检索结果-内蒙古大学图书馆

14th International Workshop on Cellular Nanoscale Networks and their applications (CNNA)

作者： Oliveira, Fernanda D. V. R. Gomes, Jose Gabriel R. C. Petraglia, Antonio Univ Fed Rio de Janeiro COPPE PEE BR-21941972 Rio De Janeiro RJ Brazil

ISBN: (纸本)9781479960071

CMOS imaging hardware has become a widespread research topic due to its flexibility in allowing focal-plane, pixel-level signal processing. In a number of vision chips, dedicated image processing techniques are carried out in the analog domain to extract relevant information. Analog processing leads to time and power consumption savings, especially if combined with parallel processing, which is conventionally used because of the inherently parallel nature of imaging arrays. We focus on the focal-plane analog implementation of an image compression algorithm, based on differential pulse-code modulation, linear transform, and vector quantization. In a prototype fabricated in a 0.35 mu m CMOS technology, the texture information inside each pixel block in a 32 x 32 array was locally encoded by inner products applied to 4 x 4 pixel neighborhoods followed by vector quantization. In this paper, a new chip implemented in a 0.18 mu m CMOS technology incorporating improvements suggested by the previous prototype experimental evaluation is presented. We highlight a 5 dB increase in image quality, confirmed by numerical simulations, at the expense of modest increase in complexity and bit rate. Cascode current mirrors are used in parts of the circuitry and pixel non-linearity models are made available to the decoder.

关键词： image compression algorithm analog circuits analog domain Vector quantization image processing techniques pixel CMOS technology parallel processing (COMPUTERS) Electric circuits decoders Power consumption differential pulse code modulation

来源：评论

学校读者我要写书评

暂无评论

GPU Accelerated Face Recognition System with Enhanced Local Ternary Patterns Using OpenCL

GPU Accelerated Face Recognition System with Enhanced Local ...

引用

Proceedings of the Digital image Computing: Technqiues and applications (DICTA)

作者： B. Vinith M.K. Akhila Narmada Naik G.N. Rathna Department of Electronics and Communication Engineering National Institute of Technology Calicut India Department of Electrical Engineering Indian Institute of Science Bangalore India

Enhanced Local Ternary Patterns (ELTP) significantly improves performance over other feature descriptor methods including Local Binary Patterns (LBP) and Local Ternary Patterns (LTP).Sequential implementation of ELTP results in poor performance in terms of execution time for real time *** and accuracy are important characteristics of a real time face recognition system. With the aim of fulfilling both these criteria, this paper presents an implementation of GPU Accelerated Face Recognition System with ELTP using OpenCL framework. As a result of our Optimization techniques, we have achieved highest kernel execution speedup of 374x for ELTP image and histogram generation with 4096x4096 (16MP) image resolution when it is implemented on GPU. Face recognition with ELTP showed higher recognition rates on ORL database. We also implemented LBP and LTP algorithms on GPU and compared their performances with ELTP. Similar Optimization techniques were applied for LBP kernel executions, which resulted in much higher speedups when compared to their previous implementations. Experimental results demonstrated that parallel implementation with ELTP on GPU (AMD Radeon HD 7650M) outperforms CPU based face recognition system using LBP in terms of speed and accuracy.

关键词： Graphics processing units Face recognition Kernel Face Real-time systems Optimization Histograms

来源：评论

学校读者我要写书评

暂无评论

FPGA implementation of low-power 3D ultrasound beamformer

FPGA implementation of low-power 3D ultrasound beamformer

引用

IEEE Symposium (IUS) Ultrasonics

作者： Richard Sampson Ming Yang Siyuan Wei Rungroj Jintamethasawat Brian Fowlkes Oliver Kripfgans Chaitali Chakrabarti Thomas F. Wenisch Department of EECS University of Michigan School of ECEE Arizona State University Department of Radiology University of Michigan

