检索结果-内蒙古大学图书馆

International IEEE conference on Intelligent Systems, IS

作者： Ramin Ramezani Plamen Angelov Xiaowei Zhou Intelligent Systems Research Laboratory Digital Signal Processing Research Group Department of Communication Systems Lancaster University Lancaster UK

Video-based surveillance and security become extremely important in the new, 21 st century for human safety, counter-terrorism, traffic control etc. Visual novelty detection and tracking are key elements of such activities. the current state-of-the-art approaches often suffer from high computational, memory storage costs and from not being fully automated (they usually require a human operator in the loop). this paper introduces a new approach to the problem of novelty detection in video streams that is based on recursive, and therefore, computationally efficient density estimation by a Cauchy type of kernel (as opposed to the usually used Gaussian one). the idea of the proposed approach stems from the recently introduced evolving clustering approach, eClustering and is suitable for online and real-time applications in fully autonomous and unsupervised systems as a stand-alone novelty detector or for priming a tracking algorithm. the approach proposed in this paper has evolving property - it can gradually update the background model and the criteria to detect novelty by unsupervised online learning. the proposed approach is faster by an order of magnitude than the well known kernel density estimation (KDE) method for background subtraction, while having has adaptive characteristics, and does not need any threshold to be pre-specified. Recursive expressions similar to the proposed approach in this paper can also be applied to image segmentation and landmark recognition used for self-localization in robotics. If combined with a real-time prediction using Kalman filter or evolving Takagi-Sugeno fuzzy models a fast and fully autonomous tracking system can be realized with potential applications in surveillance and robotic systems.

关键词： Streaming media Recursive estimation Surveillance Humans Kernel Real time systems Robots Security Safety Traffic control

来源：评论

学校读者我要写书评

暂无评论

Super-Resolution Generative Adversarial Network with Modified Architecture for Single image Super-Resolution

Super-Resolution Generative Adversarial Network with Modifie...

引用

International conference on Computer, Communication and signal processing (ICCCSP)

作者： N. Amruth Gowtham Shashikanth Deepakq Dipti Patra National Institute of Technology Rourkela India

ISBN: (数字)9781728165097

ISBN: (纸本)9781728165103

Recently, Single image Super-Resolution (SISR) has become an attractive research area in image processing which generates a High-Resolution (HR) image by using Single Low-Resolution (LR) image. Deep learningbased SISR approaches have achieved better Super-Resolved (SR) results by using mean squared error (MSE) as an objective function that increases the quality of SR results over performance metrics like peak-signal-to-noise-ratio (PSNR) and structural similarity index (SSIM). Nevertheless, MSE based approaches lead to generate over smoothed images with less high-frequency texture information at larger upscaling factors. Recent experiments have proved that Generative Adversarial Networks (GAN) generates perceptually convincing SR images through efficient extraction of high-frequency information from single LR image. In this paper, we propose a GAN based approach for SISR with modified deep-residual network architecture. In our proposed technique, we introduce the bottle-neck convolutional (CN) layer in the network structure of the Generator. Adding bottle-neck layers improves the network performance through 1 x 1 convolutional layers which extract complex features from the input and also reduces the computational complexity compared to 3 x 3 convolution layers. We further improve the model performance by removing batch normalization layer from the entire generator to overcome the unpleasant artifacts and improves GPU usage while training.

关键词： Generators Training Generative adversarial networks Feature extraction Superresolution Gallium nitride Convolution

来源：评论

学校读者我要写书评

暂无评论

Cellular automata based color image watermarking using NSCT and SVD

Cellular automata based color image watermarking using NSCT ...

