检索结果-内蒙古大学图书馆

3rd iasted international conference on signal processing, pattern recognition, and applications

作者： Jie, Wu Kamath, Markad V. Poehlman, Skip Department of Computing and Software Department of Medicine McMaster University Hamilton Ont. L8S 4K1 Canada

ISBN: (纸本)0889865477

With the development of computer graphic rendering software and the appearance of more and more photorealistic pictures, the need for automatically distinguishing Computer Generated Images from real photographs has become of particular interest to criminal and forensic science investigators. Previous studies have been based on wavelet statistics, while in our study we examined several visual features derived from colour, edge, saturation and texture features extracted with the Gabor filter. Based on the feature extraction, we examined three commonly-used classifiers: non-linear SVM, Weighted k-nearest neighbors and Fuzzy k-nearest neighbors with 1,044 Computer Generated Images and 1,114 photographs downloaded from open sources. Finally we report on the comparative analysis of the results of these automatic classifications: Gabor filter based texture feature shows very promising results (99% for photo and 91.5% for CGI) while visual features show some abilities to perform differentiation.

关键词： Computer graphics

来源：评论

学校读者我要写书评

暂无评论

A license plate locating algorithm based on multiple Gauss filters and morphology mathematics

A license plate locating algorithm based on multiple Gauss f...

引用

3rd iasted international conference on signal processing, pattern recognition, and applications

作者： Zheng, Ma Jingzhong, Yang No. 4 North Jianshe Road Chengdu 610054 China

ISBN: (纸本)0889865477

In this paper, we propose a new automatic located algorithm of license plate based on multiple Gauss filters and morphology mathematics, there are two steps in our algorithm, first, to locate the license plate coarsely from a car image based on multiple Gauss filters, it contains three steps, firstly, to compute the vertical difference of the standardized image and then to get the horizontal projective curve of the difference image, secondly, to filter the curve by a window gauss filter and then to transform the smooth horizontal projective curve by another Gauss function, thirdly, to locate the license plate coarsely by seeking the vales of the transformed curve. Second step, to extract the license plate accurately based on morphology mathematics from the coarse license plate, it contain three steps, firstly, to compute the vertical difference of the coarse license plate and then to process the difference image by morphology operation, secondly, to get the vertical projective curve of the difference image and then to smooth the curve by window gauss filter, thirdly, the accurate position of the license plate can be got by seeking the wave of maximal area of the curve. Finally, the accurate license plate can be got after these steps, the experimental results have proved that this is an effective, robust and fast method to locate the license plate from a car image captured from different backgrounds.

关键词： License plates (automobile)

来源：评论

学校读者我要写书评

暂无评论

Markov family models and its applications

Markov family models and its applications

引用

4th iasted international conference on Circuits, signals, and Systems

作者： Yuan, Lichi Jiangxi Univ Fianance & Econ Sch Informat Technol Nanchang 330013 Peoples R China

ISBN: (纸本)9780889866058

Hidden Markov model is a statistical model which has been applied successfully to speech recognition and natural language processing. However, it is based on three assumptions: (1) limited horizon, (2) time invariant (stationary), (3) the independence assumption of observations within a state. these assumptions are too strong from the view of the statistics and are also unreaistic. In order to overcome the defects of the classical HMM, Markov Family model, a new statistical model is introduced in this paper. We have successfully applied Markov Family model to speech recognition and proposed a novel speech recognition model which integrates the frame and segment based acoustic modeling techniques. the speaker independent continuous speech recognition experiments and the Part-of-Speech tagging experiments show that Markov Family models (MFMs) have higher performance than Hidden Markov models (HMMs).

关键词： Markov Family models Hidden Markov models Part-of-Speech tagging speech recognition

来源：评论

学校读者我要写书评

暂无评论

Face recognition under pose variations

引用

JOURNAL OF thE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MAthEMATICS 2006年第6期343卷 596-613页

作者： Du, Shan Ward, Rabab Univ British Columbia Dept Elect & Comp Engn Vancouver BC V6T 1Z4 Canada

In recent years, face recognition has attracted significant attention from the research and commercial communities. Because of the wide variation in face images, face recognition for real applications remains a very challenging problem. A large number of face recognition algorithms, along with their modifications, have been proposed over the past three decades. this paper presents a review of the typical algorithms that aim to overcome one of the main obstacles in the face recognition task, the variations in face pose. these algorithms are categorized and briefly described. Future research challenges in pose-invariant face recognition are also identified. (C) 2006 the Franklin Institute. Published by Elsevier Ltd. All rights reserved.

关键词： face recognition pose variation biometrics pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Image enhancement using multiple video frames and non-uniform fluency interpolation

Image enhancement using multiple video frames and non-unifor...

引用

4th iasted international conference on Communications, Internet, and Information Technology

作者： Hirano, K Kameyama, K Ohmiya, Y Toraichi, K Univ Tsukuba Masters Program Sci & Engn Tsukuba Ibaraki 305 Japan

ISBN: (纸本)0889865132

In this paper, we propose a method of image interpolation for resolution enhancement using multiple low resolution video frames. this method utilizes the local shift vector due to object movement among a multiple frame set and interpolates pixels by using a non-uniform Fluency interpolation function for highquality super resolution. We compare the enhanced images interpolated by the proposed method and the conventional methods, and show the superiority of the proposed method in subjective image quality.

