检索结果-内蒙古大学图书馆

High efficiency depth image-based rendering with simplified inpainting-based hole filling

MULTIDIMENSIONAL systems AND SIGNAL processing 2016年第3期27卷 623-645页

作者： Kuo, Pin-Chen Lin, Jhih-Ming Liu, Bin-Da Yang, Jar-Ferr Natl Cheng Kung Univ Dept Elect Engn Adv Optoelect Technol Ctr One Univ Rd Tainan 70101 Taiwan

Hole and crack filling is the most important issue in depth-image-based rendering (DIBR) algorithms for generating virtual view images when only one view image and one depth map are available. This paper proposes a priority patch inpainting algorithm for hole filling in DIBR algorithms by generating multiple virtual views. A texture-based interpolation method is applied for crack filling. Then, an inpainting-based algorithm is applied patch by patch for hole filling. A prioritized method for selecting the critical patch is also proposed to reduce computation time. Finally, the proposed method is realized on the compute unified device architecture parallel computing platform which runs on a graphics processing unit. Simulation results show that the proposed algorithm is 51-fold faster for virtual view synthesis and achieves better virtual view quality compared to the traditional DIBR algorithm which contains depth preprocessing, warping, and hole filling.

关键词： View synthesis Hole filling Crack filling Inpainting Graphics processing unit (GPU) Depth-image-based rendering (DIBR)

来源：评论

学校读者我要写书评

暂无评论

22nd International Conference on Soft Computing, MENDEL 2016

引用

22nd International Conference on Soft Computing: Evolutionary Computation, Genetic Programming, Swarm Intelligence, Fuzzy Logic, Neural Networks, Chaos, Bayesian Methods, Intelligent image processing, Bio-Inspired Robotics, MENDEL 2016

ISBN: (纸本)9783319580876

The proceedings contain 25 papers. The special focus in this conference is on Soft Computing. The topics include: A multilevel genetic algorithm for the maximum constraint satisfaction problem;models and simulations of queueing systems;influence of random number generators on GPA-ES algorithm efficiency;genetic algorithm based random selection-rule creation for ontology building;improving artificial fish swarm algorithm by applying group escape behavior of fish;genetic programming algorithm creating and assembling subtrees for making analytical functions;comparison of parallel linear genetic programming implementations;geometric particle swarm optimization and reservoir computing for solar power forecasting;walkSAT based-learning automata for MAX-SAT;a self-adaptive artificial bee colony algorithm with incremental population size for large scale optimization;lie algebra-valued bidirectional associative memories;guaranteed training set for associative networks;Markov chain for author writing style profile construction;maximum traveling salesman problem by adapted neural gas;conjugate gradient algorithms for quaternion-valued neural networks;evaluating suitable job applicants using expert system;a computationally efficient approach for mining similar temporal patterns;estimating prevalence bounds of temporal association patterns to discover temporally similar patterns;an approach for imputation of medical records using novel similarity measure;implementation of particle filters for mobile robot localization;direct point cloud visualization using T-spline with edge detection and development of methods of the fractal dimension estimation for the ecological data analysis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

In situ microscopy for online monitoring of cell concentration in Pichia pastoris cultivations

引用

JOURNAL OF BIOTECHNOLOGY 2016年第0期234卷 90-98页

作者： Marquard, D. Enders, A. Roth, G. Rinas, U. Scheper, T. Lindner, P. Leibniz Univ Hannover Inst Tech Chem Callinstr 5 D-30167 Hannover Germany

In situ Microscopy (ISM) is an optical non-invasive technique to monitor cells in bioprocesses in real-time. Pichia pastoris is one of the most promising protein expression systems. This yeast combines fast growth on simple media and important eukaryotic features such as glycosylation. In this work, the ISM technology was applied to Pichia pastoris cultivations for online monitoring of the cell concentration during cultivation. Different ISM settings were tested. The acquired images were analyzed with two image processing algorithms. In seven cultivations the cell concentration was monitored by the applied algorithms and offline samples were taken to determine optical density (OD) and dry cell mass (DCM). Cell concentrations up to 74 g/L dry cell mass could be analyzed via the ISM. Depending on the algorithm and the ISM settings, an accuracy between 0.3 % and 12 % was achieved. The overall results show that for a robust measurement a combination of the two described algorithms is required. (C) 2016 Elsevier B.V. All rights reserved.

