检索结果-内蒙古大学图书馆

26th International Conference on Radioelektronika (RADIOELEKTRONIKA)

作者： Oravec, Jakub Ovsenik, L'ubos Turan, Jan Tech Univ Kosice Fac Elect Engn & Informat Dept Elect & Multimedia Commun Kosice Slovakia

ISBN: (纸本)9781509016747

The Mojette transform has found several applications to this date. Some of them, such as systems for distributed file storage, or digital tomography systems exploit one of the main properties of Mojette transform - redundancy. However, sometimes this feature is not desirable. This is a case of applying Mojette transform for image encoding, or decoding. In these applications, higher rate of redundancy can cause longer processing times and bigger size of image data. These problems can be solved by group of procedures, which would work in a determined manner. In this article, we tried to propose a set of algorithms, which would reduce the drawbacks of Mojette transform, but exploit its advantages in the field of image coding.

关键词： image coding image reconstruction Mojette transform redundancy

来源：评论

学校读者我要写书评

暂无评论

An Experimental Comparison of Super-resolution Reconstruction for image Sequences 35

An Experimental Comparison of Super-resolution Reconstructio...

引用

第35届中国控制会议

作者： GONG Youmin ZOU Xing GUO Yanning DONG Zhen Department of Control Science and Engineering Harbin Institute of Technology Shanghai Institute of Satellite Engineering

ISBN: (纸本)9781509009107

Super-resolution reconstruction for image sequences is a promising image processing technology that using complementary information among a set of images to reconstruct a high-resolution *** super-resolution reconstruction algorithms have been studied in the literature to reconstruct a high-resolution *** this paper,first,after presenting a condensed introduction of image registration algorithms including Lucchese algorithm,Vandewalle algorithm and Keren algorithm,we experimentally compare the relative merits of these registration algorithms in terms of registration accuracy and noise ***,we experimentally compare four image reconstruction methods:projection onto convex sets method(POCS),iterative back-projection method(IBP),robust super resolution(Robust SR) and structure-adaptive normalized convolution(Structure-Adaptive NC),mainly in terms of Peak Signal to Noise Ratio(PSNR),in which salt and pepper noise is added in the low resolution *** is clearly demonstrated that the combination of Keren algorithm and Structure-Adaptive NC can achieve the best performance regarding the Lena image.

关键词： image super-resolution reconstruction image registration Reconstruction algorithm Experimental comparison

来源：评论

学校读者我要写书评

暂无评论

Software Monitoring System for Register Marker Detection 8

Software Monitoring System for Register Marker Detection

引用

8th International Conference on Ubiquitous and Future Networks (ICUFN)

作者： Kim, Sang-Chul Kookmin Univ Sch Comp Sci 77 Chongnung Ro Seoul 136702 South Korea

ISBN: (纸本)9781467399913

This paper proposes an image-processing algorithm for register marker detection in a roll-to-roll (R2R) system. Recently, R2R systems have been receiving considerable international attention from researchers because of their ability to print electronic devices on flexible substrates. During such printing, an R2R system must adjust its printing position by continuously checking the positions of the markers in order to ensure correct positioning of the printing roll. By acquiring the differences in the position information between referenced and printed marker positions, an R2R system can control the printing position by adjusting the printing roll speed. To capture and analyze referenced and printed marker images, an R2R system uses charge-coupled device (CCD) cameras and their image-processing algorithms. Therefore, it can be said that the productivity and accuracy of an R2R system depends entirely on the quality of the CCD cameras and their image-processing algorithms. This study develops an image-processing algorithm in which different markers are detected and processed.

关键词： Register Marker Detection Roll-to-Roll Software Imaging processing Software Monitoring System

来源：评论

学校读者我要写书评

暂无评论

Large Scale Retrieval and Generation of image Descriptions

引用

INTERNATIONAL JOURNAL OF COMPUTER VISION 2016年第1期119卷 46-59页

作者： Ordonez, Vicente Han, Xufeng Kuznetsova, Polina Kulkarni, Girish Mitchell, Margaret Yamaguchi, Kota Stratos, Karl Goyal, Amit Dodge, Jesse Mensch, Alyssa Daume, Hal, III Berg, Alexander C. Choi, Yejin Berg, Tamara L. Univ N Carolina Chapel Hill NC 27599 USA SUNY Stony Brook Stony Brook NY 11794 USA Microsoft Res Redmond WA USA Tohoku Univ Sendai Miyagi Japan Columbia Univ New York NY USA Yahoo Labs Sunnyvale CA USA Carnegie Mellon Univ Pittsburgh PA 15213 USA Univ Penn Philadelphia PA 19104 USA Univ Maryland College Pk MD 20742 USA Univ Washington Seattle WA 98195 USA

