检索结果-内蒙古大学图书馆

23rd symposium on image, signal processing and Artificial Vision (STSIVA)

作者： Rodriguez, Paul Pontificia Univ Catolica Peru Elect Dept Lima Peru

ISBN: (纸本)9781665416696

Proximal gradient (PG) algorithms target optimization problems composed by the sum of two convex functions, i.e. F = f + g, such that del f is L-Lipschitz continuous and g is possibly nonsmooth. Accelerated PG, which uses past information in order to speed-up PG's original rate of convergence (RoC), are of particular practical interest since they are guaranteed to, at least, achieve O(k(-2)). While there exist several alternatives, arguably, Nesterov's acceleration is the de-facto method. However in the recent years, the Anderson acceleration, a well-established technique, which has also been recently adapted for PG, has gained a lot of attention due to its simplicity and practical speed-up w.r.t. Nesterov's method for small to medium scale (number of variables) problems. In this paper we mainly focus on carrying out a computational (Python based) assessment between the Anderson and Nesterov acceleration methods for large scale optimization problems. The computational evidence from our practical experiments, which particularly target Convolutional Sparse Representations, agrees with our theoretical analysis: the extra burden (both in memory and computations) associated with the Anderson acceleration imposes a practical limit, thus giving the Nesterov's method a clear edge for large scale problems.

关键词： Costs Convolution Extreme learning machines computational modeling Superresolution signal processing algorithms Machine learning

来源：评论

学校读者我要写书评

暂无评论

An Energy-Efficient Embedded Implementation For Target Recognition In SAR imageries

An Energy-Efficient Embedded Implementation For Target Recog...

引用

ieee symposium Series on computational intelligence (ieee SSCI)

作者： Renz, Megan Wu, Qing Univ Buffalo Buffalo NY 14260 USA US Air Force Res Lab Rome NY USA

ISBN: (纸本)9781538627266

This paper presents an energy-efficient deep learning model design, training and implementation method for the synthetic aperture radar (SAR) image classification application on a neuromorphic processor. The proposed approach adopts emerging neuromorphic computing models and hardware to achieve significant improvement in computational energy efficiency over deep learning algorithms on conventional embedded processors. A deep convolutional neural network (DCNN) is designed specifically for implementing image classification on the TrueNorth neurosynaptic processor. We have explored the DCNN model design parameters to obtain a comprehensive solution set in the energy-performance trade-off space. Using a SAR image classification dataset, evaluation results show that the proposed design and implementation approach achieves at least 20X reduction in energy-per-image-classification over one of today's most energy-efficient conventional embedded processors. while achieving a classification accuracy of 95% and a processing throughput of 1,000 images per second.

关键词： neuromorphic computing embedded computing synthetic aperture radar image classification deep convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

M-channel nonlinear phase filter banks in image compression:: Structure, design, and signal extension

引用

ieee TRANSACTIONS ON signal processing 2007年第4期55卷 1339-1351页

作者： Uto, Toshiyuki Oka, Tomohiro Ikehara, Masaaki Ehime Univ Dept Comp Sci Fac Engn Matsuyama Ehime 790 Japan Keio Univ Dept Elect & Elect Engn Fac Sci & Technol Tokyo 108 Japan

This paper describes a transform coding technique based on M-channel perfect reconstruction filter banks with a nonlinear phase. In contrast with linear-phase filter banks, the nonlinearity provides an extra degree of freedom that can be used to design a more efficient transform. We present new lattice structures of paraunitary and perfect reconstruction (biorthogonal) filter banks, which can be implemented with a lower computational complexity and/or represented by a few free parameters, through the decomposition of the lattice blocks and the displacement across the delay block. We further discuss a smooth extension method for nonlinear-phase filter banks to obtain a nonexpansive transform. The promise of our proposed approaches is demonstrated through several design examples, extended signals and compression results.

关键词： image coding lattice structure nonlinear phase filter bank nonexpansive decomposition

来源：评论

学校读者我要写书评

暂无评论

KnowYourColors: Visual Dashboards for Blood Metrics and Healthcare Analytics

KnowYourColors: Visual Dashboards for Blood Metrics and Heal...