关键词： Pichia pastoris Online monitoring In situ microscopy image processing

来源：评论

学校读者我要写书评

暂无评论

Tiled-Block image Reconstruction by Wavelet-Based, Parallel-Filtered Back-Projection

引用

IEEE SENSORS JOURNAL 2016年第12期16卷 4839-4846页

作者： Escobedo, Jorge Guevara Ozanyan, Krikor B. Univ Manchester Sch Elect & Elect Engn Manchester M13 9PL Lancs England

We demonstrate an algorithm, relevant to tomography sensor systems, to obtain images from the parallel reconstruction of essentially localized elements at different scales. This is achieved by combining methodology to reconstruct images from limited and/or truncated data, with the time-frequency capabilities of the wavelet transform. Multiscale, as well as time-frequency, localization properties of the separable two-dimensional wavelet transform are exploited as an approach for faster reconstruction. The speedup is realized not only by reducing the computation load on a single processor, but also by achieving the parallel reconstruction of several tiled blocks. With tiled-block image reconstruction by wavelet-based, parallel filtered back-projection (FBP), we measure more than 36 times gain in speed, compared with standard FBP.

关键词： image reconstruction computed tomography data processing algorithms parallel processing wavelet transform

来源：评论

学校读者我要写书评

暂无评论

Zonal-Alpha-Rooting color image enhancement by the two-Side 2D quaternion discrete fourier transform 14

Zonal-Alpha-Rooting color image enhancement by the two-Side ...

引用

image processing: algorithms and systems xiv 2016

作者： Grigoryan, Artyom M. John, Aparna Agaian, Sos Department of Electrical and Computer Engineering University of Texas at San Antonio One UTSA Circle San AntonioTX78249 United States

The purpose of image enhancement is to improve the quality of a digital image, so as to support the human perception. In this paper, new methods of image enhancement are proposed for enhancement of color images, which are based on application of the concept of the two-dimensional quaternion discrete Fourier transform (QDFT) together with the well-known method of the alpha-rooting. The application of the alpha-rooting method which is based on the traditional two-dimensional discrete Fourier transform (2-D DFT) results in high quality images, when comparing with other transforms, such as Hadamard, Hartley, cosine, and heap transforms. The image enhancement technique of alpha-rooting can be used for enhancing even low contrast images. In zonal alpha-rooting method, the modification of frequency is different for different frequency zones. Optimization of alpha value is done with genetic algorithm. © 2016 Society for Imaging Science and Technology.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Robust extensions to guided image filtering 14

Robust extensions to guided image filtering

引用

image processing: algorithms and systems xiv 2016

作者： Michailovich, Oleg V. University of Waterloo WaterlooON Canada

image denoising is commonly regarded as a problem of fundamental importance in imaging sciences. The last few decades have witnessed the advent of a wide spectrum of denoising algorithms, capable of dealing with noises and images of various types and statistical natures. It is usually the case, however, that the effectiveness of a given denoising procedure and the complexity of its numerical implementation increase pro rata, which is often the reason why more advanced solutions are avoided in situations when data images have relatively large sizes and/or acquired at high frame rates. As a result, substantial efforts have been recently extended to develop efficient means of image denoising, the computational complexity of which would be comparable to that of standard linear filtering. One of such solutions is Guided image Filtering (GIF) - a recently proposed denoising technique, which combines outstanding performance characteristics with real-time implementability. Unfortunately, the standard implementation of GIF is known to perform poorly in situations when noise statistics deviate from that of additive Gaussian noise. To overcome this de-ficiently, in this note, we propose a number of modifications to the filter, which allow it to achieve stable and accurate results in the case of impulse and Poisson noises. © 2016 Society for Imaging Science and Technology.

关键词： image denoising

来源：评论

学校读者我要写书评

暂无评论

Stereo Vision based Object Tracking Control for a Movable Robot Head

引用

IFAC-PapersOnLine 2016年第5期49卷 155-162页

作者： Mohamed, Abdulla Yang, Chenguang Cangelosi, Angelo Centre for Robotics and Neural Systems Plymouth University United Kingdom Zienkiewicz Centre for Computational Engineering Swansea University United Kingdom

In this paper, we have developed a visual tracking control system on a purposely built movable robot head mounted on a Baxter robot. The tracking control algorithm used a stereo vision system provided by a Bumblebee camera, facilitated by the MATLAB computer vision toolbox. The objective of this work is to enable a robot to move its head as in a similar manner as our humans beings to focus vision on a moving object. Identification of object and estimation of its coordinate are performed based on image processing techniques. A fuzzy logic technique is applied to control the moving head in order to bring human like motion into the robot. The method developed in this work can be extended to any other movable robot head platform. Extensive experimental studies have been performed to test the effectiveness and efficiency of the proposed method. © 2016

关键词： Stereo image processing Computer circuits Computer control systems Fuzzy logic image processing Navigation Robots Stereo vision Tracking (position) Visual servoing Effectiveness and efficiencies Fuzzy logic techniques Human like motion image processing technique Object Tracking Stereo vision system Tracking control algorithms Visual tracking control

来源：评论

学校读者我要写书评

暂无评论

image Segmentation of Microscopic Wastewater images using Phase Contrast Microscopy

Image Segmentation of Microscopic Wastewater Images using Ph...

