检索结果-内蒙古大学图书馆

8th ieee symposium Series on computational intelligence (ieee SSCI)

作者： Reid, Shane Coleman, Sonya Kerr, Dermot Vance, Philip O'Neill, Siobhan Ulster Univ Magee Coll Sch Comp Engn & Intelligent Syst Coleraine Londonderry North Ireland Ulster Univ Magee Coll Sch Psychol Coleraine Londonderry North Ireland

ISBN: (纸本)9781538692769

Measuring social signals has often proved challenging as they are often characterized by subtle movements which are difficult to detect. Head pose is one such social signal used to indicate where an individual's attention is focused. This paper will discuss the problem of head pose estimation by defining the problem in terms of two fields of view, pan and tilt. A novel approach for head pose estimation is described that uses histogram of oriented gradients with support vector machines. The approach is compared with a template matching approach, among others, using a well-known dataset. The results show that the histogram of oriented gradients approach is able to determine head pan to within one class approximately 72% of the time, and head tilt to within one class approximately 71% of the time.

关键词： Head Pose estimation Template matching Social signal processing Histogram of oriented gradients Support vector machine

来源：评论

学校读者我要写书评

暂无评论

X Ray image Enhancement Technology for Steel Pipe Welding Based on Hopfield Neural Network

X Ray Image Enhancement Technology for Steel Pipe Welding Ba...

引用

2nd International symposium on computational intelligence and Design

作者： Gao Weixin Sun Lianmin Mu Xiangyang Tang Nan Wu Xiaomeng Xian Shiyou Univ Sch Elect Engn Xian Peoples R China Univ Kitakyushu Dept Informat & Media Engn Kitakyushu Fukuoka Japan

ISBN: (纸本)9780769538655

Hopfield neural network is utilized to enhance x-ray image of thick steel pipe welding, and a gray mapping matrix is constructed to replace traditional gray transformation curves and functions in this paper. The maximum dimension of the gray mapping matrix is 256(X)256, so the calculation time has little relation with the size of the image. The criterion function of image quality is used to evaluate the quality of the transformed image. In proposed approach, the problem of image enhancement is transformed to an optimization problem, so the normalization of gray values for each pixel is not necessary. The energy function that improves the performance of image enhancement is also given for Hopfield neural network.

关键词： Hopfield Neural Network image processing image Hencing

来源：评论

学校读者我要写书评

暂无评论

CO-OCCURRENCE ANALYSIS OF SPEECH WAVEFORMS

引用

ieee TRANSACTIONS ON ACOUSTICS SPEECH AND signal processing 1985年第1期33卷 5-30页

作者： TERZOPOULOS, D Artificial Intelligence Laboratory Massachusetts Institute of Technology Cambridge MA USA

The co-occurrence matrix, a two-dimensional histogram of pairs of sample amplitudes, is explored as a representation of the digital speech waveform. Co-occurrence matrix representations support a hypothesis-testing approach to digital speech analysis. This approach is pursued in the formulation of a quantitative (chi-square) measure of sample amplitude dependence, based on co-occurrence matrices. This measure, which is higly sensitive to quasi-periodicity, is shown to lead to a good estimator of the pitch period of voiced speech. Co-occurrence matrix representations are employed in conjunction with pattern classification methods in experiments involving the voiced-unvoiced-silence analysis of speech, and in an experimental pitch extraction algorithm which is tested on continuous speech.

关键词： Speech analysis Histograms Testing Pattern analysis Algorithm design and analysis Speech recognition computational efficiency Digital images image analysis image texture analysis

来源：评论

学校读者我要写书评

暂无评论

Automatic Mask Detecion using Convolutional Neural Networks and Variational Autoencoder 15

Automatic Mask Detecion using Convolutional Neural Networks ...

引用

ieee 15th International symposium on Applied computational intelligence and Informatics (SACI)

作者： Silabela, Mxolisi Bogdandy, Bence Toth, Zsolt Eszterhazy Karoly Univ Fac Informat Eger Hungary

ISBN: (纸本)9781728195438

The importance of proper hygienical behaivour is essential in today's word especially during an ongoing pandemic. Wearing mask became mandatory in many countries during the COVID-19 Pandemic. Recognizing whether people are wearing masks is complicated image recognition task which could be facilitated and automated with machine learning techniques. Camera streams are widely available in indoor environments which can be used for object detection and image processing. Convolutional Neural Networks have been successfully applied in image classification and object recognition task in various application areas. There are already trained and openly available general purpose convolutional neural networks which can be used as an initial version for specific applications. A number of different image datasets are also available for research and industrial purposes. The InceptionV3 Neural Network architecture was used to tailored to determine whether a mask is being worn or not using transfer learning techniques, and convolutional neural networks. A variational autoencoder has also been trained to normalize the dataset with respect to skin colour, angle of the head and among other parameters. This paper describes the implementation of a mask recognition software using transfer learning, a convolutional neural network and a variational autoencoder.

