Register
 Email: Passwd 验 证: 换一张 Have you forgotten your password? Stay signed in Log In
 ALL Title Author Keyword Sponsors Type Publication date Submitted Time Subject Conference Name Source Categories KOS Subject Advisor ORCID Advanced
 IOE OpenIR  > 光电技术研究所博硕士论文  > 学位论文
 题名: 小波变换用于复杂背景下目标识别的研究 作者: 彭晓明 学位类别: 硕士 答辩日期: 2000 授予单位: 中国科学院光电技术研究所 授予地点: 中国科学院光电技术研究所 导师: 张启衡 关键词: 目标识别 ; 小波变换 ; 复杂背景 ; 仿射不变量 中文摘要: 本论文基于小波变换这一新的数学工具对复杂背景下目标识别这一重要课题进行了探索性研究。在电视跟踪系统中，能否对复杂背景下目标进行识别与提取将大大影响整个系统的跟踪性能。这个问题长久以来一直未能得到很好解决。本课题的目的就是针对这个问题进行探索性研究。小波变换作为一种数学工具有着广阔的应用前景。本文将小波变换与数字图象处理和模式识别理论相结合，并针对小波变换的运算上的复杂性及复杂背景的特点提出了切实可行的识别目标的方案，在研究中取得了阶段性的成果。即先对复杂背景使用分割算法以确定可能的目标区域，在此区域进行Mallat小波变换，然后利用仿射不变量理论完成对完整提取的目标的识别。仿真实验的结果表明了算法的可行性。同时，在广泛参考文献的基础上，对这一课题的后续研究提出了参考意见。 英文摘要: Based on a new mathematical tool, i.e. wavelet transform, this thesis deals with a research work on the important issue of target recognition in a complex background. It is well known that the tracking function of a TV tracking system in a complex background greatly depends on the results of target recognition. However, although it has been studied for many years by researchers, this problem is never really resolved. Therefore, the work discussed by this thesis is a meaningful one since it is a research work for resolving this problem. Wavelet transform has been attracting more and more attention in recent years since its importance as an effective mathematical tool has been recognized. In our research work, attempts are made to utilize wavelet transform, in combination with digital image processing and pattern recognition to resolve this problem. With regard to the computational complexity of wavelet transform and the features of a complex background, this thesis offers a reasonably target recognition method. