检索结果-内蒙古大学图书馆

25th signal processing and Communications Applications conference (SIU)

作者： Sarica, Damla Demirel, Omer Burak Saritas, Emine Ulku Bilkent Univ Elekt & Elekt Muhendisligi Bolumu Ankara Turkey Bilkent Univ UMRAM Ankara Turkey Bilkent Univ Sinirbilim Programi Sabuncu Beyin Arastirmalari Merkezi Ankara Turkey

ISBN: (纸本)9781509064946

Magnetic Particle Imaging (MPI) is a new imaging technology that images the spatial distribution of iron oxide nanoparticles. Since the magnetic field strength that can be safely applied in MPI is limited, the field-of-view (FOV) must be divided into partial FOVs. Because the excitation magnetic field causes direct feedthrough on the receiver coil, the excitation frequency must be filtered out of the MPI signal. During this process, the nanoparticle signal at the same frequency is also lost, as a result of which each partial FOV experiences different levels of DC shift. In the standard MPI image reconstruction, these DC shifts are calculated from neighboring overlapping partial FOVs. Here, we propose a novel method that directly reconstructs the MPI image from the calculated DC shift values. Especially in the case of low bandwidth signal acquisitions, this method yields higher resolution images when compared to the standard method. The simulation results at various signal-to-noise ratios (SNR) show that the proposed method produces 6-8 dB increase in peak SNR and yields images that closely match the ideal image.

关键词： Magnetic Particle Imaging (MPI) direct feedthrough DC shift image image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Case Study for Graph signal Denoising by Graph Structure Similarity 2

Case Study for Graph Signal Denoising by Graph Structure Sim...

引用

2nd International conference on image, Vision and Computing (ICIVC)

作者： Song, Dao-Bang Zhang, Jiu-Wen Zhou, Jing Lanzhou Univ Sch Informat Sci & Engn Lanzhou Gansu Peoples R China

ISBN: (纸本)9781509062386

We study the denoising performance of several graph wavelet filter banks and image modeling with graph to enhance understanding of the relationship between graph signals and underlying structure. We design a new metric for measuring graph structure similarity (GSSIM) to evaluate those methods. GSSIM is positively related to PSNR as an index of corrupted signal with an additive Gaussian noise in the references and it is aware of graph structure. Subgraph-Based filter banks are superior to others in graph signal denoising. We introduce the idea of group-based approaches by removing edges between different groups, a set of communities with similar average. It can improve the signal to noise ratio substantially and reduce the high frequency loss. We demonstrate GSSIM is promise through intuitive examples. Group-based analysis improves the denoising effect of all the methods studied.

关键词： graph structure similarity community detection graph signal processing denoising image modeling

来源：评论

学校读者我要写书评

暂无评论

LABEL PROPAGATION BASED SALIENCY DETECTION VIA GRAPH design 24

LABEL PROPAGATION BASED SALIENCY DETECTION VIA GRAPH DESIGN

引用

24th IEEE International conference on image processing (ICIP)

作者： Zhang, Tianhao Zhou, Yuan Huo, Shuwei Hou, Chunping Tianjin Univ Sch Elect & Informat Engn Tianjin Peoples R China Princeton Univ Dept Elect Engn Princeton NJ 08544 USA

ISBN: (纸本)9781509021758

Saliency detection has been widely used as the pre-processing of the computer-vision tasks. Existing propagation based saliency detection methods simply select a k-regular graph for saliency propagation, which usually leads to the mistaken highlighting of the long-range smooth background regions. In this paper, we design a novel graph for label propagation based saliency detection by considering the local consistency and the global symmetry of the image scene and updating the graph model based on smoothness assumption and cluster assumption. Then, we label the reliable seeds and propagate the saliency value through the designed graph. On two widely used large open benchmark data sets, the proposed method significantly outperforms thirteen state-of-the-arts under either quantitative or qualitative evaluation.

关键词： Saliency detection Label propagation Graph construction

来源：评论

学校读者我要写书评

暂无评论

Compressive Video Sensing

引用

IEEE signal processing MAGAZINE 2017年第1期34卷 52-66页

作者： Baraniuk, Richard G. Goldstein, Tom Sankaranarayanan, Aswin C. Studer, Christoph Veeraraghavan, Ashok Wakin, Michael B. Rice Univ Elect & Comp Engn Houston TX 77005 USA OpenStax Houston TX USA Univ Maryland Comp Sci College Pk MD 20742 USA Rice Univ Digital Signal Proc Grp Houston TX USA Carnegie Mellon Univ ECE Dept Pittsburgh PA 15213 USA Swiss Fed Inst Technol Zurich Switzerland Rice Univ Houston TX USA Cornell Univ Sch Elect & Comp Engn Ithaca NY USA Rice Univ Elect & Comp Engn Computat Imaging & Vis Lab Houston TX USA Mitsubishi Elect Res Labs Cambridge MA USA Colorado Sch Mines Dept Elect Engn & Comp Sci Golden CO 80401 USA CALTECH Pasadena CA 91125 USA Univ Michigan Ann Arbor MI 48109 USA