What is the story of an image? What is the relationship between pictures, language, and information we can extract using state of the art computational recognition systems? In an attempt to address both of these questions, we explore methods for retrieving and generating natural language descriptions for images. Ideally, we would like our generated textual descriptions (captions) to both sound like a person wrote them, and also remain true to the image content. To do this we develop data-driven approaches for image description generation, using retrieval-based techniques to gather either: (a) whole captions associated with a visually similar image, or (b) relevant bits of text (phrases) from a large collection of image + description pairs. In the case of (b), we develop optimization algorithms to merge the retrieved phrases into valid natural language sentences. The end result is two simple, but effective, methods for harnessing the power of big data to produce image captions that are altogether more general, relevant, and human-like than previous attempts.

关键词： Retrieval image description Data driven Big data Natural language processing

来源：评论

学校读者我要写书评

暂无评论

Phase Adjustment for Polarimetric ISAR with Compressive Sensing

引用

IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC systems 2016年第4期52卷 1592-1606页

作者： Wu, Min Zhang, Lei Xia, Xiang-Gen Xing, Meng-Dao Xidian Univ Natl Lab Radar Signal Proc 2 Taibai Rd Xian 710071 Shaanxi Peoples R China Univ Delaware Elect & Comp Engn 311 Evans Hall Newark DE 19716 USA

Polarimetric inverse synthetic aperture radar (pol-ISAR) imaging exploits extra scattering information about a target compared with single pol-ISAR. Target description and classification can be improved by incorporating pol-ISAR images. One of the most critical problems in ISAR imaging is accurate motion compensation, specifically for noncooperative targets. Due to the imperfection of coarse motion compensation, phase-adjustment methods are further developed to eliminate the residual phase errors. Unlike taking the contrast or entropy as the measurements in the existing pol-ISAR phase-adjustment algorithms, this paper exploits the sparsity of the scattering centers to correct the phase errors and simultaneously proposes an unambiguous image formation with the sparse aperture signal. The superiority of this algorithm is that the global information of full pol-ISAR images can be properly incorporated to compensate the phase errors and suppress the noise effectively. Experimental results indicate the effectiveness of the proposed method.

关键词： Imaging Motion compensation Radar imaging Scattering Signal processing algorithms Signal resolution

来源：评论

学校读者我要写书评

暂无评论

Tolerant testers of image properties 43

Tolerant testers of image properties

引用

43rd International Colloquium on Automata, Languages, and Programming, ICALP 2016

作者： Berman, Piotr Murzabulatov, Meiram Raskhodnikova, Sofya Pennsylvania State University University Park United States

ISBN: (纸本)9783959770132

We initiate a systematic study of tolerant testers of image properties or, equivalently, algorithms that approximate the distance from a given image to the desired property (that is, the smallest fraction of pixels that need to change in the image to ensure that the image satisfies the desired property). image processing is a particularly compelling area of applications for sublinear-time algorithms and, specifically, property testing. However, for testing algorithms to reach their full potential in image processing, they have to be tolerant, which allows them to be resilient to noise. Prior to this work, only one tolerant testing algorithm for an image property (image partitioning) has been published. We design efficient approximation algorithms for the following fundamental questions: What fraction of pixels have to be changed in an image so that it becomes a half-plane? a representation of a convex object? a representation of a connected object? More precisely, our algorithms approximate the distance to three basic properties (being a half-plane, convexity, and connectedness) within a small additive error ϵ, after reading a number of pixels polynomial in 1/- and independent of the size of the image. The running time of the testers for half-plane and convexity is also polynomial in 1/ϵ. Tolerant testers for these three properties were not investigated previously. For convexity and connectedness, even the existence of distance approximation algorithms with query complexity independent of the input size is not implied by previous work. (It does not follow from the VC-dimension bounds, since VC dimension of convexity and connectedness, even in two dimensions, depends on the input size. It also does not follow from the existence of non-tolerant testers.) Our algorithms require very simple access to the input: uniform random samples for the half-plane property and convexity, and samples from uniformly random blocks for connectedness. However, the analysis of the algori

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Colour Constancy Using Sub-Blocks of the image 9

Colour Constancy Using Sub-Blocks of the Image

引用

International Conference on Signals and Electronic systems (ICSES)

作者： Hussain, Md. Akmol Akbari, Akbar Sheikh Mallik, Bruhanth Leeds Beckett Univ Sch Comp Creat Technol & Engn Leeds W Yorkshire England

