检索结果-内蒙古大学图书馆

Research on image compression algorithm based on the biorthogonal invariant set multiwavelet

Journal of Computational Information systems 2015年第16期11卷 5873-5880页

作者： Li, Yongjun Li, Yunsong Liu, Weijia State Key Lab. of Integrated Service Networks Xidian University Xi'an China Joint Laboratory of High Speed Multi-Source Image Coding and Processing Xidian University Xi'an China

On the basis of the theory of the biorthogonal invariant set multiwavelets (BISM) which is established by Micchelli and Xu, a biorthogonal invariant set multi-wavelets (BISM) filter is designed and the algorithms of decomposition and reconstruction of this filter are given in this paper, and it has many characteristics, such as symmetry, compact support, orthogonality and low complexity. In this filter, the self-affine triangle domain is as support interval, and constant function is as scaling function. Advantages such as low algorithm complexity, the energy and entropy in high concentration after transformation, no blocking effect to facilitate parallel computing are analyzed when the biorthogonal invariant sets multiwavelet (BISM) filters are used image compression. Finally, the validity of image compression algorithm based on biorthogonal invariant set multiwavelet is verified by the approximate JPEG2000 framework. © 2015 by Binary Information Press

关键词： image compression

来源：评论

学校读者我要写书评

暂无评论

UAV-based forest fire detection and tracking using image processing techniques

UAV-based forest fire detection and tracking using image pro...

引用

International Conference on Unmanned Aircraft systems (ICUAS)

作者： Chi Yuan Zhixiang Liu Youmin Zhang Department of Mechanical and Industrial Engineering Concordia University Montreal Quebec Canada Department of Information and Control Engineering Xi'an University of Technology Xi'an Shaanxi China Department of Mechanical and Industrial Engineering Concordia University Quebec Canada

ISBN: (纸本)9781479960118

In this paper, an unmanned aerial vehicle (UAV) based forest fire detection and tracking method is proposed. Firstly, a brief illustration of UAV-based forest fire detection and tracking system is presented. Then, a set of forest fire detection and tracking algorithms are developed including median filtering, color space conversion, Otsu threshold segmentation, morphological operations, and blob counter. The basic idea of the proposed method is to adopt the channel “a” in Lab color model to extract fire-pixels by making use of chromatic features of fire. Numerous experimental validations are carried out, and the experimental results show that the proposed methodology can effectively extract the fire pixels and track the fire zone.

关键词： Fires image color analysis image segmentation Morphological operations Feature extraction Real-time systems

来源：评论

学校读者我要写书评

暂无评论

An efficient and robust rotation invariant descriptor

An efficient and robust rotation invariant descriptor

引用

Congress on image and Signal processing, CISP

作者： Dongmiao xi Yankui Sun Jinghua Miao Yongge Wang Department of Computer Science and Technology Tsinghua University Beijing China School of Mathematics and Systems Science Beihang University Beijing China

A novel scheme to calculate feature descriptors with rotation invariance was proposed in this paper. Unlike traditional methods of computing feature orientations and descriptors using a single sampling pattern, we calculate the orientation of a feature point with one sampling pattern and generate its descriptor with another one. Based on this idea, we present a method to generate a rotation invariant descriptor using the sampling patterns of FREAK and BRIEF. The experimental results on image matching show that our method is not only invariant to image rotation but also robust to many other situations such as image blur, viewpoint change, illumination change and JEPG compression. At the same time, the proposed method performs competitively with BRISK and FREAK in computational time.

关键词： image matching Lighting image coding Feature extraction Detectors Robustness Signal processing algorithms

来源：评论

学校读者我要写书评

暂无评论

Research on image denoising using patch-based singular value decomposition

Research on image denoising using patch-based singular value...

引用

Canadian Conference on Electrical and Computer Engineering (CCECE)

作者： Han Liu Yue Zhao Lili Liang Yingmin Yi School of Automation and Information Engineering Xi'an University of Technology Xi'an China

ISBN: (纸本)9781479958306

This paper presents an efficient patch-based image denoising scheme by using singular value decomposition (SVD). In this scheme, similar image patches are simply grouped together from a noisy image. For a better sparse representation of these similar patches, we firstly utilize the 2D SVD to reveal the essential features of each individual patch and then the 1D SVD to exploit the correlation between similar patches. By doing so, the image features can be well preserved when attenuating noise by the shrinkage of transform coefficients. In order to improve denoising performance, the proposed scheme is employed once again. Besides that the similar patch grouping and the basis calculation of 2D SVD are performed from the first-stage estimated image, a fixed orthogonal transform instead of 1D SVD is applied to remove the redundancy shared by similar patches. Experimental results show that the proposed two-stage denoising scheme achieves more competitive performance than the state-of-the-art denoising algorithms.