引用

IEEE UP Section conference on Electrical Computer and Electronics (UPCON)

作者： Chandan Saha Md. Foisal Hossain Department of Electronics and Communication Engineering Khulna University of Engineering & Technology Khulna Bangladesh

ISBN: (纸本)9781538630051

Cellular automata based color image watermarking using non sub sampled contourlet transform (NSCT) and singular value decomposition (SVD) is presented in this paper. Game of life (GOL) cellular automata is used to scramble binary watermark so that no one can recover the watermark without secret scrambling keys. Because of the salient features like multiscale, multidirection and shift invariance of NSCT, 2-level NSCT is applied to red, green and blue component of RGB cover image. Most of the perceptual content of an image focuses on low frequency subband of NSCT and the singular values taken from low frequency subband have certain stability. So a modest change in the singular values taken from low frequency subband of NSCT is applicable. In this proposed scheme, each singular value of scrambled binary watermark is embedded in fixed location of singular value matrix of low frequency subbands of NSCT of red, green and blue components. the scheme offers security, imperceptibility and robustness against various image processing and geometric attacks like Gaussian white noise, salt and pepper noise, median filtering, JPEG compression, cropping and rotation. the proposed scheme is compared with existing watermarking schemes in terms of Peak signal to Noise ratio (PSNR), Normalized Correlation (NC)and provides satisfactory performance than other schemes.

关键词： Watermarking Automata Color Games Transforms Robustness Singular value decomposition

来源：评论

学校读者我要写书评

暂无评论

Face Makeup Transfer Algorithm Based on CycleGAN

Face Makeup Transfer Algorithm Based on CycleGAN

引用

signal processing, Communications and Engineering Management conference (ISPCEM), International

作者： Yunjin Gu Zihan Xu Dengyu Zhang International School Beijing University of Posts and Telecommunications Beijing China School of Information University of Sheffield Sheffield United Kingdom International School Zhejiang Gongshang University Hangzhou China

ISBN: (数字)9798331528676

ISBN: (纸本)9798331528683

Face makeup transfer is a popular research direction in the domain of computer vision, where makeup style is considered a special style of facial images, and makeup transfer is a part of style transfer. the process of human face makeup transfer is to transfer the makeup of the reference makeup image to the original makeup image while keeping the facial characteristics of the original makeup image. Currently, Generative Adversarial Networks (GANs) have become the mainstream technology for solving the problem of face makeup transfer. Face makeup transfer will be widely used in the future, such as in beauty cameras, makeup software for one-click makeup, virtual makeup trials for cosmetics, and video makeup transfer (such as live streaming software makeup and TV drama character makeup), and has received widespread attention in recent years. It has significant research value both in academia and industry. In this study, the paper adopted a series of innovative strategies to optimize model performance, including the introduction of non-local attention mechanisms to enhance feature extraction capabilities, improved residual blocks to increase network depth and efficiency, and attention modules in discriminators to improve focus on key features. Additionally, the paper used multi-scale discriminators to capture feature information at different levels and added skip connections to promote gradient flow and information integration, thereby achieving more efficient network training and better performance.

关键词： Training Industries TV signal processing algorithms Streaming media signal processing Feature extraction Software User experience Faces

来源：评论

学校读者我要写书评

暂无评论

Deformable Registration using Spring Mass System with Cross-section Correction

Deformable Registration using Spring Mass System with Cross-...

引用

4th International conference on Medical Information Visualisation (MediViz 2007)

作者： Jian-Kun Shen Bogdan J. Matuszewski Lik-Kwan Shark Christopher J. Moore Applied Digital Signal and Image Processing Research Centre University of Central Lancashire Preston UK Christie Hospital NHS Trust North Western Medical Physics Manchester UK

When applying 2D deformable registration to cross-sectional images from 3D data, it is assumed the images represent the same object. However, in reality, they are acquired at different axial positions and with different coronal and sagittal rotations. therefore, if the cross-section's position and orientation can be corrected, it should offer better registration accuracy. the paper describes a "2.5D" method for correcting position and orientation of the cross-section under the in-plane-2D deformable registration. For a given source image, the algorithm estimates the optimal position and orientation of the cross-section generating target image as well as displacement field of the source image. For in-plane 2D deformable registration, a previously proposed method is being used. It models the deformations using a spring mass system, which contains a number of sparse masses interconnected by springs. the external forces calculated from the image contents are used to iteratively guide the system to the "good" matching configuration under the constraints imposed by the internal forces. the performance of the method is tested using real Radiation therapy Planning CT (RTPCT) and Cone Beam CT (CBCT) as well as the simulated data. the results indicate that the newly proposed method improves registration accuracy.