ISBN: (纸本)9781509026678

Colour constancy is the ability to measure the colour of objects independent of the light source, while colour casting is the presence of unwanted colour in digital images. Colour casting significantly affects the performance of image processing algorithms such as image segmentation and object recognition. The presence of large uniform background within the image considerably deteriorates the performance of many state of the art colour constancy algorithms. This paper presents a colour constancy method using the sub-blocks of the image to alleviate the effect of large uniform colour area of the scene. The proposed method divides the input image into a number of nonoverlapping blocks, and Average Absolute Difference (AAD) value of each block colour component is calculated. The blocks with AAD greater than threshold values, which are empirically determined for each colour component, are considered to have sufficient colour information. The selected blocks are then used to determine the scaling factors to achieve achromatic values for the input image colour components. Comparing the performance of the proposed technique with the state of the art methods using images from three datasets shows that the proposed method outperforms the state of the art techniques in the presence of large uniform colour patches.

关键词： colour constancy colour balancing uniform colour average absolute difference

来源：评论

学校读者我要写书评

暂无评论

Combined Imaging System for Taking Facial Portraits in Visible and Thermal Spectra

引用

8th International Conference on image processing and Communications (IP and C)

作者： Jasinski, Piotr Forczmanski, Pawel West Pomeranian Univ Technol Fac Comp Sci & Informat Technol Zolnierska Str 52 PL-71210 Szczecin Poland

ISBN: (纸本)9783319238142;9783319238135

This work explores the subject of thermal imagery in the context of face recognition. Its aim is to create a database of facial images taken in both thermal and visual domains. To achieve this, a specialized photographic stand was designed, which allows simultaneous capture of images from IR thermal camera and SLR digital camera. To ensure precision, stability and fluency of photographic sessions, a Matlab application has been developed, through which it is possible to remotely control both devices, as well as automatically download captured images onto a hard drive and save them within an organized folder structure. Additionally, several image fusion techniques have been implemented in order to effectively combine visual and thermal data for use in face recognition algorithms.

关键词： Thermovision Biometrics Face Database image fusion

来源：评论

学校读者我要写书评

暂无评论

Development Prospects of the Visual Data Compression Technologies and Advantages of New Approaches 1

引用

9th KES International Conference on Intelligent Interactive Multimedia systems and Services (IIMSS)

作者： Vostrikov, Anton Sergeev, Mikhail St Petersburg State Univ Aerosp Instrumentat Dept Comp Syst & Networks 67 Bolshaya Morskaya St St Petersburg 190000 Russia

ISBN: (数字)9783319393452

ISBN: (纸本)9783319393452;9783319393445

The static image and video information compression algorithms development over the last 15-20 years, as well as standardized and non-standardized formats for data storage and transmission have been analyzed;the main factors affecting the further development of approaches that eliminate the redundancy of transmitted and stored visual information have been studied. The conclusion on the current prospects for the development of image compression technologies has been made. New approaches that use new low-level quasi-orthogonal matrices as transform operators have been defined. The advantages of such approaches opening new fundamentally different opportunities in the field of applied processing of digital visual information have been identified and presented.

关键词： image compression Video compression Protection against unauthorized access M-matrices Audiovisual information coding Metadata

来源：评论

学校读者我要写书评

暂无评论

Color Space Optimization for Lacunarity Method in Analysis of Papanicolaou Smears

引用

8th International Conference on image processing and Communications (IP and C)

作者： Oszutowska-Mazurek, Dorota Mazurek, Przemyslaw Sycz, Kinga Waker-Wojciuk, Grazyna Higher Sch Technol & Econ Szczecin Klonowica 14 St PL-71244 Szczecin Poland West Pomeranian Univ Technol Dept Signal Proc & Multimedia Engn 26 Kwietnia 10 St PL-71126 Szczecin Poland Independent Publ Voivodeship United Hosp Dept Pathomorphol Arkonska 4 St PL-71455 Szczecin Poland

ISBN: (纸本)9783319238142;9783319238135

There are numerous cells nuclei analysis algorithms. The lacunarity is the texture analysis algorithm and could be applied for binary or grayscale images of cells nuclei. The cells in Papanicolaou process are stained so numerous conversions to grayscale or binary images are possible. The optimization of RGB color space using weights is proposed for polynomial based analysis using lacunarity and the cell area of binary image. Obtained results show significant differences for best and worst cases for the number of cells of atypical and correct classes with similar cells area.

关键词： Lacunarity image analysis Cytology

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：