lakhmi C Jain Marius Mircea Balas

ISBN: (纸本)9783319625232

These two volumes constitute the Proceedings of the 7th International Workshop on Soft Computing Applications (SOFA 2016), held on 2426 August 2016 in Arad, Romania. This edition was organized by Aurel Vlaicu University of Arad, Romania, University of Belgrade, Serbia, in conjunction with the Institute of Computer Science, Iasi Branch of the Romanian Academy, IEEE Romanian Section, Romanian Society of Control Engineering and Technical Informatics (SRAIT) - Arad Section, General Association of Engineers in Romania - Arad Section, and BTM Resources Arad. The soft computing concept was introduced by Lotfi Zadeh in 1991 and serves to highlight the emergence of computing methodologies in which the accent is on exploiting the tolerance for imprecision and uncertainty to achieve tractability, robustness and lower costs. Soft computing facilitates the combined use of fuzzy logic, neurocomputing, evolutionary computing and probabilistic computing, leading to the concept of hybrid intelligent systems. The rapid emergence of new tools and applications calls for a synergy of scientific and technological disciplines in order to reveal the great potential of soft computing in all domains. The conference papers included in these proceedings, published post-conference, were grouped into the following areas of research: Methods and Applications in Electrical Engineering Knowledge-Based Technologies for Web Applications, Cloud Computing, Security algorithms and Computer Networks Biomedical Applications image, Text and Signal processing Machine Learning and Applications Business Process Management Fuzzy Applications, Theory and Fuzzy Control Computational Intelligence in Education Soft Computing & Fuzzy Logic in Biometrics (SCFLB) Soft Computing algorithms Applied in Economy, Industry and Communication Technology Modelling and Applications in Textiles The book helps to disseminate advances in selected active research directions in the field of soft computing, along with current issues

关键词：

来源：评论

学校读者我要写书评

暂无评论

International Conference on Advances in Information and Communication Technology, ICTA 2016

International Conference on Advances in Information and Comm...

引用

Proceedings of the International Conference on Advances in Information and Communication Technology, ICTA 2016

ISBN: (纸本)9783319490724

The proceedings contain 69 papers. The special focus in this conference is on Advances in Information and Communication Technology. The topics include: Multimodal based clouds computing systems for healthcare and risk forecasting based on subjective analysis;telematics and advanced transportation services;toward affective speech-to-speech translation;a computer vision based machine for walnuts sorting using robot operating system;a fpga based two level optimized local filter designfor high speed image processing applications;a frequency dependent investigation of complex shear modulus estimation;a method to enhance the remote sensing images based on the local approach using kmeans algorithm;a method for clustering and identifying http automated software communication;a new neuro-fuzzy inference system for insurance forecasting;a new schema to identify s-farnesyl cysteine prenylation sites with substrate motifs;a novel framework based on deep learning and unmanned aerial vehicles to assess the quality of rice fields;a semi-supervised learning method for hybrid filtering;a study on fitness representation in genetic programming;an evaluation of hand pyramid structure for hand representation based on kernels;an exploratory study on students’ performance classification using hybrid of decision tree and naïve bayes approaches;an iterative method to solve boundary value problems with irregular boundary conditions;classifying human body postures by a support vector machine with two simple features;comparing modified pso algorithms for mrs in unknown environment exploration and estimation localization in wireless sensor network based on multi-objective grey wolf optimizer.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Edge-directional interpolation algorithm using structure tensor 14

Edge-directional interpolation algorithm using structure ten...

引用

image processing: algorithms and systems xiv 2016

作者： Nasonov, Andrey V. Krylov, Andrey S. Petrova, Xenya Yu. Rychagov, Michael N. Lomonosov Moscow State University Faculty of Computational Mathematics and Cybernetics Laboratory of Mathematical Methods of Image Processing Russia Samsung R and D Institute Russia Algorithm Lab. 12 Dvintsev str. Moscow127018 Russia

The paper presents a new low complexity edge-directed image interpolation algorithm. The algorithm uses structure tensor analysis to distinguish edges from textured areas and to find local structure direction vectors. The vectors are quantized into 6 directions. Individual adaptive interpolation kernels are used for each direction. Experimental results show high performance of the proposed method without introducing artifacts. © 2016 Society for Imaging Science and Technology.

关键词： Interpolation

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：