检索结果-内蒙古大学图书馆

A study on image processing with data analysis

AIP conference Proceedings 2022年第1期2393卷

作者： D. Chandra Prakash R. C. Narayanan N. Ganesh M. Ramachandran S. Chinnasami R. Rajeshwari 1Kgreddy College of Engineering and Technology India 2Department of Computer Science and Engineering Sona College of Technology Salem India 3Department of CSE vel tech multi tech dr. Rangarajan dr. Sakunthala Engineering College Chennai India 4REST Labs Kaveripattinam Krishnagiri India

image analysis is from images extracting meaningful information; mainly through digital image processing techniques from digital images. In this context, Tasks menu coded the tags are as simple as reading or a person from their face as sophisticated as identification. This paper presentation is made on various techniques used in analyzing images,like Computer view is from digital images or videos Dealing with how computers can gain a higher level of understanding Is an intermediate field of science, Machine vision (MV) is for applications such as automation Used to provide imaging based automation analysis and analysisTechnology and methods. Study, process control and robot guidance. Format authentication is the automatic recognition of methods and regulations in data. This includes statistical data analysis, signal processing, and Contains applications in image analysis. The dividing a digital several, the innovations are detailed in more detail in the text.

关键词：

来源：评论

学校读者我要写书评

暂无评论

IMPROVING ExTREME LOW-LIGHT image DENOISING VIA RESIDUAL LEARNING

IMPROVING EXTREME LOW-LIGHT IMAGE DENOISING VIA RESIDUAL LEA...

引用

IEEE International conference on Multimedia and Expo (ICME)

作者： Maharjan, Paras Li, Li Li, Zhu xu, Ning Ma, Chongyang Li, Yue Univ Missouri Kansas City MO 64110 USA Peng Cheng Lab Shenzhen Peoples R China Amazon Go Chicago IL USA Kwai Inc Seattle WA USA Univ Sci & Technol China Hefei Anhui Peoples R China

ISBN: (纸本)9781538695524

Taking a satisfactory picture in a low-light environment remains a challenging problem. Low-light imaging mainly suffers from noise due to the low signal-to-noise ratio. Many methods have been proposed for the task of image denoising, but they fail to work under extremely low-light conditions. Recently, deep learning based approaches have been presented that have higher objective quality than traditional methods, but they usually have high computational cost which makes them impractical to use in real-time applications or where the processing power is limited. In this paper, we propose a new residual learning based deep neural network for end-to-end extreme low-light image denoising that can not only significantly reduce the computational cost but also improve the quality over existing methods in both objective and subjective metrics. Specifically, in one setting we achieved 29x speedup with higher PSNR. Subjectively, our method provides better color reproduction and preserves more detailed texture information compared to state-of-the-art methods.

关键词： Deep Residual Learning image Denoising Low Light image Enhancement

来源：评论

学校读者我要写书评

暂无评论

Towards GPU Accelerated HyperSpectral Depth Estimation in Medical applications 35

Towards GPU Accelerated HyperSpectral Depth Estimation in Me...

引用

35th conference on Design of Circuits and Integrated Systems (DCIS)

作者： Sancho, Jaime Urbanos, Gemma Ruiz, Luisa Villanueva, Marta Rosa, Gonzalo Diaz, Alberto Villa, Manuel Chavarrias, Miguel Lagares, Alfonso Salvador, Ruben Juarez, Eduardo Sanz, Cesar Univ Politecn Madrid UPM Res Ctr Software Technol & Multimedia Syst Madrid Spain Hosp 12 Octubre Imas12 Inst Invest Sanitaria Madrid Spain Cent Supelec Gif Sur Yvette France