3D ultrasound is common for non-invasive medical imaging in cardiology and OB-GYN because of its accuracy, safety, and real-time ease of use. However, high bandwidth requirements and extreme computational complexity have precluded hand-held and low-power 3D systems, limiting 3D applications. In previous work, we presented Sonic Millip3De, a hardware design that can efficiently handle the high computational demand of real-time 3D synthetic aperture beamforming, even in handheld and mobile applications. The design combines a custom, highly parallel hardware system with a novel delay approximation method to quickly produce high quality 3D image data within an estimated 15 W full-system power budget. Prior evaluations of the design relied on software prototypes; this work extends previous evaluations with an FPGA implementation of the beamforming accelerator, validating the results of earlier prototypes. In particular, we carry out image quality analyses of our beamforming architecture using simulated 3D echo data (from Field ii) and 2D artificial tissue phantom data acquired using a Verasonics V-1 system and Philips P4-1 probe. We compare results from the FPGA implementation to an ideal software beamformer and prior software prototypes of the Sonic Millip3De design.

关键词： Three-dimensional displays Field programmable gate arrays Array signal processing Transducers Ultrasonic imaging Prototypes Hardware

来源：评论

学校读者我要写书评

暂无评论

Analysis of scalability of high-performance 3D image processing platform for virtual colonoscopy

Analysis of scalability of high-performance 3D image process...

引用

Conference on Medical imaging - PACS and imaging Informatics - Next Generation and Innovations

作者： Yoshida, Hiroyuki Wu, Yin Cai, Wenli Massachusetts Gen Hosp 3D Imaging Res Dept Radiol 25 New Chardon StSuite 400C Boston MA 02114 USA Massachusetts Gen Hosp Harvard Med Sch Boston MA 02114 USA

ISBN: (纸本)9780819498328

One of the key challenges in three-dimensional (3D) medical imaging is to enable the fast turn-around time, which is often required for interactive or real-time response. This inevitably requires not only high computational power but also high memory bandwidth due to the massive amount of data that need to be processed. For this purpose, we previously developed a software platform for high-performance 3D medical image processing, called HPC 3D-MIP platform, which employs increasingly available and affordable commodity computing systems such as the multicore, cluster, and cloud computing systems. To achieve scalable high-performance computing, the platform employed size-adaptive, distributable block volumes as a core data structure for efficient parallelization of a wide range of 3D-MIP algorithms, supported task scheduling for efficient load distribution and balancing, and consisted of a layered parallel software libraries that allow image processing applications to share the common functionalities. We evaluated the performance of the HPC 3D-MIP platform by applying it to computationally intensive processes in virtual colonoscopy. Experimental results showed a 12-fold performance improvement on a workstation with 12-core CPUs over the original sequential implementation of the processes, indicating the efficiency of the platform. Analysis of performance scalability based on the Amdahl's law for symmetric multicore chips showed the potential of a high performance scalability of the HPC 3D-MIP platform when a larger number of cores is available.

关键词： 3D imaging processing high-performance computing performance scalability virtual colonoscopy

来源：评论

学校读者我要写书评

暂无评论

Digital pixel CMOS focal plane array with on-chip multiply accumulate units for low-latency image processing

Digital pixel CMOS focal plane array with on-chip multiply a...

引用

40th Conference on Infrared Technology and applications

作者： Little, Jeffrey W. Tyrrell, Brian W. D'Onofrio, Richard Berger, Paul J. Fernandez-Cull, Christy MIT Lincoln Lab Lexington MA 02420 USA

ISBN: (纸本)9781628410075

A digital pixel CMOS focal plane array has been developed to enable low latency implementations of image processing systems such as centroid trackers, Shack-Hartman wavefront sensors, and Fitts correlation trackers through the use of in-pixel digital signal processing (DSP) and generic parallel pipelined multiply accumulate (MAC) units. Light intensity digitization occurs at the pixel level, enabling in-pixel DSP and noiseless data transfer from the pixel array to the peripheral processing units. The pipelined processing of row and column image data prior to off chip readout reduces the required output bandwidth of the image sensor, thus reducing the latency of computations necessary to implement various image processing systems. Data volume reductions of over 80% lead to sub 10 mu s latency for completing various tracking and sensor algorithms. This paper details the architecture of the pixel-processing imager (PPI) and presents some initial results from a prototype device fabricated in a standard 65nm CMOS process hybridized to a commercial off-the-shelf short-wave infrared (SWIR) detector array.

