检索结果-内蒙古大学图书馆

Congress on image and Signal processing, CISP

作者： Long Liu Zhanhui Wang Qijun Song Song Hong Xi''an University of Technology Xi'an China China Electronic Systems Engineering Corporation Beijing China Naval University of Engineering Wuhan China Xi''an Shiyou University Xi'an China

This paper presents an efficient search algorithm utilizes the relationship between local motion similarity and the variation degree of motion vector. The main feature of proposed algorithm are: the motion vectors are classified as the unchanged, the slightly changed and the greatly changed motion vector according to corresponding local motion similarity; then different search schemes are adopted for different kind motion vectors. The experimental results show the proposed algorithm has a significant computational speedup compared with other popular fast algorithms, but offers a similar, even better performance.

关键词： Classification algorithms Support vector machine classification Signal processing algorithms Motion estimation Algorithm design and analysis Least squares approximation Diamond-like carbon

来源：评论

学校读者我要写书评

暂无评论

Geometric Distortion Insensitive image Watermarking in Affine Covariant Regions

引用

IEEE Transactions on systems, Man, and Cybernetics, Part C (Applications and Reviews) 2010年第3期40卷 278-286页

作者： xinbo Gao Cheng Deng Xuelong Li Dacheng Tao School of Electronic Engineering Xidian University Xi'an China State Key Laboratory of Transient Optics and Photonics Xi'an Institute of Optics and Precision Machanics Chinese Academy and Sciences Xi'an China School of Computer Engineering Nanyang Technological University Singapore Singapore

Feature-based image watermarking schemes, which aim to survive various geometric distortions, have attracted great attention in recent years. Existing schemes have shown robustness against rotation, scaling, and translation, but few are resistant to cropping, nonisotropic scaling, random bending attacks (RBAs), and affine transformations. Seo and Yoo present a geometrically invariant image watermarking based on affine covariant regions (ACRs) that provide a certain degree of robustness. To further enhance the robustness, we propose a new image watermarking scheme on the basis of Seo's work, which is insensitive to geometric distortions as well as common image processing operations. Our scheme is mainly composed of three components: 1) feature selection procedure based on graph theoretical clustering algorithm is applied to obtain a set of stable and nonoverlapped ACRs; 2) for each chosen ACR, local normalization, and orientation alignment are performed to generate a geometrically invariant region, which can obviously improve the robustness of the proposed watermarking scheme; and 3) in order to prevent the degradation in image quality caused by the normalization and inverse normalization, indirect inverse normalization is adopted to achieve a good compromise between the imperceptibility and robustness. Experiments are carried out on an image set of 100 images collected from Internet, and the preliminary results demonstrate that the developed method improves the performance over some representative image watermarking approaches in terms of robustness.

关键词： Watermarking Robustness image processing Videos Optical distortion Optical filters Clustering algorithms Degradation image quality Internet

来源：评论

学校读者我要写书评

暂无评论

Nonlinear filtering with multiple packet dropouts

Nonlinear filtering with multiple packet dropouts

引用

International Conference on image Analysis and Signal processing, IASP

作者： Jinguang Chen Jiancheng Li Lili Ma VIPS Laboratory School of Electronic Engineering Xidian University Xi'an China School of Computer Science Xi'an Polytechnic University Xi'an China

This paper considers the nonlinear system filtering with packet dropouts. We assume that the packet arrived rate is known in advance but the sequence of packet dropouts is unknown. At first, we use the probability-weighted method to achieve a pseudo measurement sequence, and every pseudo measurement is the weighted value of the measurements acquired at the current time step and the prior time step. Some classical nonlinear filtering methods can be used via the pseudo measurement sequence and the dynamic equation of the system, and then the pseudo measurement unscented Kalman filter (PM_UKF) and the pseudo measurement particle filter (PM_PF) are given. This pseudo measurement sequence can be also used in the linear system, and its time complexity is lower than that of Sun's optimal filter at this time. Simulation results show the effectiveness of the proposed algorithms.