ISBN: (纸本)9781728191324

HyperSpectral (HS) images are commonly used for classification tasks in different domains, such as medicine. In this field, a recent use is the differentiation between healthy tissues and different types of cancerous tissues. To this end, different machine learning techniques have been proposed to generate classification maps that indicate the type of tissue corresponding to each pixel in the image. These 2D representations can be used stand-alone, but they can not be properly registered with other valuable data sources like Magnetic Resonance Imaging (MRI), which can improve the accuracy of the system. For this reason, this paper builds the foundations of a multi-modal classification system that will incorporate 3D information into HS images. Specifically, we address the acceleration of one of the hotspots in depth estimation tools/algorithms. MPEG-I Depth Estimation Reference Software (DERS) provides high-quality depth maps relying on a global energy optimizer algorithm: Graph Cuts. However, this algorithm needs huge processing times, preventing its use during surgical operations. This work introduces GoRG (Graph cuts Reference depth estimation in GPU), a GPU accelerated DERS able to produce depth maps from RGB and HS images. In this paper, due to the lack of HS multi-view datasets at the moment, results are reported on RGB images to validate the acceleration strategy. GoRG shows a x25 average speed-up compared to baseline DERS 8.0, reducing total computation time from around one hour for 8 frames to only a few minutes. A consequence of our parallelization is an average decrease of 1.6 dB in Weighted-to-Spherically-Uniform Peak-signal-to-Noise-Ratio (WS-PSNR), with some remarkable disparities approaching 4 dB. However, using Structural Similarity Index (SSIM) as metric results come closer to baseline DERS. Effectively, an average decrease of only 1.20% is achieved showing that the obtained speed-up gains compesate the subjective quality losses.

关键词： HSI Depth Estimation

来源：评论

学校读者我要写书评

暂无评论

image Segmentation Method Based on Fractional Varying-order Differential

Image Segmentation Method Based on Fractional Varying-order ...

引用

Asia-Pacific signal and Information processing Association Annual Summit and conference (APSIPA)

作者： Yuru Tian Yanshan Zhangy College of Computer Science and Technology China University of Petroleum Qingdao China School of Intelligent Engineering Zhengzhou University of Aeronautics Zhengzhou China

ISBN: (数字)9789881476883

ISBN: (纸本)9781728181301

image segmentation plays a very important role in many applications. At present, the most difficult problem of image segmentation is segmenting intensity inhomogeneous images, some hybrid methods have better segmentation results than the traditional methods. In this paper, a new hybrid level set method based on fractional-varying-order differential curvature is proposed. We define a new curve evolution curvature calculated by fractional-varying-order differential according to the gradient of the level set function, so that the diverse order differential can be used in a whole curve evolution at the same time, which can describe the image edge more accurately. The energy functional for the proposed model consists of three terms: local term, length term and penalty term. The evolution of the level set function is the gradient flow that minimizes the overall energy functional. Experimental results for both synthetic and real images show desirable performance of our method. The Dice similarity coefficient are employed as the comparative quantitative measures for the segmented results.

关键词： image segmentation image edge detection Active contours Nonhomogeneous media Level set Mathematical model Kernel

来源：评论

学校读者我要写书评

暂无评论

Virtual clinical trial for task-based evaluation of a deep learning synthetic mammography algorithm

Virtual clinical trial for task-based evaluation of a deep l...

引用

conference on Medical Imaging - Physics of Medical Imaging

作者： Badal, Andreu Cha, Kenny H. Divel, Sarah E. Graff, Christian G. Zeng, Rongping Badano, Aldo US FDA CDRH OSEL Div Imaging Diagnost & Software Reliabil Silver Spring MD 20993 USA Stanford Univ Dept Elect Engn Stanford CA 94305 USA Stanford Univ Dept Radiol Stanford CA 94305 USA

ISBN: (纸本)9781510625440

image processing algorithms based on deep learning techniques are being developed for a wide range of medical applications. Processed medical images are typically evaluated with the same kind of image similarity metrics used for natural scenes, disregarding the medical task for which the images are intended. We propose a computational framework to estimate the clinical performance of image processing algorithms using virtual clinical trials. The proposed framework may provide an alternative method for regulatory evaluation of non-linear image processing algorithms. To illustrate this application of virtual clinical trials, we evaluated three algorithms to compute synthetic mammograms from digital breast tomosynthesis (DBT) scans based on convolutional neural networks previously used for denoising low dose computed tomography scans. The inputs to the networks were one or more noisy DBT projections, and the networks were trained to minimize the difference between the output and the corresponding high dose mammogram. DBT and mammography images simulated with the Monte Carlo code MC-GPU using realistic breast phantoms were used for network training and validation. The denoising algorithms were tested in a virtual clinical trial by generating 3000 synthetic mammograms from the public VICTRE dataset of simulated DBT scans. The detectability of a calcification cluster and a spiculated mass present in the images was calculated using an ensemble of 30 computational channelized Hotelling observers. The signal detectability results, which took into account anatomic and image reader variability, showed that the visibility of the mass was not affected by the post-processing algorithm, but that the resulting slight blurring of the images severely impacted the visibility of the calcification cluster. The evaluation of the algorithms using the pixel-based metrics peak signal to noise ratio and structural similarity in image patches was not able to predict the reduction in performan

关键词： Digital breast tomosynthesis Mammography image processing Denoising Clinical trials Computer simulations Breast Gaussian filters Medical imaging Monte Carlo methods

来源：评论

学校读者我要写书评

暂无评论

Recognition of low-resolution objects in remote sensing images 25

Recognition of low-resolution objects in remote sensing imag...