关键词： focal plane array digital readout integrated circuit low latency image processing wavefront sensing correlation tracking

来源：评论

学校读者我要写书评

暂无评论

Decomposition by Partial Linearization: parallel Optimization of Multi-Agent systems

引用

IEEE TRANSACTIONS ON SIGNAL processing 2014年第3期62卷 641-656页

作者： Scutari, Gesualdo Facchinei, Francisco Song, Peiran Palomar, Daniel P. Pang, Jong-Shi SUNY Buffalo Dept Elect Engn Buffalo NY 14260 USA Univ Roma La Sapienza Dept Comp Control & Management Engn I-00185 Rome Italy Hong Kong Univ Sci & Technol Dept Elect & Comp Engn Hong Kong Hong Kong Peoples R China Univ So Calif Viterbi Sch Engn Dept Ind & Syst Engn Los Angeles CA 90089 USA

We propose a novel decomposition framework for the distributed optimization of general nonconvex sum-utility functions arising naturally in the system design of wireless multi-user interfering systems. Our main contributions are i) the development of the first class of (inexact) Jacobi best-response algorithms with provable convergence, where all the users simultaneously and iteratively solve a suitably convexified version of the original sum-utility optimization problem;ii) the derivation of a general dynamic pricing mechanism that provides a unified view of existing pricing schemes that are based, instead, on heuristics;and iii) a framework that can be easily particularized to well-known applications, giving rise to very efficient practical (Jacobi or Gauss-Seidel) algorithms that outperform existing ad hoc methods proposed for very specific problems. Interestingly, our framework contains as special cases well-known gradient algorithms for nonconvex sum-utility problems, and many block-coordinate descent schemes for convex functions.

关键词： Nonconvex multi-agent problems parallel and distributed optimization successive convex approximation

来源：评论

学校读者我要写书评

暂无评论

Real-time atmospheric imaging and processing with hybrid adaptive optics and hardware accelerated lucky-region fusion (LRF) algorithm 5

Real-time atmospheric imaging and processing with hybrid ada...

引用

Conference on Photonics applications for Aviation, Aerospace, Commercial, and Harsh Environments V

作者： Liu, Jony Jiang Carhart, Gary W. Beresnev, Leonid A. Aubailly, Mathieu Jackson, Christopher Ejzak, Garrett Kiamilev, Fouad US Army RDRL CIE S Res Lab Adelphi MD 20783 USA Univ Maryland College Pk MD 20742 USA Univ Delaware CVORG Newark DE 19716 USA

ISBN: (纸本)9781628412291

Atmospheric turbulences can significantly deteriorate the performance of long-range conventional imaging systems and create difficulties for target identification and recognition. Our in-house developed adaptive optics (AO) system, which contains high-performance deformable mirrors (DMs) and the fast stochastic parallel gradient decent (SPGD) control mechanism, allows effective compensation of such turbulence-induced wavefront aberrations and result in significant improvement on the image quality. In addition, we developed advanced digital synthetic imaging and processing technique, "lucky-region" fusion (LRF), to mitigate the image degradation over large field-of-view (FOV). The LRF algorithm extracts sharp regions from each image obtained from a series of short exposure frames and fuses them into a final improved image. We further implemented such algorithm into a VIRTEx-7 field programmable gate array (FPGA) and achieved real-time video processing. Experiments were performed by combining both AO and hardware implemented LRF processing technique over a near-horizontal 2.3km atmospheric propagation path. Our approach can also generate a universal real-time imaging and processing system with a general camera link input, a user controller interface, and a DVI video output.

