检索结果-内蒙古大学图书馆

International SoC design conference, ISOCC

作者： Seongmo Park Byoung Gun Choi Kwang-Il Oh S. E. Kim J. H. Lee J. J. Lee Sung Weon Kang ETRI: Department of Intelligent SoC Research Deajeon Korea

The proposed algorithm describes compressed image processing based on the Modified Region Convolutional Neural Network (MR-CNN) method. An object extracting unit may classify each of the modified-regions into a background region or an object region on the basis of the degree of pixel changes in the respective set of the modified-regions. There is an efficient compression ratio that can classify an image with each parameter according to the object, text, and background images. The algorithm proposed in the paper improved compression ratio by 10.95% with no degradation compared to the JPEG, and HEVC standards.

关键词： image coding Quantization (signal) Standards High efficiency video coding Convolutional neural networks Classification algorithms Degradation

来源：评论

学校读者我要写书评

暂无评论

Multi Denoising Approximate Message Passing for Optimal Recovery with Lower Computational Cost

Multi Denoising Approximate Message Passing for Optimal Reco...

引用

European signal processing conference

作者： Alessandro Perelli Mike E. Davies Institute for Digital Communications The University of Edinburgh (UK)

An emerging issue in large-scale inverse problems is constituted by the interdependency between computational and recovery performance;in particular in practical application, such as medical imaging, it is crucial to provide high quality estimates given bounds on computational time. While most work in this direction has gone down the lines of improving optimisation schemes, in this paper we are proposing and investigating a different approach based on a multi denoising approximate message passing (MultiD-AMP) framework for Compressive Sensing (CS) image reconstruction which exploits an hierarchy of denoisers by starting with a low fidelity model and then using the estimate as starting point for a higher fidelity models through an iterative reconstruction algorithm. MultiD-AMP achieves lower time complexity and same accuracy compared to using the same most accurate denoiser as in D-AMP. The novelty of our approach is based on exploiting the deterministic state evolution of AMP, which means the predictability of the recovery performances, to design a strategy for selecting the denoiser from a set ordered by both computational complexity and statistical efficiency. We apply the MultiD-AMP framework for image reconstruction given noisy Gaussian random linear measurements. Furthermore, we extend and show the applicability of MultiD-AMP for CS to image reconstruction.

关键词： Switches Noise reduction image reconstruction Noise measurement Training Discrete wavelet transforms Time complexity

来源：评论

学校读者我要写书评

暂无评论

Low latency divider using ensemble of moving average curves

Low latency divider using ensemble of moving average curves

引用

IEEE International Symposium on Quality Electronic design

作者： Yuhan Fu Masayuki Ikebe Takeshi Shimada Tetsuya Asai Masato Motomura Graduate School of Information Science and Technology Hokkaido University Sapporo Japan

ISBN: (纸本)9781509054053

Division is a fundamental operation used in the architectures for digital signal processing algorithms. In this paper, we propose a fixed-point divider based on an ensemble of moving average (EnMA) curves. The EnMA algorithm generates piecewise polynomial explicit functions, which are first-order continuously differentiable. Thus, applying the EnMA algorithm for generating the curve y = 1/x, we directly obtain values of y and decrease multiplications and subtractions in the division algorithm. Evaluation of our divider on an FPGA Xilinx Kintex-7 board revealed latency of one clock cycle and operation speed of 23.12 ns by using only 625 look-up-tables, which is two times faster than the latest Xilinx IPs. The relative error was smaller than 0.01%, so our divider guaranteed 13-bit precision in division. Therefore, our proposed divider can be effectively used for image processing applications.

关键词： signal processing algorithms Hardware Interpolation Mathematical model Computer architecture Linear approximation Optimization

来源：评论

学校读者我要写书评

暂无评论

Complex domain nonlocal block-matching denoising based on high-order singular value decomposition (HOSVD)

Complex domain nonlocal block-matching denoising based on hi...

