检索结果-内蒙古大学图书馆

8th International symposium on image and signal processing and Analysis (ISPA)

作者： Kapinaiah, Viswanath Mukhopadhyay, Jayanta Biswas, Prabir Kumar SIT Dept Telecommun Engg Tumkur India IIT Kharagpur Dept CS&E Kharagpur W Bengal India IIT Kharagpur Dept E&ECE Kharagpur W Bengal India

ISBN: (纸本)9789531841948;9789531841870

In this paper, we show how the DCT blocks can be transcoded to wavelet subbands for image deblocking in the wavelet domain. The approach is based on the transcoding of DCT blocks to wavelet coefficient subbands directly in the transform domain. The transcoding uses filtering (wavelet analysis) along with re-sampling (down) operation in the block DCT space. To perform transcoding, linear filtering is used in the block DCT domain. In this technique, filtering is performed on the three adjacent blocks. The complexity is reduced by performing sampling rate change and filtering operations in a single combined step. The proposed approach achieves the quality as same as the spatial domain technique at a reduced computational cost.

关键词： Transform Domain processing Deblocking Transcoding Block DCT DWT Post-processing

来源：评论

学校读者我要写书评

暂无评论

Evaluation of a Channel Decorrelation Approach for Stereo Acoustic Echo Cancellation

Evaluation of a Channel Decorrelation Approach for Stereo Ac...

引用

8th International symposium on image and signal processing and Analysis (ISPA)

作者： Romoli, Laura Cecchi, Stefania Piazza, Francesco Univ Politecn Marche Dept Informat Engn I-60131 Ancona Italy

ISBN: (纸本)9789531841948;9789531841870

Multichannel acoustic echo cancellers are used in teleconferencing systems in order to reduce undesired echoes and to introduce better performance in terms of sound localization in the presence of more than one participant. In this context, stereophonic systems obtain realistic performance, since listeners have spatial information that helps to identify the speaker position. Unfortunately, the correlation between the two channels prevents a correct identification of the echo paths and signal decorrelation is needed. In this paper, a subjective analysis of a low-complexity implementation of a real-time decorrelation approach is presented. The analyzed approach is based on the "missing-fundamental" phenomenon and it is focused on the computation of one adaptive parameter in order to guarantee high performance in terms of convergence speed, audio quality, and computational complexity. A deeply investigation of the subjective perception is here presented, confirming the effectiveness of the proposed approach and showing its feasibility in real scenarios.

关键词： acoustic signal processing audio signal processing decorrelation echo suppression teleconferencing

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Computer Vision and image processing: some FAQs, Current Challenges and Future Perspectives

Evolutionary Computer Vision and Image Processing: some FAQs...

引用

ieee Congress on Evolutionary Computation (CEC) held as part of ieee World Congress on computational intelligence (ieee WCCI)

作者： Cagnoni, Stefano Zhang, Mengjie Univ Parma Dept Informat Engn Parma Italy Victoria Univ Wellington Sch Engn & Comp Sci Wellington New Zealand

ISBN: (纸本)9781509006229

Applications to image/signal processing and analysis have been studied since the very early years in the history of Evolutionary Computation up to a degree of popularity which has allowed terms like Evolutionary Computer Vision (ECV) and Evolutionary image processing (EIP) to become common among researchers. Within these fields, the role of EC has gone well beyond basic optimization of the parameters of traditional Computer Vision (CV) or image processing (IP) algorithms or mere use within those algorithms which comprise an optimization stage anyway. This paper, far from having the pretence of making an exhaustive review, tries to sketch the motivations behind the success of ECV/EIP, the present status of research in such a field, and a personal view of its possible developments in the near future, based on the authors' more than 20-year long direct experience.

关键词： Evolutionary Computer Vision Evolutionary image processing GPUs

来源：评论

学校读者我要写书评

暂无评论

Receiver of L-DACS1 Physical Layer System

Receiver of L-DACS1 Physical Layer System

引用

6th International symposium on computational intelligence and Design (ISCID)

作者： Liu, Haitao Xu, Jun Li, Chongyi Civil Aviat Univ China Tianjin Key Lab Adv Signal Proc Tianjin 300300 Peoples R China

ISBN: (纸本)9780769550794

According to the proposal of L-DACS1, we build the model of the receiver of the physical layer of the L-DACS1 system, using verilog HDL and DSP programming language. Timing synchronization module, which is used to locate the signals with noises accurately, is programmed in verilog HDL, considering the special structure of the time domain representation of synchronization symbols. The module of channel estimating and equalizing process the data using DSP chips, so than we can avoid errors brought by fixed algorithms and reduce the work of FPGA effectively at the same time. The result shows that the receiver can ensure a good use of the resources on chips and realize accurate and continuous work, using FPGA and DSP.