The design of conventional sensors is based primarily on the Shannon?Nyquist sampling theorem, which states that a signal of bandwidth W Hz is fully determined by its discrete time samples provided the sampling rate exceeds 2 W samples per second. For discrete time signals, the Shannon?Nyquist theorem has a very simple interpretation: the number of data samples must be at least as large as the dimensionality of the signal being sampled and recovered. This important result enables signal processing in the discrete time domain without any loss of information. However, in an increasing number of applications, the Shannon-Nyquist sampling theorem dictates an unnecessary and often prohibitively high sampling rate (see “What Is the Nyquist Rate of a Video signal?”). As a motivating example, the high resolution of the image sensor hardware in modern cameras reflects the large amount of data sensed to capture an image. A 10-megapixel camera, in effect, takes 10 million measurements of the scene. Yet, almost immediately after acquisition, redundancies in the image are exploited to compress the acquired data significantly, often at compression ratios of 100:1 for visualization and even higher for detection and classification tasks. This example suggests immense wastage in the overall design of conventional cameras.

关键词： Sensors Streaming media Spatial resolution Cameras Bandwidth Compression algorithms

来源：评论

学校读者我要写书评

暂无评论

COMPRESSIVE INFORMATION ACQUISITION WITH HARDWARE IMPAIRMENTS AND CONSTRAINTS: A CASE STUDY

COMPRESSIVE INFORMATION ACQUISITION WITH HARDWARE IMPAIRMENT...

引用

IEEE International conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Gopalakrishnan, S. Moy, T. Madhow, U. Verma, N. Univ Calif Santa Barbara Dept ECE Santa Barbara CA 93106 USA Princeton Univ Dept EE Princeton NJ 08544 USA

ISBN: (纸本)9781509041176

Compressive information acquisition is a natural approach for low-power hardware front ends, since most natural signals are sparse in some basis. Key design questions include the impact of hardware impairments (e.g., nonlinearities) and constraints (e.g., spatially localized computations) on the fidelity of information acquisition. Our goal in this paper is to obtain specific insights into such issues through modeling of a Large Area Electronics (LAE)-based image acquisition system. We show that compressive infonnation acquisition is robust to stochastic nonlinearities, and that appropriately designed spatially localized computations are effective, by evaluating the performance of reconstruction and classification based on the information acquired.

关键词： Compressed sensing stochastic nonlinearities image acquisition low-power front ends hardware impairments

来源：评论

学校读者我要写书评

暂无评论

TEO Separated AM-FM Components for Identification of Apnea EEG signals 2

TEO Separated AM-FM Components for Identification of Apnea E...

引用

2nd IEEE International conference on signal and image processing (ICSIP)

作者： Taran, Sachin Bajaj, Varun Sharma, Dheeraj PDPM Indian Inst Informat Technol Design & Mfg Ja Discipline Elect & Commun Engn Jabalpur 482005 India

ISBN: (纸本)9781538609699

Sleep apnea event is occurred due to hindrance in respiration, which is most commonly observed in children and adults. It is noticed that, if this event sustained for long time it will cause several brain and heart disorders. Diagnoses of such disorders require identification of apnea event. Recently, electroencephalogram (EEG) signals show proficiency for assessing the sleep quality and detection of apnea event. In this work, amplitude modulated (AM) and frequency modulated (FM) components based features extracted from EEG signals, are using for identification of sleep apnea event. Teager energy operator (TEO) is uses for separation of AM-FM components but it requires band limited signals. The nature of EEG is highly non-stationary, so an adaptive empirical mode decomposition technique is applied, which convert the non-stationary EEG signals into band limited intrinsic mode functions (IMF). TEO separates each IMF into AM-FM components. The extracted features from separated components are applied as input to least square support vector machine (LS-SVM) classifier and obtained better performance parameters for identification of apnea event compared to existing methods.

关键词： electroencephalogram signal teager energy operator empirical mode decomposition least square support vector machine

来源：评论

学校读者我要写书评

暂无评论

Real Time image processing Based Obstacle Avoidance and Navigation System for Autonomous Wheelchair Application 9

Real Time Image Processing Based Obstacle Avoidance and Navi...