引用

IEEE Conference on systems, Process and Control (ICSPC)

作者： Nisar, Humaira Hang, Ho Yuen Siang, Soh Chit Khan, Muhammad Burhan Univ Tunku Abdul Rahman Fac Engn & Green Technol Dept Elect Engn Kampar Malaysia

ISBN: (纸本)9781509011810

image processing and analysis is a useful tool for monitoring of activated sludge wastewater treatment plants. However, its effectiveness is dependent on performance of the segmentation algorithms. The activated sludge wastewater plant can be monitored by image processing and analysis of images acquired through microscope using bright field microscopy and phase contrast microscopy. In this paper, we have investigated three segmentation algorithms which are channel based segmentation, edge based segmentation and Bradley based segmentation. The performance of the algorithms is assessed using the performance metric of accuracy. Forty gold approximations of ground truth images are manually prepared for comparing with the result for segmentation. Half of the forty images are acquired at lOx and rest at 20x objective magnification of the microscope. Edge based segmentation gives better results compared to other algorithms with accuracy of 0.972.

关键词： image segmentation phase contrast microscopy wastewater treatment edge detection filamentous bacteria

来源：评论

学校读者我要写书评

暂无评论

image analysis operations applied to hyperspectral images for non-invasive sensing of food quality - A comprehensive review

引用

BIOsystems ENGINEERING 2016年 142卷 53-82页

作者： ElMasry, Gamal M. Nakauchi, Shigeki Toyohashi Univ Technol Dept Comp Sci & Engn Tenpa Ku 1-1 Hibarigaoka Toyohashi Aichi 4418580 Japan Suez Canal Univ Dept Agr Engn Fac Agr Ismailia Egypt

image analysis involving mathematical, statistical and software programming approaches are the essential elements of any computer-integrated hyperspectral imaging systems. The theoretical and practical issues associated with the development, analysis, and application of essential image processing algorithms are explored in order to exploit hyperspectral imaging for application to food quality evaluations. The breadth of different image processing approaches adopted over the years in attempting to implement hyperspectral imaging for food quality monitoring was surveyed. Firstly, the fundamental configurations and working principles of hyperspectral systems, as well as the basic concept and structure of hyperspectral data, were described and explained. The understanding of different approaches used during image acquisition, data collection and visualisation were examined. Strategies and essential image processing routines necessary for making the appropriate decision during detection, classification, identification, quantification and/or prediction processes are presented. Examples and figures were selected to reinforce the main approach of each analysis algorithm applied in different agro-food products to answer the question "What does the user want to see in the target food samples?" The theoretical background for each algorithm was beyond the scope of this article thus only essential equations were addressed. The literature presented clearly revealed that hyperspectral imaging systems have gained a rapid interest from researchers to display the chemical structure and related physical properties of numerous types of food stuffs and hyper spectral imaging systems are expected to gain more considerably more potential and application in food processing and engineering plants. (C) 2015 IAgrE. Published by Elsevier Ltd. All rights reserved.

关键词： image processing image analysis Hyperspectral imaging Multispectral imaging Machine vision Food quality

来源：评论

学校读者我要写书评

暂无评论

Comparison study of Gaussian mixture models for fingerprint image duplication with a new model 14

Comparison study of Gaussian mixture models for fingerprint ...

引用

image processing: algorithms and systems xiv 2016

作者： Agaian, Sos S. Yeole, Rushikesh D. Reinecke, Gary Ann, Mary Troy, Mike Division of Engineering University of Texas at San Antonio One UTSA Circle San AntonioTX782549 United States University of Texas at San Antonio One UTSA Circle San AntonioTX78249 United States Boston University United States FlashScan3D United States

This paper presents a comparison study of Gaussian Mixture Models for fingerprints image duplication and analysis. It also presents a new probabilistic Parametric Gaussian Mixture Model(GMM). The system is built around the likelihood ratio test for verification, using simple but effective GMMs for likelihood functions and a form of Bayesian adaptation to derive the models. The Computer simulation show that the developed new algorithms have the most optimal performance as compared to state of art algorithms GMMs, Generalized GMMs, Finite Bayesian learning for GMMS, Texture Synthesis and Improved Adaptive Algorithm. The performance of the presented algorithm was evaluated by Bovik Index, Entropy and Mean Square Error. © 2016 Society for Imaging Science and Technology.

关键词： Mean square error

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：