关键词： L-band digital aeronautical communication system (L-DACS1) Orthogonal frequency division multiplexing (OFDM) Digital signal processing (DSP)

来源：评论

学校读者我要写书评

暂无评论

Expanding an HPC Cluster to Support the computational Demands of Digital Pathology

Expanding an HPC Cluster to Support the Computational Demand...

引用

ieee signal processing in Medicine and Biology symposium (SPMB)

作者： Campbell, C. Mecca, N. Duong, T. Obeid, I. Picone, J. Temple Univ Neural Engn Data Consortium Philadelphia PA 19122 USA

ISBN: (纸本)9781538659168

The goal of this work was to design a low-cost computing facility that can support the development of an open source digital pathology corpus containing 1M images [1]. A single image from a clinical-grade digital pathology scanner can range in size from hundreds of megabytes to five gigabytes. A 1M image database requires over a petabyte (PB) of disk space. To do meaningful work in this problem space requires a significant allocation of computing resources. The improvements and expansions to our HPC (high-performance computing) cluster, known as Neuronix [2], required to support working with digital pathology fall into two broad categories: computation and storage. To handle the increased computational burden and increase job throughput, we are using Slurm [3] as our scheduler and resource manager. For storage, we have designed and implemented a multi-layer filesystem architecture to distribute a filesystem across multiple machines. These enhancements, which are entirely based on open source software, have extended the capabilities of our cluster and increased its cost-effectiveness.

关键词： Pathology Microsoft Windows Random access memory Linux Scheduling Processor scheduling Resource management

来源：评论

学校读者我要写书评

暂无评论

Local Discriminant Basis algorithm - A review of theory and applications in signal processing

Local Discriminant Basis algorithm - A review of theory and ...

引用

ieee International symposium on Circuits and Systems

作者： Hazaveh, K Raahemifar, K Ryerson Univ Elect & Comp Engn Dept Toronto ON M5B 2K3 Canada

ISBN: (纸本)0780377613

Local Discriminant Basis (LDB) algorithm is a powerful algorithmic framework that was originally developed by Coifman and Saito as a technique for analyzing object classification problems. Prior to the development of LDB, an adapted waveform framework called best basis algorithm had been developed mainly for signal compression problems. The main advantage of LDB over other similar techniques such as Karhunen-Loeve transform (KLT) also known as Principal Component Analysis (PCA) is its lower computational cost of O(n log n) order. This paper is the outcome of a literature review on theory and applications of LDB in signal processing.

关键词： best basis local discriminant basis local feature extraction pattern recognition time-frequency analysis signal processing image processing wavelet transform wavelet packet local trigonometric basis

来源：评论

学校读者我要写书评

暂无评论

Extended Map Estimation Algorithm Using Joint Entropy-Distortion Metric for Non-Rectified Stereoscopic images 15

Extended Map Estimation Algorithm Using Joint Entropy-Distor...

引用

ieee International symposium on signal processing and Information Technology (ISSPIT)

作者： Kadaikar, Aysha Dauphin, Gabriel Mokraoui, Anissa Univ Paris 13 Sorbonne Paris Cite L2TI 99 Ave Jean Baptiste Clement F-93430 Villetaneuse France

ISBN: (纸本)9781509004805

This paper deals with the disparity map estimation problem to encode non-rectified stereoscopic images. This encoding issue is considered as a trade-off between the quality of the predicted view and the bit-rate required to encode the estimated disparity map. A sub-optimal optimization algorithm, known as Modified-M-Algorithm, based on an entropy-distortion metric has already been proposed specifically for rectified stereoscopic images. Indeed the selected disparities reduce not only the distortion of the predicted image but also the entropy of the estimated disparity map under a low computational complexity. An extension of this strategy is proposed to non-rectified stereoscopic images. Simulation results confirm that our extended algorithm still achieves better rate-distortion performance than the traditional block-matching algorithm. Moreover an improvement in terms of rate-distortion performance is also observed even in the case of rectified stereoscopic images.

