检索结果-内蒙古大学图书馆

Asia International Conference on Modeling & Simulation

作者： Zohre Foroushi Ali Asghar Beheshti Shirazi Image Processing Lab Iran University of Science and Technology Tehran Iran

ISBN: (纸本)9781424471966;9780769540627

Improvement of performance in sub-band coding system that style in image coding system, is very important. In the coding systems, due to the filter bank that used, coding schemes are classified into two classes, one might have the pair-wise mirror-image property in their filter banks, and performs symmetrically regardless of the sign of the autocorrelation, and the other including JPEG2000 that uses bi-orthogonal 9/7-tap Daubechies filters for lossy compression, has not the mirror image property and performs asymmetrically with inferior performance for negative autocorrelation. In this paper, we want with modulating the negatively-correlated signal sequence by the alternating sign signal with unity magnitude to convert them into positively correlated-sequence. The experimental results for test images show that little gain was obtained by for natural images, since they have small amount of energy in the high frequency bands in horizontal and vertical directions. However 1.5-2dB improvement of PSNR has been obtained for images such as Fingerprint, which have a large amount of energy in high frequency range.

关键词： Performance loss Transform coding image coding Filter bank Autocorrelation Frequency Mirrors image converters Testing PSNR

来源：评论

学校读者我要写书评

暂无评论

An automatic face indexing framework for actor-based video services in an IPTV environment

An automatic face indexing framework for actor-based video s...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Jae Young Choi Wesley De Neve Seung-Ho Lee Yong Man Ro Image and Video Systems Lab Korea Advanced Institute of Science and Technology South Korea

ISBN: (纸本)9781424443147

Automatic face indexing is a promising technique for personalized IPTV applications. This paper proposes a novel framework that makes use of an STB's Internet connection in order to realize face indexing for a personal media library. In particular, given a drama or movie title, actor names are first retrieved from a drama or movie information web service. The obtained actor names are subsequently used to acquire training and gallery face images from the Internet. More than 20,000 video frames collected from five drama video sequences were used to evaluate our face indexing framework. Experimental results show that the obtained face indexing accuracy is promising for realizing actor-based video services in an IPTV environment.

关键词： Indexing IPTV Face detection US Department of Transportation Internet Motion pictures Libraries Information retrieval Video sequences Telecommunications

来源：评论

学校读者我要写书评

暂无评论

Modeling of McKibben Pneumatic Artificial Muscles Using Optimized Echo State Networks

Modeling of McKibben Pneumatic Artificial Muscles Using Opti...

引用

The 8th World Congress on Intelligent Control and Automation(第八届智能控制与自动化世界大会 WCICA 2010)

作者： Hanying Zhou Yongji Wang Kexin Xing Key Lab for Image Processing &Intelligent Control Department of Control Science and Engineering Huazhong University of Science and Technology

In conventional techniques for modeling Pneumatic artificial muscle, there are difficulties such as poor knowledge of the process, inaccurate process or complexity of the resulting mathematical model. Trying to solve these problems, this study investigates the method of establishing the model using a novel network—Echo State Network (ESN). We introduce the mechanism of this net and apply it to our modeling work. The relevant parameters of the net were optimized using Particle Swarm Optimization (PSO). Then we get the simulation results which reveal that it can get quite satisfactory results.

关键词： Training Trajectory Muscles Data models Mathematical model Force Artificial neural networks

来源：评论

学校读者我要写书评

暂无评论

Real-time driver fatigue detection based on simplified landmarks of AAM

Real-time driver fatigue detection based on simplified landm...

引用

International Conference on Apperceiving Computing and Intelligence Analysis, ICACIA

作者： Hua-Zhi Dong Mei Xie Image Processing and Information Security Lab School of Electronic Engineering University of Electronic Science and Technology Chengdu China

Using Active Appearance Model to detect driver fatigue has been proposed in past research. This paper proposes a rapid method of driver fatigue detection by applying Active Appearance Model with simplified landmarks only around eyes, and also proposes to convert the eye contour aspect ratio into PERCLOS to judge the degree of the driver fatigue. Compared to the original method, this method reduces redundant facial texture information, and accelerates the speed of eye state detection while improving detection accuracy rate of driver fatigue. The experiments results show that this method is fast and effective that can be used in real-time detection.

