检索结果-内蒙古大学图书馆

Blind super-resolution restoration with frame-by-frame nonparametric blur estimation

MULTIDIMENSIONAL systems AND SIGNAL processing 2016年第1期27卷 255-273页

作者： Qian, Qinchun Gunturk, Bahadir K. Louisiana State Univ Sch Elect Engn & Comp Sci Baton Rouge LA 70803 USA

In this paper, we investigate super-resolution image restoration from multiple images, which are possibly degraded with large nonparametric motion blur. The blur kernel for each input image is separately estimated. This is unlike many existing super-resolution algorithms, which assume identical blur kernel for all input images. We also do not make any restrictions on the motion field among images;that is, we estimate dense motion field without simplifications such as parametric motion. We present a two-step algorithm: In the first step, each input image is deblurred using its estimated blur kernel. In the second step, multi-frame super-resolution restoration is applied to the deblurred images. Because the estimated blur kernels may not be accurate, we propose a weighted cost function for the super-resolution restoration step, where a weight associated with an input image reflects the reliabilities of the corresponding kernel estimate and deblurred image. We provide experimental results with both simulated and real data, and show the effectiveness and robustness of the proposed method compared to some alternative approaches and state-of-the-art methods.

关键词： Motion deblurring Super-resolution Blind image deconvolution

来源：评论

学校读者我要写书评

暂无评论

Automated processing of Cytological and Histological images 12

Automated Processing of Cytological and Histological Images

引用

12th International Conference on Perspective Technologies and Methods in MEMS Design (MEMSTECH)

作者： Berezsky, Oleh Pitsun, Oleh Ternopil Natl Econ Univ CIT Dept Lvivska St 11 Ternopol Ukraine

The paper analyzes well-known automated microscopy systems. The work presents the comparative analysis of low-and middle-designed algorithms. The adaptive module of pre-processing and image segmentation has been worke... 详细信息

ISBN: (纸本)9786176079132

关键词： automated microscopy system algorithm image preprocessing and segmentation

来源：评论

学校读者我要写书评

暂无评论

ProxImaL: Efficient image Optimization using Proximal algorithms

ProxImaL: Efficient Image Optimization using Proximal Algori...

引用

ACM SIGGRAPH Conference

作者： Heide, Felix Diamond, Steven Niessner, Matthias Ragan-Kelley, Jonathan Heidrich, Wolfgang Wetzstein, Gordon Stanford Univ Stanford CA 94305 USA Univ British Columbia Vancouver BC V5Z 1M9 Canada KAUST Thuwal Saudi Arabia

ISBN: (纸本)9781450342797

Computational photography systems are becoming increasingly diverse, while computational resources-for example on mobile platforms-are rapidly increasing. As diverse as these camera systems may be, slightly different variants of the underlying image processing tasks, such as demosaicking, deconvolution, denoising, inpainting, image fusion, and alignment, are shared between all of these systems. Formal optimization methods have recently been demonstrated to achieve state-of-the-art quality for many of these applications. Unfortunately, different combinations of natural image priors and optimization algorithms may be optimal for different problems, and implementing and testing each combination is currently a time-consuming and error-prone process. ProxImaL is a domain-specific language and compiler for image optimization problems that makes it easy to experiment with different problem formulations and algorithm choices. The language uses proximal operators as the fundamental building blocks of a variety of linear and nonlinear image formation models and cost functions, advanced image priors, and noise models. The compiler intelligently chooses the best way to translate a problem formulation and choice of optimization algorithm into an efficient solver implementation. In applications to the image processing pipeline, deconvolution in the presence of Poisson-distributed shot noise, and burst denoising, we show that a few lines of ProxImaL code can generate highly efficient solvers that achieve state-of-the-art results. We also show applications to the nonlinear and nonconvex problem of phase retrieval.

关键词： computational photography digital image processing optimization

来源：评论

学校读者我要写书评

暂无评论

Scene reduction for subjective image quality assessment

引用

JOURNAL OF ELECTRONIC IMAGING 2016年第1期25卷 1-13页

作者： Lewandowska (Tomaszewska), Anna West Pomeranian Univ Technol Fac Comp Sci & Informat Syst Ul Zolnierska 49 PL-71210 Szczecin Poland

Evaluation of image quality is important for many image processing systems, such as those used for acquisition, compression, restoration, enhancement, or reproduction. Its measurement is often accompanied by user studies, in which a group of observers rank or rate results of several algorithms. Such user studies, known as subjective image quality assessment experiments, can be very time consuming and do not guarantee conclusive results. This paper is intended to help design an efficient and rigorous quality assessment experiment. We propose a method of limiting the number of scenes that need to be tested, which can significantly reduce the experimental effort and still capture relevant scene-dependent effects. To achieve it, we employ a clustering technique and evaluate it on the basis of compactness and separation criteria. The correlation between the results obtained from a set of images in an initial database and the results received from reduced experiment are analyzed. Finally, we propose a procedure for reducing the initial scenes number. Four different assessment techniques were tested: single stimulus, double stimulus, forced choice, and similarity judgments. We conclude that in most cases, 9 to 12 judgments per evaluated algorithm for a large scene collection is sufficient to reduce the initial set of images. (C) 2015 SPIE and IS&T

关键词： image quality assessment image evaluation user study perceptual experiments computer vision

来源：评论

学校读者我要写书评

暂无评论

Concatenated image completion via tensor augmentation and completion 10

Concatenated image completion via tensor augmentation and co...