关键词： Signal processing Handheld computers Decision support systems Conferences Correlation Pattern analysis

来源：评论

学校读者我要写书评

暂无评论

Learning multiple linear mappings for efficient single image super-resolution

引用

IEEE Transactions on image processing 2015年第3期24卷 846-861页

作者： Zhang, Kaibing Tao, Dacheng Gao, xinbo Li, Xuelong xiong, Zenggang State Key Laboratory of Integrated Services Networks School of Electronic Engineering Xidian University Xi'an710071 China School of Computer and Information Science Hubei Engineering University Xiaogan432000 China Centre for Quantum Computation and Intelligent Systems Faculty of Engineering and Information Technology University of Technology SydneyNSW2007 Australia State Key Laboratory of Transient Optics and Photonics Chinese Academy of Sciences Xi'an710119 China

Example learning-based superresolution (SR) algorithms show promise for restoring a high-resolution (HR) image from a single low-resolution (LR) input. The most popular approaches, however, are either time-or space-intensive, which limits their practical applications in many resource-limited settings. In this paper, we propose a novel computationally efficient single image SR method that learns multiple linear mappings (MLM) to directly transform LR feature subspaces into HR subspaces. In particular, we first partition the large nonlinear feature space of LR images into a cluster of linear subspaces. Multiple LR subdictionaries are then learned, followed by inferring the corresponding HR subdictionaries based on the assumption that the LR-HR features share the same representation coefficients. We establish MLM from the input LR features to the desired HR outputs in order to achieve fast yet stable SR recovery. Furthermore, in order to suppress displeasing artifacts generated by the MLM-based method, we apply a fast nonlocal means algorithm to construct a simple yet effective similarity-based regularization term for SR enhancement. Experimental results indicate that our approach is both quantitatively and qualitatively superior to other application-oriented SR methods, while maintaining relatively low time and space complexity. © 1992-2012 IEEE.

关键词： Mathematical transformations

来源：评论

学校读者我要写书评

暂无评论

Compressive tracking based on random channel haar-like feature

Compressive tracking based on random channel haar-like featu...

引用

International Conference on Intelligent Control and Information processing (ICICIP)

作者： Junyan Chen Ying Liu Na Li Zhiquan Guo School of Communication and Information Engineering Xi'an University of Post and Telecommunications Xi’an China

ISBN: (纸本)9781479917181

Compressive tracking based on random channel Haar-like feature (RCCT) is proposed in this paper to improve tracking accuracy. Firstly, the color video frame is converted into grayscale image for tracking in real-time compressive tracking (CT), which may lose some information. Therefore, Haar-like features with random position and size are generated from three channels (RGB with random), represent the target better. What's more, it costs much time to detect new target round the position of the target in the current frame in the CT algorithm, and causes the target to drift when the speed of the target increases suddenly. Searching the new target in the vicinity of prediction target is proposed to reduce search time and to avoid missing the target. We have done experiments with large number of public data sets. Experimental results show that the RCCT algorithm reduces the average error of the target center compared with CT algorithm and other improved algorithms, and it performs favorably at the circumstances of the change of illumination and target position.

关键词： Yttrium Target tracking Compressed sensing Decision support systems Statistical analysis

来源：评论

学校读者我要写书评

暂无评论

Face sketch synthesis from a single photo-sketch pair

引用

IEEE Transactions on Circuits and systems for Video Technology 2015年第99期PP卷

作者： Zhang, Shengchuan Gao, xinbo Wang, Nannan Li, Jie Video and Image Processing System Laboratory School of Electronic Engineering Xidian University Xi'an Shaanxi710071 China State Key Laboratory of Integrated Services Networks School of Electronic Engineering Xidian University Xi'an Shaanxi710071 China

Face sketch synthesis is crucial in many practical applications, such as digital entertainment and law enforcement. Previous methods relying on many photo-sketch pairs have made great progress. State-of-the-art face sketch synthesis algorithms adopt Bayesian Inference (BI) (e.g. Markov Random Fields) to select local sketch patches around corresponding position from a set of training data. However, these methods have two limitations: firstly, they depend on many training photosketch pairs; secondly, they cannot tackle non-facial factors (e.g. hairpins, glasses, backgrounds and image size) if these factors are excluded in training data. In this paper, we propose a novel face sketch synthesis method that is capable of handling non-facial factors only using a single photo-sketch pair from coarse to fine. Our method proposes a cascaded image synthesis (CIS) strategy and integrates sparse representation based greedy search (SRGS) and BI for face sketch synthesis. We first apply SRGS to select candidate sketch patches from the whole training photo-sketch pairs sampled from the only photo-sketch pair. We then employ BI to estimate an initial sketch. Afterwards, the input photo and the estimated initial sketch are taken as an additional photosketch pair for training. Finally, we adopt CIS with given two photo-sketch pairs to further improve the quality of the initial sketch. Experimental results on several databases demonstrate that our algorithm outperforms state-of-the-art methods. © 2015 IEEE.

关键词： image processing

来源：评论

学校读者我要写书评

暂无评论

Bio-inspired Computational Intelligence and its Engineering Applications

Bio-inspired Computational Intelligence and its Engineering ...