引用

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

作者： Reese, Kristopher Bessette, Russell Hancock, Pricilla Univ Louisville Louisville KY 40292 USA

ISBN: (纸本)9781479947966

The understanding of medical test results is markedly improved through the use of visual analytics. While traditional theorists in the field of healthcare analytics seek to improve decision making through data mining and machine learning, Visual Analytics augments that intelligence by providing an interface to integrate all of the data in a composite image. KnowYourColors TM is a visual analytics interface providing many dashboards to help the healthcare and insurance providers make better decisions in treatment and spending. This paper discusses many of the visualizations that are used in those applications. This includes new visualizations focused around polar area diagrams that are designed for showing blood metrics and visualizations of prior research work that help in the decision making process. This paper also demonstrates the effectiveness of the application and the reactions of physicians and patients.

关键词： Visual analytics Visualization Dashboards Health Care MEDICAL TESTS intelligence Metronidazole data mining

来源：评论

学校读者我要写书评

暂无评论

Manual Microaneurysm Detection Support with Size- and Shape-based Detection

Manual Microaneurysm Detection Support with Size- and Shape-...

引用

9th ieee International symposium on Applied computational intelligence and Informatics (SACI)

作者： Varsanyi, Petra Fegyvari, Zsolt Sergyan, Szabolcs Vamossy, Zoltan Obuda Univ Inst Appl Comp Sci Budapest Hungary

ISBN: (纸本)9781479946945

The goal of this paper is to detect visible microaneurysms in retina using size and shape. To achieve the desired goal multi-stage image processing techniques are used. The vascular network and the red regions are highlighted using morphological methods, so these can be segmented with region growing algorithms. Mask is generated that contains only the blood vessels. The red blobs of original images are classified using the generated binary image and their produced skeleton. Our goal is to detect as many as possible microaneurysms taking their shape and size into account. Experiments with manual settings on the test images showed approx. 50% of detection performance, and it can be further improved by development of pre-processing and increasing classification criteria. The developed system can help the manual evaluation of microaneurysms, hence can accelerate of the work of doctors.

关键词： medical image processing microaneurysm detection image segmentation skeletonization

来源：评论

学校读者我要写书评

暂无评论

Flocculation Effect Detection of Chemical Wastewater Based on image processing 11

Flocculation Effect Detection of Chemical Wastewater Based o...

引用

11th International symposium on computational intelligence and Design (ISCID)

作者： Rong, Huang Chen Li, Tang Jia Nanjing Inst Technol Sch Comp Engn Nanjing Jiangsu Peoples R China Jiangsu Univ Technol Coll Comp Engn Changzhou Peoples R China

ISBN: (纸本)9781538685273

With the image correction technology, a deep study and analysis was performed on the mutual relationships among a series of key parameters, including the coagulant dosage and the equivalent diameter, fractal dimension and concentration characteristics of the flocculation image, in the correction process of the chemical wastewater. Considering the actual operation environment and the real-time requirements of automatic dosing control, the Retinex algorithm was adopted in this article to solve the problems of uneven light distribution occurring in the process of experiment. In addition, another algorithm, the simple algorithm, was also applied to the calculation in the link of image correction, so as to shrink the program scale. According to the simulation results, it was indicated that the simulation operation was of relatively good practicability in the practical automatic control.

关键词： chemical wastewater correction flocculation image correction uneven illumination real time

来源：评论

学校读者我要写书评

暂无评论

HIGH-SPEED MULTIDIMENSIONAL CONVOLUTION

引用

ieee TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE intelligence 1980年第3期2卷 269-273页

作者： KIM, CE STRINTZIS, MG Department of Electrical Engineering University of Pittsburgh Pittsburgh PA 15261.

