检索结果-内蒙古大学图书馆

2018 International conference on Intelligent systems and Computer vision, ISCV 2018

作者： El Khoukhi, Hasnae Sabri, My Abdelouahed LIIAN Department of computer science Faculty of Sciences Dhar-Mahraz Sidi Mohamed Ben Abdellah University Fez Morocco

ISBN: (纸本)9781538643969

Digital image processing (DIP) plays a vital role in the analysis and interpretation of remotely sensed data. It forms core research area within engineering and computer science disciplines too. This paper describes a proposal design for image processing in Verilog and that can be applied for any format of images like jpg, gif, bmp etc. The main advantage of using Verilog to simulate DIP of any logical inputs is related with the possibility of an immediate FPGA based hardware implementation. Our algorithm is designed in Verilog and simulated using the Matlab and Modelsim. In fact, the input image is converted to text/pixel using Matlab and results are stored in a new text file. Using Verilog with test bench program, the inputs, outputs and memory locations are assigned in the form of text file. Then, the output texts file back to image after a conversion step using Matlab. A comparative study between HDLs Simulation and Matlab are conducted. Obtained results show well the efficiency of the proposed design. As an extension of this work, we aim to implement an efficient FPGA based hardware design for a set of image processing, enhancement, and filtering algorithms. © 2018 IEEE.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

Contrast Optimization using Elitist Metaheuristic Optimization and Gradient Approximation for Biomedical image Enhancement

Contrast Optimization using Elitist Metaheuristic Optimizati...

引用

Amity International conference on Artificial Intelligence (AICAI)

作者： Chakraborty, Shouvik Raman, Aishwarya Sen, Soumya Mali, Kalyani Chatterjee, Sankhadeep Hachimi, Hanaa Univ Kalyani Dept Comp Sci & Engn Nadia W Bengal India Univ Engn & Management Dept Comp Applicat Kolkata W Bengal India Univ Calcutta AK Choudhury Sch Informat Technol Kolkata W Bengal India Univ Engn & Management Dept Comp Sci & Engn Kolkata W Bengal India Ibn Tofail Univ Dept Informat Logist & Math Kenitra Morocco

ISBN: (纸本)9781538693469

Biomedical image analysis is one of the most challenging and inevitable part of the computer aided diagnostic systems. Automated analysis of the image can detect various diseases automatically without human intervention. Computer vision and artificial intelligence can sometimes defeat human diagnostic power and can reveal some hidden information from the biomedical images. In the field of health care, accurate results are highly required within stipulated amount of time. But to increase accuracy, proper preprocessing with sophisticated algorithms is required. Low quality image can affect processing algorithm which can leads to the poor result. Therefore, sophisticated preprocessing methods are required to get reliable results. Contrast is one of the most important parameter for any image. Poor contrast may cause several problems for computer vision algorithms. Conventional algorithms for contrast adjustment may not be suitable for many purposes. Sometimes, these methods can generate some images that may lose some critical information. In this work, a contrast optimization method based on well-known metaheuristic technique called genetic algorithm with elitism is used that can enhance the biomedical images for better analysis. A new kernel has been proposed to detect the edges. Obtained results illustrate the efficiency of the proposed algorithm.

关键词： Biomedical image enhancement contrast optimization genetic algorithm metaheuristic supported preprocessing automated health care system

来源：评论

学校读者我要写书评

暂无评论

Representation and processing of multispectral satellite images and sequences 22

Representation and processing of multispectral satellite ima...

引用

22nd International conference on Knowledge-Based and Intelligent Information and Engineering systems (KES)

作者： Vasiliev, Konstantin Dementiev, vitaly Andriyanov, Nikita Ulyanovsk State Tech Univ Ulyanovsk 432027 Russia

The article considers a complex approach to image processing based on the application of mathematical models. At the same time, special attention is paid to the processing of images' sequences. Moreover, the proposed algorithms are developed for processing satellite multispectral images. The presented filtering algorithm is of great applied importance as well as an algorithm for detecting objects and delineating boundaries. In this paper, description of complex images is achieved by using doubly stochastic models of random fields and the quasi-isotropic properties of generated images is obtained by using autoregressive models with multiple roots of the characteristic equations. (C) 2018 The Authors. Published by Elsevier Ltd.

关键词： doubly stochastic models image processing filtering autoregression with multiple roots

来源：评论

学校读者我要写书评

暂无评论

Pansharpening of Multispectral images based on Cycle-spinning Quincunx Lifting Transform

Pansharpening of Multispectral Images based on Cycle-spinnin...