引用

European signal processing conference

作者： Vladimir Katkovnik Mykola Ponomarenko Karen Egiazarian Laboratory of Signal Processing Tampere University of Technology Tampere Finland

Block matching 3D collaborative filtering (BM3D) is one of the most popular denoising technique based on data sparsity concept applied to specially structured data. In this paper we develop this technique for complex domain, i.e. for application to complex-valued data. Sparsity as an approximation technique can be addressed directly to complex-valued variables or to real-valued pairs phase/amplitude and real/imaginary parts of complex-valued variables. As a result we arrive to various ways of development and obtain a set of quite different algorithms. The algorithms proposed in this paper are composed from two components: nonlocal patch-wise grouping and high-order singular value decomposition (HOSVD) for grouped data processing. The latter gives data adaptive complex-valued bases for complex-valued data or real-valued bases for joint processing of the pairs phase/amplitude, real/imaginary parts of complex-valued variables. Comparative study of the developed algorithms is produced in order to select the most efficient ones.

关键词： Algorithm design and analysis signal processing algorithms Transforms Three-dimensional displays Noise reduction image reconstruction Extraterrestrial measurements

来源：评论

学校读者我要写书评

暂无评论

Optimal MIMO array configuration for ultrawideband microwave imaging

Optimal MIMO array configuration for ultrawideband microwave...

引用

IEEE signal processing and Communications Applications (SIU)

作者： M. Burak Kocamış Figen S. Öktem Elektrik ve Elektronik Mühendisliği Bölümü Orta Doğu Teknik Üniversitesi Çankaya Ankara Türkiye

Wideband microwave imaging systems are recently used in various applications including airport security, surveillance, through-wall imaging and medicine. For the operation of such high-resolution systems, sparse multiple-input-multiple-output (MIMO) arrays are of interest to reduce the hardware complexity and cost of conventional planar arrays. In this paper, we present a method for the optimal design of two-dimensional MIMO arrays in near-field imaging. Using a statistical framework, the optimality criterion is defined based on the image reconstruction quality. A modified version of the sequential backward selection algorithm is used to optimize the criterion over all possible locations of desired number of antenna elements. The designs obtained with the algorithm are compared with the commonly used sparse array configurations such as Mills Cross array and curvilinear structure composed array in terms of image reconstruction quality.

关键词： MIMO Microwave imaging Microwave theory and techniques Radar imaging Zirconium image reconstruction

来源：评论

学校读者我要写书评

暂无评论

The Joint International Symposium on Artificial Intelligence and Natural Language processing, iSAI-NLP 2017

引用

The Joint International Symposium on Artificial Intelligence and Natural Language processing, iSAI-NLP 2017

ISBN: (纸本)9783319947020

The proceedings contain 22 papers. The special focus in this conference is on Artificial Intelligence and Natural Language processing. The topics include: Isan Dhamma Characters Segmentation and reading in Thai;ontology-assisted structural design flaw detection of object-oriented software;virtual reality application for animal cruelty education;anti-theft motorcycle system using face recognition by deep learning under concept on Internet of Things;balanced scorecard quality information dashboards model for competitive business advantage;criminal background check program with fingerprint;Jobs analysis for business intelligence skills requirements in the ASEAN region: A text mining study;the model of teenager’s internet usage behavior analysis using data mining;privacy-preserving reputation management in fully decentralized systems: Challenges and opportunities;cloud-based services for cooperative robot learning of 3D object detection and recognition;empirical testing of a technique for assessing prior knowledge in the field of research training;problem content table construction based on extracting Sym-Multi-Word-Co from texts;Unpredictable disaster evacuation guide for weak people by real-time sensor network, SNS and maps;Detection of normal and abnormal ECG signal using ANN;dynamic relation-based analysis of objective interestingness measures in association rules mining;image encryption using cellular neural network and matrix transformation;improved term weighting factors for keyword extraction in hierarchical category structure and Thai text classification;ontology-based classifiers for wikipedia article quality classification;thai Named-Entity Recognition using variational long short-term memory with conditional random field;cardiac arrhythmia classification using Hjorth Descriptors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Transparent objects: Influence of shape and color on depth perception

Transparent objects: Influence of shape and color on depth p...

引用

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

作者： Ar-pha Pisanpeeti Éric Dinet UJM Saint-Etienne Laboratoire Hubert Curien Saint-Etienne France

Recovering depth information from a single still image is an important problem in computer vision. However, the problem is difficult and challenging because it has an infinite number of solutions. To address this issue, humans use numerous visual cues to infer depth. Much progress has been made towards an understanding of the visual mechanisms involved in 3D perception. Such an understanding provides relevant knowledge to design efficient approaches for computer vision. While there is much prior work on opaque objects, there has been relatively little in relation with transparency. In this paper we investigate depth estimation from single still images containing nonplanar and real transparent objects. We focused our study on two visual features: shape and color. A database of stimuli was created to carry out a psychophysical experiment with 42 naïve observers.