关键词： Filtering Time measurement Current measurement Particle measurements Nonlinear systems Weight measurement Nonlinear dynamical systems Nonlinear equations Particle filters Linear systems

来源：评论

学校读者我要写书评

暂无评论

A new adaptive filtering algorithm based on discrete wavelet transforms

A new adaptive filtering algorithm based on discrete wavelet...

引用

Congress on image and Signal processing, CISP

作者： Cunqian Feng Linrang Zhang xiaoping Hui Xidian University Xian Shaanxi CN National Laboratory of Radar Signal Processing Xidian University Xi'an China Institute of Missile AFEU Xi'an China

The wavelet transform domain LMS algorithm are integrated with variable step-size LMS algorithm, from which a new adaptive filtering algorithm is presented based on discrete wavelet transforms (NDWT-LMS). The algorithm can reduce the self-correlation of input signals effectively and can overcome the conflict between high convergence rate and low steady-state error in LMS algorithm which leading by fixed step-size, The computer simulation results indicate that the new algorithm has higher convergence rate and lower steady-state error to compared with LMS algorithm, it can be applied effectively in the adaptive systems.

关键词： Signal processing algorithms Convergence Least squares approximation Discrete wavelet transforms Adaptive filters Algorithm design and analysis

来源：评论

学校读者我要写书评

暂无评论

Block Matching Algorithm based on RANSAC Algorithm

Block Matching Algorithm based on RANSAC Algorithm

引用

International Conference on image Analysis and Signal processing, IASP

作者： Kexiang Liu Jie Qian Ruike Yang School of science Xidian University Xi'an China

A new type of real-time image stabilization system is introduced in present paper. RANSAC Algorithm is used in the system. The accuracy and speed of image stabilization is improved effectively. A low-cost and high-performance solution of real-time digital image stabilization system is given in this paper. Video stabilization working principle is discussed and the moving image mathematical model is set up. The RANSAC Algorithm can reduce the amount of calculation and the error rate of block matching. Simulation of the real-time image stabilization system is accomplished. The result shows the new model is effective; the power SNR of the video is raised about 8-10 dB.

关键词： Motion estimation Partitioning algorithms Digital images Real time systems Error analysis Motion compensation Mathematical model Power system modeling Digital signal processing US Department of Transportation

来源：评论

学校读者我要写书评

暂无评论

A Fruit Size Detecting and Grading System Based on image processing

A Fruit Size Detecting and Grading System Based on Image Pro...

引用

2010 Second International Conference on Intelligent Human-Machine systems and Cybernetics(第二届智能人机系统与控制论国际学术会议 IHMSC 2010)

作者： Hongshe Dang Jinguo Song Qin Guo School of Electric and Information Engineering Shaanxi University of Science and Technology Xi'an CityShaanxi710021 China

this paper presents a fruit size detecting and grading system based on image processing. After capturing the fruit side view image, some fruit characters is extracted by using detecting algorithms. According to these characters, grading is realized. Experiments show that this embedded grading system has the advantage of high accuracy of grading, high speed and low cost. It will have a good prospect of application in fruit quality detecting and grading areas.

关键词： embedded system size detecting fruit grading image processing

来源：评论

学校读者我要写书评

暂无评论

An Iterative Surface Evolution Algorithm for Multiview Stereo

引用

EURASIP JOURNAL ON image AND VIDEO processing 2010年第unknown期2010卷 274269-274269页

作者： xi, Yongjian Duan, Ye Univ Missouri Dept Comp Sci Columbia MO 65211 USA

We propose a new iterative surface evolution algorithm for multiview stereo. Starting from an embedding space such as the visual hull, we will first conduct robust 3D depth estimation (represented as 3D points) based on image correlation. A fast implicit distance function-based region growing method is then employed to extract an initial shape estimation based on these 3D points. Next, an explicit surface evolution will be conducted to recover the finer geometry details of the recovered shape. The recovered shape will be further improved by several iterations between depth estimation and shape reconstruction, similar to the Expectation Maximization (EM) approach. The experiments on the benchmark datasets show that our algorithm can obtain high-quality reconstruction results that are comparable with the state-of-art methods, with considerable less computational time and complexity.