引用

Signal, Information and Data processing (ICSIDP), IEEE International conference on

作者： Yan Shi Wanyu Zhou Wei Li Beijing Key Laboratory of Fractional Signals and Systems School of Information and Electronics Beijing Institute of Technology Beijing China

ISBN: (数字)9781728123455

ISBN: (纸本)9781728123462

Pansharpening is a process of fusing the multispectral (MS) images with the panchromatic (PAN) image to improve the spatial resolution of the MS images. The key of pansharpening is how to extract the lost detail from the PAN image and add it to the MS images with an appropriate injection model. In this paper, a pansharpening approach based on cycle-spinning quincunx lifting transform (CQLT) is proposed. The CQLT features translation invariance and vanishing moments which can extract the detail properly. In order to reduce the spectral distortion of the fused image, the histogram matching along with two popular injection models are involved in the fusion. Experimental results show that the proposed method has better quantitative results as well as competitive visual results compared with some other state-of-the-art algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Color image Segmentation Techniques: A Survey 1st

Color Image Segmentation Techniques: A Survey

引用

1st International conference on Microelectronics, Computing & Communication systems (MCCS)

作者： Jain, Sneha Laxmi, vijaya Birla Inst Technol Mesra Dept Elect & Elect Engn Ranchi Bihar India

ISBN: (纸本)9789811055652;9789811055645

In today's world, where digital image processing is becoming an essential part of technology, segmentation of images poses a challenging problem. Before any complex task that has to be done on images, segmentation is a prerequisite. Segmentation ensures the simplification of a problem by changing the representation of an image from a complex one to a more analytical and easier form. Pixels of segmented regions share common characteristics. Perfect segmentation is difficult to obtain. There exist many techniques which have been applied such as edge-based segmentation, region-based segmentation, morphological operations, thresholding and clustering methods. Segmentation has a crucial role in image analysis. The accuracy of segmentation determines the success or failure of computer algorithms. Therefore, there is a need to develop efficient and less time-consuming algorithms for segmentation. This paper summarizes a number of segmentation methods.

关键词： Clustering Edge maximization technique Segmentation Thresholding Watershed algorithm

来源：评论

学校读者我要写书评

暂无评论

The study of effectiveness of a high-performance crystal lattice parametric identification algorithm based on CUDA technology 5

The study of effectiveness of a high-performance crystal lat...

引用

5th International conference on Information Technology and Nanotechnology, ITNT 2019

作者： Shirokanev, A.S. Kirsh, D.V. Kupriyanov, A.V. Samara National Research University Moskovskoe Shosse 34A Samara443086 Russia Image Processing Systems Institute of RAS Branch of the FSRC Crystallography and Photonics RAS Molodogvardejskaya street 151 Samara443001 Russia

The study of substances with a crystal structure is a complex multi-step process. The key step in the crystalline substance analysis is the unit cell parameter estimation. The estimation of the crystal lattice unit cell parameters is a particular problem that involves the search of the crystal lattice model's parameters according to the information which can be extracted from the substance. In these recent times, the most accurate information about the substance structure can be obtained with the electron microscope whose linear resolution is high enough to observe the atomic structure of a substance. The problem of parameter estimation in this case means the reconstruction of the three-dimensional crystal lattice with 2-dimentional images received by an electron microscope, and the estimation of the crystal lattice unit cell parameters by reconstructed lattice. In the previous papers the crystal lattice parametric identification algorithms based on solving the local optimization problem were presented. However, the analysis of a large crystal lattice database requires a lot of computations. In this paper, a high-performance crystal lattices parametric identification algorithm using the CUDA technology is proposed. The investigation of the algorithm effectiveness is carried out on the GPU GeForce Nvidia GTX 1070 Ti. With data dimension more than 32 translations the acceleration is higher than 70. The algorithm runs more efficiently at the use of a large number of CUDA-blocks. © 2019 IOP Publishing Ltd. All rights reserved.

关键词： Parameter estimation

来源：评论

学校读者我要写书评

暂无评论

Navel Orange Recognition Method Based on Improved Otsu Algorithm

Navel Orange Recognition Method Based on Improved Otsu Algor...

引用

International conference on Intelligent Computing, Automation and systems (ICICAS)

作者： Kai Liu Changgeng Yu Liping Lai School of Information and Communication Guilin University of Electronic Technology Guilin China School of Information and Communication Engineering Hezhou University Guangxi China

ISBN: (数字)9781728161068

ISBN: (纸本)9781728161075

An improved Otsu threshold segmentation algorithm with filling a circle method based on the center of mass(FCCM) is proposed to solve the problems of missing regional feature information and unsatisfactory effect in navel orange recognition by traditional image processing method. We first choose the appropriate color model. By analyzing the data, YCbCr model has better contrast compared with other color models, and the histogram of its Cr component has obvious peaks and troughs, which is conducive to image segmentation. We then segmented the extracted Cr component images by Otsu threshold segmentation algorithm. And further processing is carried out in combination with morphology and hole filling algorithm to make the image coherent, so as to ensure that the feature information of navel orange is not easy to be missing. And next, the center of mass of the image is determined and the radius of the detection circle is calculated by stepping method. Finally, the noise points outside the radius of the detection circle are eliminated and the recognition results are displayed in the original image. The experimental results show that the proposed method is effective in the recognition of low pixel images with both different light conditions and obscured condition.

关键词： feature extraction image colour analysis image segmentation image colour analysis image segmentation COLOR MODEL Citrus sinensis Feature extraction Recognition (Psychology) Radius images Circles troughs algorithms

来源：评论

学校读者我要写书评

暂无评论

Joint Autoregressive and Hierarchical Priors for Learned image Compression 32

Joint Autoregressive and Hierarchical Priors for Learned Ima...