关键词： Machine Learning Feedforward neural networks Variational Autoencoder image Recognition Deep learning

来源：评论

学校读者我要写书评

暂无评论

Curvelet Transform Based Super-Resolution image processing

Curvelet Transform Based Super-Resolution Image Processing

引用

12th ieee International symposium on signal processing and Information Technology (ISSPIT)

作者： Thuong Le-Tien Luc Nguyen-Tan Giang Le-Thach Cao Bui-Thu Hochiminh City Univ Technol Dept Elect & Elect Engn 268 Ly Thuong KietDist 10 Ho Chi Minh City Vietnam Ind Univ Dept Elect Technol Ho Chi Minh City Vietnam

ISBN: (纸本)9781467356046

Super-Resolution (SR) processing is a technique that produces a High - Resolution (HR) image from a range of Low - Resolution (LR) images. There are many methods for implementing the SR signal processing. In this paper, we introduce a specific transformation that were developed in the recent years called Curvelet Transform (CT), and then apply it in SR processing to obtain a quality improvement of SR images. We discuss two separate algorithms using the Discrete Curvelet Transform (DCT) and then compare them based on the results of HR images. We find out that the first algorithm, named the iterative algorithm can produce better HR images than the second one, the Interpolation algorithm. However, the iterative algorithm also take more computational cost than that of the Interpolation Algorithm. It is a reasonable trade-off between images quality and processing speed. We also made a comparison between our algorithms and previous works such as the Projection onto Convex Sets (POCS) and the Nearest Neighbourhood algorithms to show the quality improvement.

关键词： Curvelet Transform Superresolution image processing Iterative Algorithm Interpolation Algorithm POCS algorithm Nearest Neighbourhood Algorithm

来源：评论

学校读者我要写书评

暂无评论

Performance of Overloaded MIMO-OFDM System with Repetition Code

Performance of Overloaded MIMO-OFDM System with Repetition C...

引用

International symposium on Intelligent signal processing and Communication Systems (ISPACS)

作者： Matsuoka, Hikari Doi, Yoshihito Yabe, Tatsuro Sanada, Yukitoshi Keio Univ Dept Elect & Elect Engn Yokohama Kanagawa Japan

ISBN: (纸本)9781479961207

This paper investigates the performance of an overloaded multiple-input multiple-output (MIMO) orthogonal frequency division multiplexing (OFDM) system with a repetition code. It has been demonstrated that diversity with block coding prevents the performance degradation induced by signal multiplexing. However, the computational complexity of a joint decoding scheme increases exponentially with the number of multiplexed signal streams. Thus, this paper proposes the use of a repetition code in the overloaded MIMO-OFDM system. In addition, QR decomposition with M-algorithm (QRM) maximum likelihood decoding (MLD) is applied to the decoding of the repetition code. QRM-MLD significantly reduces the amount of joint decoding complexity. In addition, virtual antennas are employed in order to increase the throughput that is reduced by the repetition code. It is shown that the proposed scheme reduces the complexity by about 1/48 for 6 signal streams with QPSK modulation while the BER degradation is less than 0.1dB at the BER of 10(-3).

关键词： MIMO communication OFDM modulation error statistics maximum likelihood decoding BER degradation QR decomposition with M-algorithm QRM maximum likelihood decoding block coding computational complexity joint decoding scheme multiple-input multiple-output multiplexed signal streams orthogonal frequency division multiplexing overloaded MIMO-OFDM system repetition code signal multiplexing virtual antennas computational modeling Decoding Encoding Joints Multiplexing Throughput Transmitting antennas repetition coding Orthogonal frequency division multiplexing Block codes multiple input multiple output systems maximum likelihood decoding MULTIPLEXOR DECODING transmitting antennas MIMO communication Throughput decoding scheme computational modeling Joints Joints complexity classes

来源：评论

学校读者我要写书评

暂无评论

Interactive Evolutionary Parameter Optimization for Eulerian Video Magnification 8

Interactive Evolutionary Parameter Optimization for Eulerian...