引用

10th International Conference on Signal processing and Communication systems (ICSPCS)

作者： Bengua, Johann A. Tuan, Hoang D. Phien, Ho N. Do, Minh N. Univ Technol Sydney Fac Engn & Informat Technol Ultimo Australia Univ Illinois Dept Elect & Comp Engn Urbana IL USA Univ Illinois Coordinated Sci Lab Urbana IL USA

ISBN: (纸本)9781509009411

This paper proposes a novel framework called concatenated image completion via tensor augmentation and completion (ICTAC), which recovers missing entries of color images with high accuracy. Typical images are second-or third-order tensors (2D/3D) depending if they are grayscale or color, hence tensor completion algorithms are ideal for their recovery. The proposed framework performs image completion by concatenating copies of a single image that has missing entries into a third-order tensor, applying a dimensionality augmentation technique to the tensor, utilizing a tensor completion algorithm for recovering its missing entries, and finally extracting the recovered image from the tensor. The solution relies on two key components that have been recently proposed to take advantage of the tensor train (TT) rank: A tensor augmentation tool called ket augmentation (KA) that represents a low-order tensor by a higher-order tensor, and the algorithm tensor completion by parallel matrix factorization via tensor train (TMac-TT), which has been demonstrated to outperform state-of-the-art tensor completion algorithms. Simulation results for color image recovery show the clear advantage of our framework against current state-of-the-art tensor completion algorithms.

关键词： Color image recovery tensor completion ket augmentation tensor train rank image concatenation

来源：评论

学校读者我要写书评

暂无评论

Hue-Preserving Color image processing with a High Arbitrariness Without Gamut Problem

Hue-Preserving Color Image Processing with a High Arbitrarin...

引用

International Symposium on Intelligent Signal processing and Communication systems (ISPACS)

作者： Kamiyama, Minako Taguchi, Akira Tokyo City Univ Fac Knowledge Engn Dept Comp Sci Setagaya Ku Tokyo 1588557 Japan

ISBN: (纸本)9781509006298

Preserving hue is an important issue for color image processing. In order to preserve hue, color image processing is often carried out in HSI or HSV color space which is translated from RGB color space. Transforming from RGB color space to another and processing in these spaces usually generate gamut problem. We propose image enhancement algorithms which conserve hue and preserve the range (gamut) of the R, G, B channels. First we show an intensity processing method while preserving hue and saturation. In this method, arbitrary gray-scale transform functions can be applied in the intensity component. Next, a hue and intensity preserving saturation mapping method is proposed. Arbitrary gray-scale methods can be also applied in the saturation mapping. Finally, we combine two methods and realize the hue-preserving color image processing with a high arbitrariness without gamut problem. Numerical results confirm our theoretical results and show that our processing scheme performs much better than the conventional hue-preserving methods.

关键词： Color image enhancement gamut hue preserving intensity saturation gray-level transformation

来源：评论

学校读者我要写书评

暂无评论

Non-destructive inspection of aircraft composite materials using triple IR imaging

引用

IFAC-PapersOnLine 2016年第28期49卷 291-296页

作者： Moustakidis, S. Anagnostis, A. Karlsson, P. Hrissagis, K. City University of London London United Kingdom IRETETH Institute for Research and Technology Thessaly CERTH Centre for Research & Technology Hellas Thessaloniki Greece

The wide use of composite materials in a number of industrial sectors has necessitated the development of new nondestructive inspection techniques for both manufacturing quality assurance and in-service damage testing. This paper discusses the development of a new holistic inspection system for aircraft composite materials that is composed of three thermographic cameras (operating at different wavelengths such as Near-infrared, Mid-Wave and Long-Wave) placed on the head of a robotic arm. Different setups were investigated in order to achieve optimal settings for a variety of influencing parameters including camera distance from the surface under investigation, excitation source type and power. Experiments were also conducted to define the effectiveness of each thermographic camera towards a variety of defect types. Advanced image processing algorithms were further developed and deployed to enhance the inspection capabilities of the three cameras and improve the interpretation of the collected thermal images. Future work on validating fusion and machine learning tools, their integration as well as on-site inspections has been planned. © 2016

关键词： Nondestructive examination Aircraft materials Cameras Composite materials Data handling Data processing Fighter aircraft image enhancement Infrared devices Inspection Learning systems Materials testing Quality assurance Thermography (imaging) Thermography (temperature measurement) Aircraft inspections Excitation sources image processing algorithm Influencing parameters Manufacturing quality Non destructive inspection On site inspection Thermographic cameras

来源：评论

学校读者我要写书评

暂无评论

processing Time Reduction of Tone Mapping Based on Iterative Shrinkage Smoothing Using Parallel processing

Processing Time Reduction of Tone Mapping Based on Iterative...