关键词： adaptive optics system lucky-region fusion atmospheric imaging real-time image processing FPGA

来源：评论

学校读者我要写书评

暂无评论

Medical imaging and computers in the diagnosis of breast cancer 2

Medical imaging and computers in the diagnosis of breast can...

引用

Conference on Photonic Innovations and Solutions for Complex Environments and systems (PISCES) ii

作者： Giger, Maryellen L. Univ Chicago Dept Radiol Chicago IL 60637 USA

ISBN: (纸本)9781628412161

Computer-aided diagnosis (CAD) and quantitative image analysis (QIA) methods (i.e., computerized methods of analyzing digital breast images: mammograms, ultrasound, and magnetic resonance images) can yield novel image-based tumor and parenchyma characteristics (i.e., signatures that may ultimately contribute to the design of patient-specific breast cancer management plans). The role of QIA/ CAD has been expanding beyond screening programs towards applications in risk assessment, diagnosis, prognosis, and response to therapy as well as in data mining to discover relationships of image-based lesion characteristics with genomics and other phenotypes;thus, as they apply to disease states. These various computer-based applications are demonstrated through research examples from the Giger Lab.

关键词： Computer aided diagnosis and therapy Computing systems Breast Breast cancer Tumors image processing image segmentation Medical imaging image analysis Cancer

来源：评论

学校读者我要写书评

暂无评论

FPGA Implementation of a Modified Pulse Mode FCM image Segmentation algorithms 1

FPGA Implementation of a Modified Pulse Mode FCM Image Segme...

引用

Conference on First International image processing, applications and systems

作者： Karray, Marwa Krid, Mohamed Gargouri, Amir Masmoudi, Dorra Sellami Univ Sfax Sfax Engn Sch Comp Imaging Elect & Syst Grp CIELS Adv Control & Energy Management Lab CEMLab BP W Sfax 3038 Tunisia

ISBN: (纸本)9781479970698

This paper present a novel architecture for image segmentation. The design is based on the fuzzy c-means algorithm based gaussian function in pulse mode for reducing the large storage requirement. The proposed algorithm is tested in mammogram image segmentation approximately with 0 : 9 2 of segmentation index. The pulse mode stochastic computing technique is implemented with a simple bloc avoiding the use of conventional multipliers for sake of compactness. The whole modified FCM is implemented on a Virtex ii PRO FPGA platform and synthesis results are presented.

关键词： FCM FPGA implementation pulse mode mammogram image segmentation

来源：评论

学校读者我要写书评

暂无评论

Fast and Accurate Implementation of Canny Edge Detector on Embedded Many-core Platform 12

Fast and Accurate Implementation of Canny Edge Detector on E...

引用

12th IEEE International New Circuits and systems Conference (IEEE NEWCAS)

作者： Ben Cheikh, Taieb Lamine Nicolescu, Gabriela Trajkovic, Jelena Bouchebaba, Youcef Paulin, Pierre Ecole Polytech Dept Comp Engn Montreal PQ Canada Concordia Univ Dept Elect & Comp Engn Montreal PQ H3G 1M8 Canada Synopsys Inc Ottawa ON Canada

ISBN: (纸本)9781479948857

image processing and computer vision applications are used intensively in several domains in particular multimedia and medicine. The main challenge in developing such applications is how to guarantee both high accuracy and low execution time. Accordingly, we observe two research directions: the first focuses on improving the algorithms and the second focuses on designing fast hardware platforms. In this paper, we propose an efficient parallel implementation of an accurate extended Canny edge detection algorithm suitable for medical applications on embedded many-core platform. The proposed implementation is running at a frame rate of 10 frames/s for image size of 512x512 with high accurate and smooth line edges.

关键词： Accuracy Computer architecture Fabrics Graphics processing units Hardware image edge detection Real-time systems Edge detection Computer Architecture real-time systems Canny edge detector Textile fabrics fabric Computer hardware Graphics processing Unit boundary detection algorithm Fasting Frame Rate image SIZE

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：