引用

9th Annual Summit and conference of the Asia-Pacific-signal-and-Information-processing-Association (APSIPA ASC)

作者： Lee, Yoon Ket Lim, Jay Ming Eu, Kok Seng Goh, Yeh Huann Tew, Yiqi Tunku Abdul Rahman Univ Coll Kuala Lumpur Malaysia

ISBN: (纸本)9781538615423

Wheelchairs have played an important role in both disabled young people and adults not only in term of physically but also psychologically. The idea of electrical wheelchairs has been brought up and carried out as to help these disabled people to be more independent instead of always depending caregivers. However, electronics wheelchairs are not enabling for every patient such as people who have lost mobility due to brain injury or loss of limbs. Thus, the idea of Smart Wheelchair or Autonomous Wheelchair where it is intelligent enough to provide navigation with a series of navigation assistances has brought up to the table. The purpose of this project is to design a navigation system and an obstacle avoidance system for an autonomous wheelchair application. The obstacle detection system is done merely using the camera sensor with the knowledge of image processing. The techniques used are including Canny Edge Detection, Erosion and so on where algorithms are developed to identify and detect the obstacle. The navigation system is performed with the use of compass sensors where the compass calibration, compass reading and compass value comparison are done to ensure the autonomous wheelchair move in a correct direction towards the targeted destination. Enhancement of autonomous wheelchair with Internet connectivity can be achieved using our designed system for enabling Internet of Things (IoT) application on independent disable people.

关键词： Wheelchairs Navigation Compass Speech recognition image processing Cameras Software

来源：评论

学校读者我要写书评

暂无评论

colour image Watermarking based on Wavelet and QR Decomposition 25

colour Image Watermarking based on Wavelet and QR Decomposit...

引用

25th signal processing and Communications Applications conference (SIU)

作者： Rasti, Pejman Anbarjafari, Gholamreza Demirel, Hasan Univ Tartu Inst Technol ICV Res Grp EE-50411 Tartu Estonia Eastern Mediterranean Univ Dept Elect & Elect Engn Famagusta Kktc Turkey

ISBN: (纸本)9781509064946

In this work, a new image watermarking algorithm on colour images is proposed. The proposed algorithm divides a cover image into three colour bands of red, green and blue. Then the following tasks are done on all three channels separately. First, Each colour band is divided into patches of small sizes then the entropy of each patch is calculated. At this step a threshold is found based on the average entropy of all patches and following is applied to all patches which have entropy lower than the threshold. A wavelet representation of each patch are given by applying a discrete wavelet transform. Then Singular value decomposition, orthogonal-triangular decomposition, and a chirp z-transform are used to embed a watermark on the cover image. Several signal processing attacks are applied on watermarked images in order to robustness of the algorithm. The Proposed algorithm is compared with one conventional and two state-of-the-art algorithms. Experimental results show superiority of the proposed algorithm compare with other algorithm in the area of image watermarking.

关键词： digital image Watermarking DWT CZT Entropy SVD QR

来源：评论

学校读者我要写书评

暂无评论

Group Metropolis Sampling 25

Group Metropolis Sampling

引用

25th European signal processing conference (EUSIPCO)

作者： Martino, Luca Elvira, Victor Camps-Valls, Gustau Univ Valencia Image Proc Lab Valencia Spain IMT Lille Douai CRISTAL UMR 9189 Villeneuve Dascq France

ISBN: (纸本)9780992862671

Monte Carlo (MC) methods are widely used for Bayesian inference and optimization in statistics, signal processing and machine learning. Two well-known class of MC methods are the Importance Sampling (IS) techniques and the Markov Chain Monte Carlo (MCMC) algorithms. In this work, we introduce the Group Importance Sampling (GIS) framework where different sets of weighted samples are properly summarized with one summary particle and one summary weight. GIS facilitates the design of novel efficient MC techniques. For instance, we present the Group Metropolis Sampling (GMS) algorithm which produces a Markov chain of sets of weighted samples. GMS in general outperforms other multiple try schemes as shown by means of numerical simulations.

关键词： Bayesian inference Importance Sampling Markov Chain Monte Carlo (MCMC) Gaussian Processes (GP)

来源：评论

学校读者我要写书评

暂无评论

Vegetation Detection with Spatial Segmentation and Spectral Indices 25

Vegetation Detection with Spatial Segmentation and Spectral ...

引用

25th signal processing and Communications Applications conference (SIU)

作者： Demirel, Berkan Esin, Yunus Emre Ozdil, Omer HAVELSAN AS Algilayicilar Sinyal &e Goruntu Isleme Grubu Ankara Turkey

ISBN: (纸本)9781509064946

This paper proposes a new vegetation detection approach using spatial segmentation and vegetation indices. For this purpose, hyperspectral images are segmented by using the previously trained spatial segmentation model. Thereafter, grape plants are tried to be detected in hyperspectral data by using the obtained segments and related vegetation indices. Experimental results on Salinas data cube show that the use of the spatial segmentation models with vegetation indices produces promising results.

关键词： hyperspectral image processing spatial segmentation vegetation indices grape plant detection

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：