关键词： Springs Computed tomography image registration Interpolation image processing Biomedical imaging image generation Biomedical applications of radiation Feature extraction Spline

来源：评论

学校读者我要写书评

暂无评论

Multiple scaling factors based Semi-Blind watermarking of grayscale images using OS-ELM neural network

Multiple scaling factors based Semi-Blind watermarking of gr...

引用

IEEE International conference on signal processing, Communications and Computing (ICSPCC)

作者： Ankit Rajpal Anurag Mishra Rajni Bala Department of Computer Science University of Delhi New Delhi India

ISBN: (纸本)9781509027095

In this paper, a multiple scaling factor based Semi-Blind watermarking scheme for grayscale image watermarking using Online Sequential Extreme Learning Machine (OS-ELM) is proposed. Four-level DWT is applied on three standard test images of size 512 × 512. LL4 sub-band coefficients are chosen for watermark embedding. OS-ELM is initially tuned with a fixed number of training data used in its initial phase and size of data block learned in each iteration. the training set is developed by combining the quantized and desired LL4 sub-band coefficients. this training set is fed to OS-ELM for training. the output of OS-ELM is a sequence of predicted coefficients which is sorted and divided into three equal parts. Multiple Scaling Factor (MSF) scheme is used for embedding a binary watermark in a Semi-Blind manner. Results show good visual quality of signed images and good similarity between the extracted and original watermarks from signed and attacked images. the PSNR and BER are found to be well optimized both in case of signed and attacked images. the time for embedding and extraction is in milliseconds, which makes the proposed technique effective for developing real time watermarking applications.

关键词： Watermarking Mathematical model Training data Training Gray-scale Visualization Discrete wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Intelligent Solid Waste Sorting System using IoT and image processing

Intelligent Solid Waste Sorting System using IoT and Image p...

引用

Innovation in Technology (ASIANCON), Asian conference on

作者： Remya Jayachandran Rupesh S Shaeen Kalathil Electronics and Communication Engineering The National Institute of Engineering Mysuru Karnataka India Biofuel Research Information and Demonstration Center (BRIDC) P.E.S College of Engineering Mandya Karnataka India Dept. of Electrical Engineering Princess Nourah Bint Abdulrahman University Riyadh Saudi Arabia

ISBN: (数字)9798350354218

ISBN: (纸本)9798350354225

Solid waste management (SWM) is one of the global challenges due to the lack of an efficient automated real-time waste segregation and reuse system. this work deals with the design, development and testing of an intelligent solid waste sorting system by integrating image processing and Internet of things (IoT). the proposed system utilizes image processing algorithm to detect the e-waste as well as e-waste with plastic content from other wastes. Additionally, the developed system is capable of sorting organic wastes, plastic wastes and metal wastes using respective sensors embedded in the system. the speed of the conveyor belt is synergistically tuned with the processing time of the algorithm for waste detection, signal communication, and response time of the flap, thereby attaining effective sorting. the detection accuracy above 95% is obtained for the present system which is better compared to the existing ones.

关键词： image sensors Accuracy Metals Electronic waste Sensor systems Capacitive sensors Sensors Time factors Internet of things Sorting

来源：评论

学校读者我要写书评

暂无评论

the 6th International conference on Computer Science and Computational Mathematics (ICCSCM 2017)