Fast computation algorithms are developed for twodimensional and general multidimensional convolutions. Two basic techniques (overlap-and-add, overlap-and-save) are described in detail. These techniques allow speed and storage requirement tradeoffs and they define a decomposition of the total convolution into partial convolutions that can be easily found by parallel use of fast sequential cyclic convolution algorithms. It is shown that unlike what is the case in one dimension, the ``overlap-and-save'' method enjoys a clear advantage over the ``overlap-and-add'' method with respect to speed and storage in multidimensional convolution. A specific computational burden is assessed for the case where these methods are used in conjunction with radix-2 fast Fourier transform algorithms.

关键词： Multidimensional systems Convolution image processing Fast Fourier transforms image analysis Pattern analysis signal analysis Multidimensional signal processing signal processing Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Adaptive Vehicle Shadow Detection Algorithm in Highway

Adaptive Vehicle Shadow Detection Algorithm in Highway

引用

5th International symposium on computational intelligence and Design (ISCID)

作者： He, Yufeng Li, Jiatian Wang, Hua Pu, Haixia Li, Rui Kunming Univ Sci & Technol Fac Land Resource Engn Kunming Peoples R China

ISBN: (纸本)9780769548111

Traditional shadow suppression method based on HSV color space was proved to be an effective method. However, shadow detection with fixed parameters does not meet the change of monitored scene. According to vehicle property and scene change by the shadow projection, this article proposed an adaptive detection algorithm to achieve proposes of adaptive shadow suppression without adjusts the threshold manually. Experiment result shows that, in the process of monitoring and tracking on the highway, this method can adaptively suppress the shadow in the condition of the scene change.

关键词： Shadow Detection Adaptive Vehicle Detection and Tracking Intelligent Transportation System image processing

来源：评论

学校读者我要写书评

暂无评论

Analysis of Visual Attributes of Clothes on Dressing images 8

Analysis of Visual Attributes of Clothes on Dressing Images

引用

8th International symposium on computational intelligence and Design (ISCID)

作者： Han, Zhitian Sun, Tao Beihang Univ State Key Lab Software Dev Environm Beijing Peoples R China

ISBN: (纸本)9781467395878

We propose a new method to extract the attributes of clothes on human body. Some appropriate composite- parts of the collar are chosen to represent its peculiarity. The HOG feature is extracted and efficient filters with linear SVM are created to predicate the parts. Then structure expanding method is proposed to recognize the collar type according to the constraint spatial relationships between the parts. We also acquire the clothes length attribute with the area search method and analyze the sleeve length attribute. A contrast experiment on a dataset including 1683 images indicates that our methods can significantly improve the recognition accuracy. Finally we develop a fully- automatic image retrieving system to show the effect of our work.

关键词： image processing attributes recognisation structure expanding

来源：评论

学校读者我要写书评

暂无评论

Optimized Wavelet Denoising Algorithm Using Hybrid Noise Model for Radiographic images 7

Optimized Wavelet Denoising Algorithm Using Hybrid Noise Mod...

引用

7th International symposium on computational intelligence and Design (ISCID)

作者： Dang, Changying Gao, Jianmin Wang, Zhao Chen, Fumin Xiao, Yulin Xi An Jiao Tong Univ State Key Lab Mfg Syst Engn Xian Peoples R China Xi An Jiao Tong Univ Sch Mech Engn Xian Peoples R China

ISBN: (纸本)9781479970056

To improve the performance of denoising algorithm for industrial radiographic testing ( RT) images, an optimized wavelet denoising algorithm using hybrid noise model ( WDHM) is proposed. Firstly, a hybrid noise model is constructed by analyzing the noise components to solve the problem of noise variance estimation when wavelet denoising is adopted for RT images. Then, a wavelet processing threshold is determined by the hybrid noise model, and noise in RT images is reduced by wavelet denoising. Meanwhile, a fixed-point median processing is used for eliminating image distortion caused by wavelet denoising. Comparing with conventional wavelet and Wiener filter denoising, the experimental results show that WDHM not only gets good denoising effectiveness, but also keeps a good balance between removing noise and preserving edge characteristics well.

关键词： radiographic image hybrid noise model wavelet denoising fixed point median edge preserving

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：