关键词： Active appearance model Fatigue Driver circuits Face Eyelids Fitting Training

来源：评论

学校读者我要写书评

暂无评论

Semantic Detection of Adult image Using Semantic Features

Semantic Detection of Adult Image Using Semantic Features

引用

International Conference on Multimedia and Ubiquitous Engineering (MUE)

作者： Jae-Hyun Jeon Se Min Kim Jae-Young Choi Hyun Suk Min Yong-Man Ro Image and Video Systems Lab Department of Electrical Engineering Korea Advanced Institute of Science and Technology Daejeon South Korea

Recently, in the fields of internet and social networking, the classification and filtering of naked images has been receiving a significant amount of attention. In this paper, we propose a novel naked image classification which can make effective use of semantic features of a naked image. In addition, a novel measurement, termed accumulated distance ratio (ADR), is proposed in order to systematically analyze the effect of semantic features on improving classification performance, compared to the approach relying on low-level visual features. Extensive experiments have been carried out to assess the effectiveness of semantic features in naked image classification with realistic and challenging data set. The experimental result of the proposed approach using semantic features, for challenging data set, shows improvement up to 14% than the approach using low-level visual feature. Further, the proposed ADR measure has proven to be useful measure for analyzing the effect of semantic features for naked image classification.

关键词： Semantics Support vector machines Visualization Training image classification Testing Training data

来源：评论

学校读者我要写书评

暂无评论

Representation of videokeratoscopic height data using a set of discrete tchebichef orthogonal polynomials

International Journal of Signal Processing, Image Processing...

引用

International Journal of Signal Processing, image Processing and Pattern Recognition 2010年第3期3卷 13-28页

作者： Zhu, Hongqing Liu, Min Shu, Huazhong Zhang, Jin Zhang, Hui Department of Electronics and Communications Engineering East China University of Science and Technology Shanghai 200237 China Lab of Image Science and Technology School of Computer Science and Engineering Southeast University Nanjing 210096 China

The continuous orthogonal polynomials, such as Zernike and pseudo-Zernike, are often used as an expansion of corneal height data. However, the use of continuous polynomials has some limitations due to the discretization. It is because that the integrals are usually approximated by discrete summations, and this process not only leads to numerical errors, but also severely affects some analytical properties such as rotation invariance, orthogonality, etc. To overcome these drawbacks, this paper presents a methodology for decomposing corneal height data into discrete orthogonal Tchebichef polynomials. Tchebichef polynomials, which are a product of angular functions and radial Tchebichef polynomials, are orthogonal in the discrete coordinate. Therefore, the approximation error caused by discretization can be avoided, and the analytical property can be well preserved. Examples of modeling corneal elevation are provided for simulation corneas, real normal corneas, and real abnormal corneas. The experimental results show that the proposed discrete Tchebichef polynomials have better surface representation capability than Zernike polynomials or pseudo-Zernike polynomials, and have more robust fitting for the level of noise found in current videokeratoscopes, so that they can be used as an alternative to fit the corneal surface.

关键词： Polynomials

来源：评论

学校读者我要写书评

暂无评论

Wavelet filter banr selection based on power spectral density

Wavelet filter banr selection based on power spectral densit...

引用

International Conference on Computer and Automation Engineering, ICCAE

作者： Zohre Foroushi Mijid R. Ardestini Ali Asghire Beheshti Shirizi Image Processing Lab Iran University of Science and Technology Tehran Tehran Iran Imige Processing Lib School of Electricil Eng. Ir in University of Science ind Technology Tehrin Irin

Filter banr design for wavelet compression schemes is very important. Although, JPEG2000 standard adopted bi-orthogonal 9/7-tap Daubechies wavelet, it is experimentally shown that this banr is well suited for natural images, which they have small amount of energy in the high frequency in horizontal and vertical directions. In this paper, we introduce a method for filter banr design according to power spectral density function of input source. By this method we propose a new efficient 9/7 wavelet filter banr for image compression applications, whose coefficients are adaptively chosen according to power spectral density function of the input image. The experimental results for images by substituting our filter banr in the JPEG2000 standard coding mode show that little gain was obtained by for natural images, since they have small amount of energy in the high frequency bands in horizontal and vertical directions. However, 0.5–1 dB improvement of PSNR has been obtained for images such as Fingerprint, which have a large amount of energy in high frequency range.