引用

Journal of Physics: conference Series 2017年第1期892卷

the ICCSCM 2017 (the 6th International conference on Computer Science and Computational Mathematics) has aimed to provide a platform to discuss computer science and mathematics related issues including Algebraic Geometry, Algebraic Topology, Approximation theory, Calculus of Variations, Category theory; Homological Algebra, Coding theory, Combinatorics, Control theory, Cryptology, Geometry, Difference and Functional Equations, Discrete Mathematics, Dynamical Systems and Ergodic theory, Field theory and Polynomials, Fluid Mechanics and Solid Mechanics, Fourier Analysis, Functional Analysis, Functions of a Complex Variable, Fuzzy Mathematics, Game theory, General Algebraic Systems, Graph theory, Group theory and Generalizations, image processing, signal processing and Tomography, Information Fusion, Integral Equations, Lattices, Algebraic Structures, Linear and Multilinear Algebra; Matrix theory, Mathematical Biology and Other Natural Sciences, Mathematical Economics and Financial Mathematics, Mathematical Physics, Measure theory and Integration, Neutrosophic Mathematics, Number theory, Numerical Analysis, Operations Research, Optimization, Operator theory, Ordinary and Partial Differential Equations, Potential theory, Real Functions, Rings and Algebras, Statistical Mechanics, Structure Of Matter, Topological Groups, wavelets and wavelet Transforms, 3G/4G Network Evolutions, Ad-Hoc, Mobile, Wireless Networks and Mobile Computing, Agent Computing & Multi-Agents Systems, All topics related image/signal processing, Any topics related Computer Networks, Any topics related ISO SC-27 and SC- 17 standards, Any topics related PKI(Public Key Intrastructures), Artifial Intelligences(A.I.) & Pattern/image Recognitions, Authentication/Authorization Issues, Biometric authentication and algorithms, CDMA/GSM Communication Protocols, Combinatorics, Graph theory, and Analysis of Algorithms, Cryptography and Foundation of Computer Security, Data Base(D.B.) Management & Information Retr

关键词：

来源：评论

学校读者我要写书评

暂无评论

Co-Cyclic Jacket Matrix Based Optimal Training Design and Placement for MIMO OFDM Channel Estimation

Co-Cyclic Jacket Matrix Based Optimal Training Design and Pl...

引用

IEEE International conference on Circuits and Systems for Communications (ICCSC)

作者： Chengyu Lin Wenjun Zhang Ying Guo Youyun Xu Shanghai Key Laboratory of Digital Media Processing and Transmissions Shanghai Jiaotong University Shanghai China Shanghai Jiao Tong University Shanghai CN School of Information Science and Engineering Central South University Changsha China

this paper deals with optimal training design and placement over multiple OFDM symbols for the least squares (LS) channel estimation in multiple-input multiple- output (MIMO) orthogonal frequency division multiplexing (OFDM) systems. When the number of transmit antennas increases, more pilot tones are required and the transmission efficiency decreases. To solve this problem, the pilot sequences are distributed over multiple OFDM symbols. Motivated by the properties of co-cyclic Jacket matrices, we derive the optimal pilot sequences from co-cyclic Jacket matrices based on the minimum mean square error (MSE) of the LS channel estimation. Simulation results show that the derived optimal pilot sequences over one, two and four OFDM symbols have the same performance, and greatly outperform the orthogonal pilot sequences in slowly time-varying channels.

关键词： MIMO OFDM Channel estimation Receiving antennas Transmitting antennas signal design Design engineering image communication Information processing Laboratories

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Survey On Transformer Fault Diagnosis and Operating Condition Prediction

A Comprehensive Survey On Transformer Fault Diagnosis and Op...

引用

IEEE conference on Energy Internet and Energy System Integration (EI2)

作者： Jian Wang Xihai Zhang Peiyi Li Xingyang Liu School of Electrical Engineering Southwest Jiaotong University Chengdu China College of Electrical Engineering Sichuan University Chengdu China

ISBN: (数字)9781728196060

ISBN: (纸本)9781728196077

Transformers are playing an increasingly significant role in electricity energy conversion, transmission, and distribution, which link energy resources such as conventional, renewable and sustainable energy, from generation to consumption. Reliable and precise diagnosis and prediction of operating conditions of power transformers have become continuously important. Until now, several methods for transformer fault diagnosis and operating condition prediction have been applied to various theoretical investigations and actual applications. this paper provides a comprehensive review of the existing works from two perspectives, namely, transformer fault diagnosis and operating condition prediction. the overview of transformer fault diagnosis consists of dissolved gas analysis, acoustic signal processing, and image recognition. On the other hand, the previous studies related to operating condition prediction of the transformer are critically examined and explored according to whether considering the association rules of state parameters. Finally, conclusions and future trends are presented.

关键词： image recognition Energy resources System integration Reliability theory Market research Internet Power transformers

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：