关键词： Stereoscopic image block matching optimization entropy disparity

来源：评论

学校读者我要写书评

暂无评论

DEEP FEATURE COMPRESSION FOR COLLABORATIVE OBJECT DETECTION 25

DEEP FEATURE COMPRESSION FOR COLLABORATIVE OBJECT DETECTION

引用

25th ieee International Conference on image processing (ICIP)

作者： Choi, Hyomin Bajic, Ivan V. Simon Fraser Univ Sch Engn Sci Burnaby BC Canada

ISBN: (纸本)9781479970612

Recent studies have shown that the efficiency of deep neural networks in mobile applications can be significantly improved by distributing the computational workload between the mobile device and the cloud. This paradigm, termed collaborative intelligence, involves communicating feature data between the mobile and the cloud. The efficiency of such approach can be further improved by lossy compression of feature data, which has not been examined to date. In this work we focus on collaborative object detection and study the impact of both near-lossless and lossy compression of feature data on its accuracy. We also propose a strategy for improving the accuracy under lossy feature compression. Experiments indicate that using this strategy, the communication overhead can be reduced by up to 70% without sacrificing accuracy.

关键词： Deep feature compression collaborative intelligence compression-augmentation object detection

来源：评论

学校读者我要写书评

暂无评论

An Extendable Multi-Purpose 3D Neuromorphic Fabric using Nanoscale Memristors

An Extendable Multi-Purpose 3D Neuromorphic Fabric using Nan...

引用

ieee symposium on computational intelligence for Security and Defense Applications (CISDA)

作者： Manem, Harika Beckmann, Karsten Xu, Min Carroll, Robert Geer, Robert Cady, Nathaniel C. SUNY Polytech Inst Coll Nanoscale Sci & Engn Albany NY USA

ISBN: (纸本)9781467375573

Neuromorphic computing offers an attractive means for processing and learning complex real-world data. With the emergence of the memristor, the physical realization of cost-effective artificial neural networks is becoming viable, due to reduced area and increased performance metrics than strictly CMOS implementations. In the work presented here, memristors are utilized as synapses in the realization of a multi-purpose heterogeneous 3D neuromorphic fabric. This paper details our in-house memristor and 3D technologies in the design of a fabric that can perform real-world signal processing (i.e., image/video etc.) as well as everyday Boolean logic applications. The applicability of this fabric is therefore diverse with applications ranging from general-purpose and high performance logic computing to power-conservative image detection for mobile and defense applications. The proposed system is an area-effective heterogeneous 3D integration of memristive neural networks, that consumes significantly less power and allows for high speeds (3D ultra-high bandwidth connectivity) in comparison to a purely CMOS 2D implementation. images and results provided will illustrate our state of the art 3D and memristor technology capabilities for the realization of the proposed 3D memristive neural fabric. Simulation results also show the results for mapping Boolean logic functions and images onto perceptron based neural networks. Results demonstrate the proof of concept of this system, which is the first step in the physical realization of the multi-purpose heterogeneous 3D memristive neuromorphic fabric.

关键词： 3D integrated circuits memristor Neuromorphics neural networks image processing nanoelectronics

来源：评论

学校读者我要写书评

暂无评论

Advances in neural networks research: An introduction

引用

NEURAL NETWORKS 2009年第5-6期22卷 489-490页

作者： Kozma, Robert Bressler, Steven Perlovsky, Leonid Venayagamoorthy, Ganesh Kumar Univ Memphis FedEx Inst Technol Memphis TN 38152 USA Florida Atlantic Univ Boca Raton FL 33431 USA Harvard Univ Cambridge MA 02138 USA Missouri Sci & Technol Univ Rolla MO USA

The present Special Issue "Advances in Neural Networks Research: IJCNN2009" provides a state-of-art overview of the field of neural networks. It includes 39 papers from selected areas of the 2009 International joint Conference on Neural Networks (IJCNN2009). IJCNN2009 took place on June 14-19, 2009 in Atlanta, Georgia, USA, and it represents an exemplary collaboration between the International Neural Networks Society and the ieee computational intelligence Society. Topics in this issue include neuroscience and cognitive science, computational intelligence and machine learning, hybrid techniques, nonlinear dynamics and chaos, various soft computing technologies, intelligent signal processing and pattern recognition, bioinformatics and biomedicine, and engineering applications. (C) 2009 Elsevier Ltd. All rights reserved.

关键词： Neuroscience Cognition Machine Learning Hybrid Systems Soft Computing Dynamic Systems image processing Bioinformatics Robotics Power Systems

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：