关键词： image coding Filter bank Discrete wavelet transforms Bit rate image reconstruction Transform coding Frequency Density functional theory Signal synthesis Band pass filters

来源：评论

学校读者我要写书评

暂无评论

Texture analysis in quantitative osteoporosis assessment: Characterizing microarchitecture

Texture analysis in quantitative osteoporosis assessment: Ch...

引用

IEEE International Symposium on Biomedical Imaging

作者： Alexander Valentinitsch Janina Patsch Dirk Mueller Franz Kainberger Georg Langs Computational Image Analysis and Radiology Lab Medical University of Vienna Austria Clinical Science Philips Research CT USA Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology USA

ISBN: (纸本)9781424441259

The microarchitecture of the trabecular bone is an highly informative feature for osteoporosis assessment. High resolution peripheral quantitative computed tomography permits its in-vivo observation at a resolution of 82 μm. In this paper we propose an approach that assesses bone microarchitecture based on texture features extracted from the trabecular bone. The method is based on three-dimensional texture features as local descriptors of the structure in the trabecular bone. A clustering in the feature space indicates characteristic classes of microarchitecture that are repeatedly detected across subjects. The distribution of those classes allows for a differentiation between osteoporotic and healthy subjects. We report initial results for the repeatability of the method and its performance for the differentiation of healthy and osteoporotic subjects.

关键词： Osteoporosis Microarchitecture Feature extraction Cancellous bone Biomedical imaging image texture analysis image analysis Computed tomography Bone diseases Data mining

来源：评论

学校读者我要写书评

暂无评论

A new roadmap constitution method based on dividing grid and level-set

A new roadmap constitution method based on dividing grid and...

引用

International Symposium on Intelligence Information Processing and Trusted Computing

作者： Li, Shidong Ding, Mingyue Cai, Chao Institute for Information Engineering of Hubei University for Nationalities Enshi Hubei China Institute for Pattern Recognition and Artificial Intelligence National Lab. for Multi-spectral Information Processing Technologies HUST Wuhan China College of Life Science and Technology Image Processing and Intelligent Control Key Laboratory of Education Ministry of China HUST Wuhan China

ISBN: (纸本)9780769541969

Roadmap methods were widely used in route planning fields, both for robots and unmanned aircrafts. Traditional roadmap is constituted by connecting the vertexes of convex obstacle, which is related to the locations of start and goal of route, so the roadmap can not be reused when anyone of start and goal changed. Absence of reusability reduces the efficiency of route planning by using roadmap. A new roadmap constitution method was proposed in this paper, which is build on dividing the 2D configuration space into multi-scale grids and setting nodes of roadmap on grid boundary using Level-Set method, same method was used to construct the map cells of roadmap between any two nodes lays on same grid . The roadmap constituted with new method can be reused when the start or goal was changed;it is efficient for replanning problem. © 2010 IEEE.

关键词： Reusability

来源：评论

学校读者我要写书评

暂无评论

Classification of hyperspectral images by using morphological attribute filters and independent component analysis

Classification of hyperspectral images by using morphologica...

引用

Workshop on Hyperspectral image and Signal Processing

作者： Mura, Mauro Dalla Villa, Alberto Benediktsson, Jon Atli Chanussot, Jocelyn Bruzzonea, Lorenzo Department of Information Engineering and Computer Science University of Trento Via Sommarive 14 I-38123 Povo Trento Italy Faculty of Electrical and Computer Engineering University of Iceland Hjardarhaga 2-6 101 Reykjavik Iceland GIPSA-lab Signal and Image Dept. Grenoble Institute of Technology - INP 961 rue de la Houille Blanche 38402 Grenoble Cedex France

ISBN: (纸本)9781424489077

In this paper, a technique based on Independent Component Analysis (ICA) and morphological attribute filters is presented for the classification of high geometrical resolution hyperspectral images. The ICA is computed instead of the conventional principal component analysis (PCA) in order to better model the information in the hyperspectral image. The spatial characteristics of the objects in the scene are modeled by different multi-level attribute filters. Moreover, a method for increasing the robustness of the analysis based on a decision fusion strategy is proposed. A hyperspectral high resolution image acquired over the city of Pavia (Italy) was considered in the experiments. ©2010 IEEE.

关键词： Independent component analysis

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：