引用

International Symposium on Intelligent Signal processing and Communication systems (ISPACS)

作者： Imai, Seijiro Kasauka, Dabwitso Tsutsui, Hiroshi Imagawa, Takashi Okuhata, Hiroyuki Miyanaga, Yoshikazu Hokkaido Univ Grad Sch Informat Sci & Technol Kita Ku Kita 14Nishi 9 Sapporo Hokkaido 0600814 Japan Synth Corp Esaka Soliton Bldg 8th FloorEsaka Cho 1-12-38 Suita Osaka 5640063 Japan

ISBN: (纸本)9781509006298

Iterative shrinkage smoothing algorithm can perform image smoothing with eliminating fine details and preserving principal edges in an image. However, real time processing is difficult due to large processing time when input image size is large. By utilizing downscaled image of an input image, the processing time can be dramatically reduced. In this case, however, the information of preserved principal edges is not accurate. Considering the applications utilizing such edge preserving smoothing algorithms, such as image tone mapping and detail enhancement, inaccurate principal edge information degrades the quality of resulted images. In this paper, we focus on tone mapping in the applications and propose processing time reduction method of tone mapping based on iterative shrinkage smoothing by utilizing parallel processing. Experimental results show that the proposed method improves the frame rates to 16 and 10 times for VGA and full HD resolutions, respectively, compared to single process implementation.

关键词： Parallel processing multiprocessing tone mapping image smoothing edge-aware smoothing Retinex

来源：评论

学校读者我要写书评

暂无评论

A high-speed image super-resolution algorithm based on sparse representation for MEMS defect detection 11

A high-speed image super-resolution algorithm based on spars...

引用

11th IEEE Annual International Conference on Nano/Micro Engineered and Molecular systems, NEMS 2016

作者： Li, Xiuyuan Zhao, Yulong Hu, Tengjiang Zhang, Qi Li, Yingxue State Key Laboratory for Mechanical Manufacturing System Xi'An Jiaotong University China Collaborative Innovation Center of High-End Manufacturing Equipment Xi'An Jiaotong University China

ISBN: (纸本)9781509019472

A novel high- speed image super-resolution algorithm based on sparse representation for MEMS defect detection is proposed in this paper. Traditional super-resolution algorithms adopt a single dictionary to represent images, which cannot differentiate varieties of image blocks and leads to slow processing speed. Aiming at overcoming this shortage of traditional super-resolution algorithms, image blocks are divided into different categories by local features and each of these categories possesses the corresponding high and low resolution dictionary pairs. Experimental results of different MEMS defects show that the improved algorithm can obtain images of little lower quality with much less processing time, indicating that the proposed algorithm is more suitable for MEMS defect detection. © 2016 IEEE.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Parallel image processing on the Sunway Many-core Processor

Parallel Image Processing on the Sunway Many-core Processor

引用

18th IEEE International Conference on High Performance Computing and Communications (HPCC) / 14th IEEE International Conference on Smart City (Smart City) / 2nd IEEE International Conference on Data Science and systems (DSS)

作者： Zhao, Meiting Liu, Rui Liu, Yi Song, Kaida Qian, Depei Beihang Univ Sinogerman Joint Software Inst Beijing Peoples R China State Key Lab Math Engn & Adv Comp Wuxi Peoples R China

ISBN: (纸本)9781509042975

Many image processing algorithms have been parallelized successfully on many-core processors, such as GPU and Intel Xeon Phi. In this paper, we choose the Sunway many-core processor SW26010, which is a new processor designed and made in China that constitutes the current NO. 1 supercomputer Sunway TaihuLight. This paper firstly introduces the architecture of Sunway SW26010 processor and two representative image processing algorithms: local binary pattern (LBP) and histogram of oriented gradient (HOG). Furthermore we propose a method of parallel implementation, and the experimental results of this method show that the speedup can be up to 170 for LBP and 33 for HOG. Then two optimized methods are brought forward based on this parallel implementation, including the optimization of program and parallel design. We optimize the program by using the method that combined step transmission and software prefetching. From the experiment results of the first optimization we can know that the maximum speedup can reach 310 for LBP with processing high-resolution images and 83 for HOG. Then we optimize the parallel design by using a coarse grained parallel method, and the experimental results show that the speedup can be up to 370 for LBP and 95 for HOG when processing low-resolution images. Finally, we investigate the scalability of our parallelism on the Sunway TaihuLight with different number of processor nodes, and the experiment results prove that the two algorithms' parallel design and implementation have better expansibility.

关键词： image processing Sunway SW26010 processor the Sunway TaihuLight supercomputer parallel implementation optimization

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：