引用

conference on image and signal processing for Remote Sensing xxV

作者： Knyaz, Vladimir State Res Inst Aviat Syst GosNIIAS 7 Victorenko Str Moscow Russia MIPT Moscow Russia

ISBN: (数字)9781510630147

ISBN: (纸本)9781510630147

Object detection and recognition is one of the important problems in many remote sensing applications such as monitoring, security, rescue mission and other data analysis tasks. So a large number of approaches and techniques have been developed to improve the quality of object detection. Recently, deep learning methods have made significant progress in detecting objects. But when dealing with objects having small size in the image (which are the often case in monitoring or rescue mission), the quality of detection noticeably decreases. To study the performance and the limits of deep learning abilities for object detection in remote sensing imagery with degrading object resolution in the image, a special dataset of aerial images containing objects of interest (human, car) at different resolution has been collected. The dataset consists of images acquired at different distances to the objects of interest, providing representative subsets of object images of various scale. Two state-of-the-art object detection convolutional neural networks (Faster-RCNN and SSD) was evaluated on the collected dataset. The aim of the study was to find out how the object size in the image influences on the detection performance and to estimate the value of object image size at which the performance drops significantly. Also the approaches for improving the small size object recognition were developed and evaluated. First approach uses multimodal image fusion, the second one applies deep learning to increase the resolution of small objects in the image. The performed tests have proved that the developed approaches allow to improve the quality of object recognition when dealing with low resolution object images.

关键词： object detection deep learning convolutional neural network detection performance image resolution unmanned aerial vehicle

来源：评论

学校读者我要写书评

暂无评论

Efficient Statistical Learning Framework with applications to Human Activity and Facial Expression Recognition

Efficient Statistical Learning Framework with Applications t...

引用

International conference on Advanced Technologies for signal and image processing (ATSIP)

作者： Fatma Najar Sami Bourouis Marwan Alshar’e Roobaea Alroobaea Nizar Bouguila Ali H. Al Badi Ines Channoufi ENIT Laboratoire RISC Robotique Informatique et Systèmes Complexes Université de Tunis El Manar Tunis Tunisie ENIT Laboratoire: LR-SITI Signal Image et Technologies de 1’Information Université de Tunis E1 Manar Tunis Tunisie Taif University Taif Saudi Arabia Faculty of Computing Sciences Gulf College Muscat Oman The Concordia Institute for Information Systems Engineering (CIISE) Concordia University Montreal QC Canada Centre for Postgraduate Studies and Research Gulf College Muscat Oman

ISBN: (数字)9781728175133

ISBN: (纸本)9781728175140

In this paper, we address the problem of human activities and facial expression recognition by investigating the effectiveness of Bayesian inference methods. Indeed, a novel method termed as Bayesian learning for finite multivariate generalized Gaussian mixture model is developed. The multivariate generalized Gaussian distribution is encouraged by its ability to model a large range of data and its shape flexibility. Our main contribution in this work is to develop a Markov Chain Monte Carlo within Metropolis-Hastings algorithm for proposed generative model. In this research, we tackle also some key issues related to machine learning and pattern recognition such as the statistical model's parameters estimation. We demonstrate the merits of our developed learning framework over two challenging applications that concern human activity recognition and facial expression recognition.

关键词： Bayes methods Face recognition Visualization Mixture models Hidden Markov models Feature extraction Vocabulary

来源：评论

学校读者我要写书评

暂无评论

Staistical features extraction in wavelet domain for texture classification

Staistical features extraction in wavelet domain for texture...