引用

8th ieee symposium Series on computational intelligence (ieee SSCI)

作者： Rizvi, Syed Raazi Rahnamayan, Shahryar UOIT Dept Elect Comp & Software Engn Nat Inspired Computat Intelligence NICI Lab Oshawa ON Canada

ISBN: (纸本)9781538692769

This paper explores control parameter tuning for the Eulerian Video Magnification (EVM) process using a pair comparison-based interactive differential evolution (PCB-IDE) algorithm. Interactive evolutionary optimizers have a history of being applied to video/image post-processing tasks because assessing the quality of video data is objectively difficult without subjective assessment by users. The EVM technique magnifies motion and color variations within a video in a manner similar to a visual microscope. Applying EVM to video sequences allows the observation of known physical phenomenon by using only video data, which is critical to development of camera based monitoring applications. The proposed PCB IDE assists experts in determining the optimal parameters for EVM process to better identify visual changes and correlate them to physical phenomenons.

关键词： Eulerian Video Magnification Parameter Estimation Video Post-processing Interactive Differential Evolution

来源：评论

学校读者我要写书评

暂无评论

Composite techniques for quality analysis in automotive laser welding

Composite techniques for quality analysis in automotive lase...

引用

ieee International symposium on computational intelligence for Measurement Systems and Applications

作者： Alippi, C D'Angelo, G Matteucci, M Pasquettaz, G Piuri, V Scotti, F Politecn Milan Dept Elect & Informat I-20133 Milan Italy

ISBN: (纸本)0780377834

Real-time monitoring of the laser-based applications is becoming a main issue for quality analysis in the steel manufacturing industry. The paper suggests a solution achieving an automated real-time quality inspection in laser welding applications. A composite system composed of soft-computing and traditional techniques has been considered for its positive impact on the reduced computational once compared with more traditional approaches.

关键词： Automotive engineering Chromium Gears Information technology Inspection Laser tuning Power lasers Ring lasers signal processing algorithms Welding

来源：评论

学校读者我要写书评

暂无评论

Identification of functional states of the cardiovascular system according to flowmetry data using machine learning methods 11

Identification of functional states of the cardiovascular sy...

引用

11th International symposium on computational intelligence and Design (ISCID)

作者： Sergeevna, Konnova Natalia Alekseevich, Basarab Mikhail Bauman Moscow State Tech Univ Informat Secur Dept Moscow Russia Bauman Moscow State Tech Univ Theoret Informat & Comp Technol Moscow Russia

ISBN: (纸本)9781538685273

The aim of this work is to analyze the applicability of machine learning methods to the problems of diagnosing on the cardiovascular system data and develop a novel technique for automating this process to support decision making in cardiology. Here, the results obtained with the help of classifiers based on random decision forests are examined, and a proprietary numerical experiment is performed with the Doppler flowmetry data. Considerable attention is paid to data processing and reduction of the input vector dimension for analysis.

关键词： machine learning random forest diagnostics of the cardiovascular system state decision support system digital signal processing Doppler flowmetry

来源：评论

学校读者我要写书评

暂无评论

Design of the Autocollimator Tracking System based on TMS320DM642 and TMS320F2812

Design of the Autocollimator Tracking System based on TMS320...

引用

ieee 5th International Conference on Advanced computational intelligence (ICACI)

作者： Guo, Hongxiang Hu, Xiaodong Chinese Acad Sci Xian Inst Opt & Precis Mech Xian Hitech Ind 17Xinxi RdNew Ind Pk Xian Shaanxi Peoples R China Chinese Acad Sci Xian Inst Opt & Precis Mech Xian Shaanxi Peoples R China

ISBN: (纸本)9781467317443

This paper introduces the composition of the autocollimator tracking system, and analyses in detail the image processing part and servo tracking part of the system. The image processing part uses TMS320DM642 DSP to complete the image acquisition and image display. Using RS232 serial ports to transmit each frame offset of target to the servo tracking part. According to the offset information, the servo tracking part makes use of TMS320F2812 DSP to complete real-time tracking. Autocollimator tracking system uses two rhombic prisms to ensure real-time transmission of optical path. Experiments show that the autocollimator tracking system can achieve 1HZ real-time tracking and fully meets the project needs.

关键词： aerospace components aerospace computing angular measurement digital signal processing chips image processing equipment object tracking peripheral interfaces rockets

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：