引用

32nd conference on Neural Information processing systems (NIPS)

作者： Minnen, David Balle, Johannes Toderici, George Google Res Mountain View CA 94043 USA

Recent models for learned image compression are based on autoencoders that learn approximately invertible mappings from pixels to a quantized latent representation. The transforms are combined with an entropy model, which is a prior on the latent representation that can be used with standard arithmetic coding algorithms to generate a compressed bitstream. Recently, hierarchical entropy models were introduced as a way to exploit more structure in the latents than previous fully factorized priors, improving compression performance while maintaining end-to-end optimization. Inspired by the success of autoregressive priors in probabilistic generative models, we examine autoregressive, hierarchical, and combined priors as alternatives, weighing their costs and benefits in the context of image compression. While it is well known that autoregressive models can incur a significant computational penalty, we find that in terms of compression performance, autoregressive and hierarchical priors are complementary and can be combined to exploit the probabilistic structure in the latents better than all previous learned models. The combined model yields state-of-the-art rate-distortion performance and generates smaller files than existing methods: 15.8% rate reductions over the baseline hierarchical model and 59.8%, 35%, and 8.4% savings over JPEG, JPEG2000, and BPG, respectively. To the best of our knowledge, our model is the first learning-based method to outperform the top standard image codec (BPG) on both the PSNR and MS-SSIM distortion metrics.

关键词： image compression

来源：评论

学校读者我要写书评

暂无评论

Accelerating Real-Time, High-Resolution Depth Upsampling on FPGAs 3

Accelerating Real-Time, High-Resolution Depth Upsampling on ...

引用

3rd IEEE International conference on image processing, Applications and systems (IPAS)

作者： Langerman, David Sabogal, Sebastian Ramesh, Barath George, Alan Univ Pittsburgh Dept Elect & Comp Engn NSF Ctr Space High Performance & Resilient Comp S Pittsburgh PA 15260 USA

ISBN: (纸本)9781728102474

While the popularity of high-resolution, computer-vision applications (e.g. mixed reality, autonomous vehicles) is increasing, there have been complementary advances in time-of-flight depth sensor resolution and quality. These advances in time-of-flight sensors provide a platform for new research into realtime, depth-upsampling algorithms targeted at high-resolution video systems with low-latency requirements. This paper describes a case study in which a previously developed bilateral-filter-style upsampling algorithm is profiled, parallelized, and accelerated on an FPGA using high-level synthesis tools from Xilinx We show that our accelerated algorithm can effectively upsample the resolution and reduce the noise of time-of-flight sensors. We also demonstrate that this algorithm exceeds the real-time requirements of 90 frames per second necessitated by mixed-reality hardware, achieving a lower-bound speedup of 40 times over the fastest CPU-only version.

关键词： time-of-flight sensor depth upsampling FPGA acceleration high level synthesis image processing

来源：评论

学校读者我要写书评

暂无评论

Geological Feature Prediction Using image-Based Machine Lear

引用

PETROPHYSICS 2018年第6期59卷 750-760页

作者： Jobe, T. D. vital-Brazil, E. Khait, M. Armco Res Ctr 16300 Pk Row Dr Houston TX 77469 USA IBM Res Rua Tutoia 1157 BR-04007005 Paraiso SP Brazil Delft Univ Technol Dept Petr Engn Bldg 23 Stevinweg 1 NL-2628 CN Delft Netherlands

Petrographic description is one of the primary methods by which geoscientists develop an understanding of geologic systems and constrain source, reservoir, and seal characteristics. Geologic facies or rock types are routinely interpreted from petrographic features in thin sections, hut these methods are time consuming and tedious. The interpretations can be heavily biased. Variations in experience base, microscope quality, and scale of observation can lead to inconsistent interpretations, absorbing costly time to achieve alignment. With advances in computing, millions of images can be analyzed in seconds through signal-processing technologies. With this capability, machine-learning methods can support geologic pattern identification to classify geologic features. Combined, automated image analysis and classification though machine learning can significantly reduce analysis time, interpreter bias and inconsistencies. These methods make it possible to share "expert knowledge" with nonexpert users. image processing, segmentation and classification are key workflows for translating geologic features into discrete representations that can be used for computational modeling. Here, we present two examples where advanced image analysis and machine learning are used to predict geologic and petrophysical properties from optical microscopy thin-section images. The first example uses multiple machine-learning algorithms and pore geometries as a means for predicting and classifying rock properties, such as lithofacies, reservoir zone, porosity and permeability. The second example focuses on training and using convolutional neural networks to classify and predict Dunham textures (mudstone, wackestone, packstone and grainstone) from carbonate thin sections. Data for both machine-learning applications comes from a Jurassic bimodal carbonate reservoir. Key depositional lithofacies include micritic mudstones, bivalve-coated grain pack/grainstones, Cladocoropsis pack/grainstones, stro

关键词： Artificial Intelligence december 2018 aapg bulletin computer Reservoir Characterization geological feature prediction Symposium machine learning Upstream Oil & Gas computer neural network Artificial intelligence Information Management and systems Reservoir Characterization

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：