引用

International conference on image and signal processing and their applications (ISPA)

作者： Soraya ZEHANI Abdeldjalil OUAHABI Malika MIMI Abdelmalik TALEB-AHMED Electrical Engineering department Biskra University Biskra Algeria Polytech Tours Imaging and Brain University of Tours Tours France Electrical Engineering department Mostaganem University Mostaganem Algeria IEMN DOAE UMR CNRS 8520 UPHF Valenciennes France

ISBN: (纸本)9781728131573

This paper presents a new approach for texture classification generalizing a well-known statistical features combining the fractal analysis by means of fractal dimension (FD) with the selection first and second order statistics features in the spatial and wavelet domain. The objective of our paper is to propose the features extraction using statistical parameters in the spatial domain and in wavelet domain with different wavelets, with and without preprocessing stage for the texture classification using neural networks for pattern recognition and studying the effect of the preprocessing and wavelets in classification accuracy. The extracted features are used as the input of the ANN classifier. The performance of the proposed methods are evaluated by using two classes of Brodatz database textures. Finally, classification assessment measures such as the confusion matrix, ROC curves and accuracy are applied to the proposed methods.

关键词： Artificial neurals network (ANN) Discrete wavelet transform (DWT) Fractal dimension (FD) Preprocessing Statistical features extraction Texture analysis Feature extraction Wavelet domain texture analysis Pretreatment Taxonomy wavelets texture textures fractal analysis spatial domain

来源：评论

学校读者我要写书评

暂无评论

An Automated Feature Tracking Based Algorithm for Estimation of Ice Flow and Glacier Surface Velocity Using Resourcesat-2A Data for Himalayan Terrain 5

An Automated Feature Tracking Based Algorithm for Estimation...

引用

5th International conference on image Information processing (ICIIP)

作者： Bhateja, Yatharath Misra, Indranil Dhar, Debajyoti Shukla, Tushar Roy, Sampa Space Applicat Ctr ISRO Opt Data Proc Div Signal Image Proc Grp Ahmadabad Gujarat India

ISBN: (纸本)9781728108995

Determination of ice flow and glacier surface velocity plays a pivotal role in the study of glacial geography, its sensitivity to climate change and its impact on water cycle of the region. This study becomes of utmost importance in case of Himalayan Cryosphere, which is a source of water to many areas in Asia. In this paper, we propose an algorithm for optical remote sensing multispectral data which can automatically calculate the ice flow velocity and further help other glacier related studies. An ortho-rectified image pair of Resourcesat - 2A LISS-3 (Linear Imaging and Self Scanning) sensor is taken as an input, which is further subjected to a cloud mask and snow feature enhancement technique to improve the visibility of the requisite area. This in turn is used as an input to the first level Principal component analysis (PCA). Further a common raster is extracted and then moving chip based sub-pixel correlation is performed to find the ice shift. Post processing steps are used to remove spurious matches and false positives. In the analysis we observe variations in velocities during the winter and summer season, further fluctuations were also observed in velocities for different zones of glaciers. Average glacier surface velocities ranging from 30my(-1) to 110my(-1) are observed. This study shows that optical image based correlation is suitable and efficient for measurement of ice flow in the fast moving glaciers of the Himalayas.

关键词： Ice Flow Glacier Surface velocity Cryosphere Sub-pixel correlation Resourcesat

来源：评论

学校读者我要写书评

暂无评论

Frame-based reflectance estimation from multispectral images for weed identification in varying illumination conditions

Frame-based reflectance estimation from multispectral images...

引用

Workshops on image processing Theory, Tools and applications, IPTA

作者： Anis Amziane Olivier Losson Benjamin Mathon Aurélien Dumenil Ludovic Macaire Centrale Lille UMR 9189 – CRIStAL – Centre de Recherche en Informatique Signal et Automatique de Lille Univ. Lille CNRS Lille France Chambre d’Agriculture de la Somme Amiens France

ISBN: (数字)9781728187501

ISBN: (纸本)9781728187518

To prevent the growth of weeds in precision farming, multispectral imaging has gained much interest for its ability to provide vegetation images with a high spectral resolution. However, spectral reflectance computation is an issue when the image is assembled from successive frames acquired under varying illumination conditions. In this study, we present a method to estimate reflectance from images acquired by a linescan camera in such conditions. Because rows in a given channel are associated to different illumination conditions, we process the image row-wise to improve reflectance estimation. Experimental segmentation results show that our method is a good candidate to effectively identify crops from weeds.

关键词： Reflectivity image segmentation Lighting Estimation Vegetation mapping Tools Cameras

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：