关键词： Glass Shape image color analysis Observers Visualization Databases Three-dimensional displays

来源：评论

学校读者我要写书评

暂无评论

Memristive system design for variable pixel g-neighbor denoising filter

arXiv

引用

arXiv 2017年

作者： Aliakhmet, Kamilla Sadykova, Diana Mathew, Joshin James, Alex Pappachen School of Engineering Nazarbayev University Ars Traffic and Transport Technology India

image blurring artifact is the main challenge to any spatial, denoising filters. This artifact is contributed by the heterogeneous intensities within the given neighborhood or window of fixed size. Selection of most similar intensities (G-Neighbors) helps to adapt the window shape which is of edge-Aware nature and subsequently reduce this blurring artifact. The paper presents a memristive circuit design to implement this variable pixel G-Neighbor filter. The memristive circuits exhibits parallel processing capabilities (near realtime) and neuromorphic architectures. The proposed design is demonstrated as simulations of both algorithm (MATLAB) and circuit (SPICE). Circuit design is evaluated for various parameters such as processing time, fabrication area used, and power consumption. Denoising performance is demonstrated using image quality metrics such as peak signal-Tonoise ratio (PSNR), mean square error (MSE), and structural similarity index measure (SSIM). Combining adaptive filtering method with mean filter resulted in average improvement of MSE to about 65% reduction, increase of PSNR and SSIM to nearly 18% and 12% correspondingly. Copyright © 2017, The Authors. All rights reserved.

关键词： SPICE

来源：评论

学校读者我要写书评

暂无评论

The effect of pre-processing steps on geometric based hyperspectral unmixing algorithms

The effect of pre-processing steps on geometric based hypers...

引用

IEEE signal processing and Communications Applications (SIU)

作者： Bilal Kocakuşaklar Burak Alptekin Nihan Kahraman Elektronik ve Haberleşme Mühendisliği Bölümü Yıldız Teknik Üniversitesi İstanbul Türkiye

Hyperspectral unmixing is a process to find number of surface materials (called endmember), estimation of their signatures, their abundance fractions in each pixel on the scene. Geometric based algorithms are developed for hyperspectral unmixing problem in the literature. The distribution of spectra (points in n-dimensional scatterplot) can be used to estimate endmember signatures geometrically. Both denoising and the use of spatial information in the hyperspectral image as a pre-processing step may cause the endmember signatures to be estimated closer to the truth. For this purpose, Spatio-spectral total variation (SSTV) is used for denoising and Spatial pre-processing (SPP) is used for the use of spatial information. Experiments on real data have shown that these pre-processing steps lead to closer endmember signature estimates.

关键词： Hyperspectral imaging Metals Algorithm design and analysis Noise reduction Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

1st International conference on Intelligent Computing and Communication, ICIC2 2016

1st International Conference on Intelligent Computing and Co...

引用

1st International conference on Intelligent Computing and Communication, ICIC2 2016

ISBN: (纸本)9789811020346

The proceedings contain 70 papers. The special focus in this conference is on Biomedical image processing, Bioinformatics, Cloud Computing, Communication Network, Device System, Modeling, Security and Cryptography. The topics include: Concentration of acetone levels in breath for monitoring blood glucose level;an insight into signal transduction for ophthalmology;common subcluster mining to explore molecular markers of lung cancer;intelligent storage management using cloud shared disk architecture;introspecting effect of packet size on end-to-end network delay;an ontology based context aware protocol in healthcare services;link based protection of light trail in WDM mesh networks;event detection over twitter social media;comparative study of parallelism on data mining;brief review on optimal suffix data structures;closure based integrated approach for associative classifier;a novel mapreduce based k-means clustering;cross-coupled dynamic CMOS latches;cross-coupled dynamic CMOS latches;design based new coupling metric for component based development environment;scientific workflow management system for community model in data fusion;a new implementation scheme in robotic vehicle propulsion using brushless DC motor;binary fuzzy goal programming for effective utilization of IT professionals;AVR microcontroller based conference presentation timer;a person identification system with biometrics using modified RBFN based multiple classifiers;automatic measurement and analysis of vessel width in retinal fundus image;an eigencharacter technique for offline-tamil handwritten character recognition;page-to-word extraction from unconstrained handwritten document images and a novel approach to E-Voting using multi-bit steganography.

关键词：

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：