引用

2015 IEEE Advanced Information Technology,Electronic and Automation Control Conference(IAEAC 2015)

作者： Guojian Cheng E&E School of Xi'an Peihua University CIDOFI Computational Intelligence for Digital Oil Fields School of Computer ScienceXi'an Shiyou University

The main branches of Bio-inspired Computational Intelligence(BCI) include artificial neural networks(to understand how the brain of living organisms works,and to design efficient algorithms based on the principles of how the human brain processes information),evolutionary computation(a computational system based on the notion of simulated *** comprises a constant- or variable-size population of individuals,a fitness criterion,and genetically inspired operators that produce the next generation from the current one),swarm intelligence(defined as the problem solving behavior that emerges from the interaction of individual agents which communicate with other agents by acting on their local environments.),artificial immune system(a computational system inspired by the natural immune systems of biological organisms.),artificial life(an agent based system which is used to study the emergent properties of societies of agents),DNA computing(a form of parallel computing in that it takes advantage of the many different molecules of DNA to try many different possibilities at once),*** talk will give an overview BCI and their engineering applications in the fields of image processing,computer vision and petroleum engineering such as reservoir simulation,geology modeling,oil &gas prediction.

关键词： Artificial neural networks Evolutionary computation Swarm intelligence Artificial immune systems image processing Computer vision Petroleum reservoir modeling

来源：评论

学校读者我要写书评

暂无评论

A HIGH-CONTRAST IMAGING ALGORITHM: OPTIMIZED image ROTATION AND SUBTRACTION

引用

ASTROPHYSICAL JOURNAL 2015年第1期802卷 12-12页

作者： Dou, Jiangpei Ren, Deqing Zhao, Gang Zhang, xi Chen, Rui Zhu, Yongtian Chinese Acad Sci Natl Astron Observat Nanjing Inst Astron Opt & Technol Nanjing 210042 Jiangsu Peoples R China Chinese Acad Sci Key Lab Astron Opt & Technol Nanjing Inst Astron Opt & Technol Nanjing 210042 Jiangsu Peoples R China Calif State Univ Northridge Dept Phys & Astron Northridge CA 91330 USA

image Rotation and Subtraction (IRS) is a high-contrast imaging technique that can be used to suppress the speckle noise and facilitate the direct detection of exoplanets. IRS is different from Angular Differential Imaging (ADI), in that it will subtract a copy of the image with 180 degrees rotated around its point-spread function (PSF) center, rather than the subtraction of the median of all of the PSF images. Since the planet itself will be rotated to the other side of the PSF, IRS does not suffer from planet self-subtraction. In this paper, we have introduced an optimization algorithm to IRS (OIRS), that can provide an extra contrast gain at small angular separations. The performance of OIRS has been demonstrated with ADI data. We then made a comparison of the signal-to-noise ratio (S/N) achieved by algorithms of locally optimized combinations of images and OIRS. Finally, we found that the OIRS algorithm can deliver a better S/N for small angular separations.

关键词： instrumentation: adaptive optics planetary systems stars: imaging techniques: image processing

来源：评论

学校读者我要写书评

暂无评论

Trans-PET: Towards plug and imaging coincidence measurement

Trans-PET: Towards plug and imaging coincidence measurement

引用

IEEE Symposium on Nuclear Science (NSS/MIC)

作者： Yuqing Liu Daoming xi Chien-Min Kao Rong Yuan Shuai Wang Chung-Yi Li xiao Liang Bingxuan Li Jun Zhu Heejong Kim Peng xiao Qingguo xie Biomedical Engineering Department Huazhong University of Science and Technology Wuhan Hubei Raycan Technology Co. Ltd(Suzhou) Suzhou Jiangsu Department of Radiology University of Chicago Chicago Illinois Department of Electronic Engineering Chang Gung University Taoyuan Taiwan

Recently, there is growing interest in directly digitizing the scintillation pulses in PET detectors. With digital pulse samples, in principle one can apply nontrivial signal analysis software algorithms to either yield better detection performance or more flexibility in detector design. Previously, we have proposed the MVT method for direct scintillation pulse sampling and developed several kinds of digital PET detectors named basic detector modules (BDM). These highly modular detectors output the resulting MVT samples in a uniform data format via a RJ45 connector while adopting the UDP protocol. For PET systems based on these detectors, single-event processing and coincidence filtering are all carried out by softwares. As a result, new processing/filtering methods can be readily updated or upgraded. Therefore, we wish to provide a BDM based design architecture to enable quick setup of a PET system. We use two system geometry definition files, named the SG file1 and SG file2, to define the types and number of the BDMs employed, as well as their positions and orientations. The MVT data processing like single event information retrieving, coincidence filtering, data format conversion, image reconstruction and data/image analysis are carried out by separate software modules with standard input and output definitions. Those software modules can be conveniently modified or replaced, and be put into cascade chains to provide desired functions. In this work, we present such a BDM based system design architecture, as well as the BDMs newly developed. As an example, a panel PET system adopting this architecture with 12 BDMs is shown with phantom imaging result.

关键词： Positron emission tomography Detectors Software Computer architecture image reconstruction Timing

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：