关键词： image processing THREE-dimensional imaging COMPUTER algorithms ITERATIVE methods (Mathematics) EVOLUTIONARY computation EMBEDDED computer systems image quality analysis image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Feature extraction of hyperspectral images based on preserving neighborhood discriminant embedding

Feature extraction of hyperspectral images based on preservi...

引用

International Conference on image Analysis and Signal processing, IASP

作者： Jinhuan Wen Zheng Tian Hongwei She Weidong Yan School of Science Northwestern Polytechnical University Xi'an China State Key Laboratory of Remote Sensing Science Institute of Remote Sensing Applications Chinese Academy and Sciences Beijing China

A novel manifold learning feature extraction approach-preserving neighborhood discriminant embedding (PNDE) of hyperspectral image is proposed in this paper. The local geometrical and discriminant structure of the data manifold can be accurately characterized by within-class neighboring graph and between-class neighboring graph. Unlike manifold learning, such as LLE, Isomap and LE, which cannot deal with new test samples and images larger than 70×70, the method here can process full scene hyperspectral images. Experiments results on hyperspectral datasets and real-word datasets show that the proposed method can efficiently reduce the dimensionality while maintaining high classification accuracy. In addition, only a small amount of training samples are needed.

关键词： Feature extraction Hyperspectral imaging Hyperspectral sensors Remote sensing Testing Clustering algorithms Layout Data mining Principal component analysis Learning systems

来源：评论

学校读者我要写书评

暂无评论

Realization and Optimization of Face Detection Algorithm Based on DSP

Realization and Optimization of Face Detection Algorithm Bas...

引用

International Conference of Information Science and Management Engineering (ISME)

作者： Ling-bin Kong Jin-ye Peng Zhao-qiang xia Yu Lian Shao-chong Fan Dept. of Electron. & Inf. Northwestern Polytech. Univ. Xi'an China

It introduced the principle and the process of human face detection algorithm, as well as its implementation and optimization using DSP. It applied AdaBoost algorithm to detect human face. Before the detection, some methods were used to optimize original image data, such as image scale, median filter, histogram equalization and edge detection. After the detection, it judged and modified the results to improve the detection accuracy further. Then it used many optimization methods to meet the real-time requirement. Experimental results show that, this DSP system can meet real-time requirement even if it detects faces in 720×576 high-resolution images, at the same time it has a high accuracy and low miss rate in a complex environment.

关键词： Face Digital signal processing Face detection Real time systems Classification algorithms Accuracy Pixel

来源：评论

学校读者我要写书评

暂无评论

The creation of a hue-constancy space for color management system

The creation of a hue-constancy space for color management s...

引用

International Conference on Computer Application and System Modeling (ICCASM)

作者： Xue-mei Luo Yi-feng Wang Hai-hong Zheng Institute of Computer Peripherals Xidian University Xi'an China

The CIELAB space is known as hue nonconstancy. This is why gamut mapping in constant hue angle in CIELAB space may not give satisfactory performances. To solve this problem, a new color space tLAB was constructed, which is used to replace CIELAB in color management system. Firstly, the hue in CIELAB is corrected according to Munsell renotation data, and the hue-constancy tLAB color space is created. Then 3D look up table is used to characterize the nonlinear relationship between CIELAB and tLAB. Finally, an implementation scheme for color management with a low spatio-temporal cost is presented. Experiments show that the results of gamut mapping in the new tLAB space gain an advantage over the traditional ones. In addition, the color management using tLAB color space has real time performance and universality.

关键词： image color analysis systems modeling Computer applications Signal processing algorithms Printers Extraterrestrial measurements Color

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：