关键词： signal processing applications resolution enhancement multiple video frames non-uniform interpolation

来源：评论

学校读者我要写书评

暂无评论

Spatial Normalization Fourier Descriptor

Spatial Normalization Fourier Descriptor

引用

2nd iasted international Multi-conference on Automation, Control, and Information Technology - signal and Image processing

作者： Haitao, Jia Mei, Xie Electronics Engineering Department University of Electronic Science and Technology of China No.4 North Jianshe Road Chengdu 610054 China

ISBN: (纸本)0889864772

this paper presents a novel normalization for the Fourier descriptor, named as Spatial Normalization Fourier Descriptor. this algorithm normalizes the contour in the spatial domain while the traditional Fourier descriptor does in the other domains, such as the frequency domain. this invent greatly improve the performance of the Fourier descriptor, and provides high robust and division degree. It will greatly impulse the pattern recognition of shape and in the so many applications for the flourier descriptor it will be highlighted. Lastly the experiment verifies it and it outperform the traditional Fourier descriptor.

关键词： Fourier transforms

来源：评论

学校读者我要写书评

暂无评论

Linear time construction of vectorial object boundaries

Linear time construction of vectorial object boundaries

引用

6th iasted international conference on signal and Image processing

作者： Lovell, N Fenwick, J Griffith Univ Sch CIT Inst Intelligent & Integrated Syst Brisbane Qld 4111 Australia

ISBN: (纸本)0889864349

Classical alaorithms for identifying straight edges within an image, such as the Hough transform, run in O(n(2)) time which has been improved to O(nlog(2) (n)) by other heuristic algorithms. By focusing on 8-connected space rather than Euclidean space, we present a method for classifying a connected list of pixels as either straight or non-straight in constant time. We then build on this method to enable a heuristic algorithm to identify the straight edges within an image in linear time. Although the improvement from O(nlog(2)(n)) to O(n) time does not appear great we find that our algorithm is faster than others even on small images due to the large amount of data required to represent an image. As images become larger or as the number of straight edges in each image increases our improvement becomes more pronounced. Our algorithm then enables fast construction of vectorial object boundaries and medial axes which, in turn, enables efficient object recognition. We illustrate this with images from RoboCup.

关键词： computer vision artificial intelligence applications image segmentation pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Bayesian MCMC for biometric person authentication incorporating on-line signature trajectories

Bayesian MCMC for biometric person authentication incorporat...

引用

Proceedings of the iasted international conference on signal processing, pattern recognition and applications

作者： Kondo, Mitsuru Muramatsu, Daigo Sasaki, Masahiro Matsumoto, Takashi Department of Electrical Engineering Waseda University 3-4-1 Ohkubo Shinjuku-ku Tokyo Japan

ISBN: (纸本)0889863784

Authentication of individuals is rapidly becoming an important issue. the authors have previously proposed a pen-input online signature verification algorithm. the algorithm considers writer's signature as a trajectory of pen-position, pen-pressure and pen-inclination which evolves over time, so that it is dynamic and biometric. In our previous work, genuine signatures were separated from forgery signatures in a linear manner. this paper proposes a new algorithm which performs nonlinear separation using Bayesian MCMC (Markov Chain Monte Carlo). A preliminary experiment is performed on a database consisting of 1825 genuine signatures and 4117 skilled forgery signatures from fourteen individuals. FRR 0.81% and FAR 0.87% are achieved. Since no fine tuning was done, this preliminary result looks very promising.

关键词： Image analysis

来源：评论

学校读者我要写书评

暂无评论

ICICS-PCM 2003 - Proceedings of the 2003 Joint conference of the 4th international conference on Information, Communications and signal processing and 4th Pacific-Rim conference on Multimedia

ICICS-PCM 2003 - Proceedings of the 2003 Joint Conference of...

引用

Joint conference of the 4th international conference on Information, Communications and signal processing and 4th Pacific-Rim conference on Multimedia, ICICS-PCM 2003

ISBN: (纸本)0780381858

the proceedings contain 407 papers. the topics discussed include: block image retrieval based on a compressed linear Quadtree;a low complexity 2-power transform for video compression;a motion compensation method using least squares motion estimation filter in wavelet domain;a histogram based adaptive vector filter for color image restoration;color appearance-based approach to robust tracking and recognition of multiple people;computational video editing model based on optimization with constraint-satisfaction;on the implementation of melody recognition on 8-bit and 16-bit microcontrollers;automatic localization and tracking of moving objects using adaptive snake algorithm;day markings detection in natural photo with morphological method;a user-attention based focus detection framework and its applications;video quality evaluation for wireless transmission with robust header compression;a novel low-complexity packetization method for fine-granularity scalable (FGS) video streaming;and cluster-dependent feature transformation with divergence-based out-of-handset rejection for robust speaker verification.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ICICS-PCM 2003 - Proceedings of the 2003 Joint conference of the 4th international conference on Information, Communications and signal processing and 4th Pacific-Rim conference on

ICICS-PCM 2003 - Proceedings of the 2003 Joint Conference of...

引用

Joint conference of the 4th international conference on Information, Communications and signal processing and 4th Pacific-Rim conference on Multimedia, ICICS-PCM 2003

ISBN: (纸本)0780381858

关键词：

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：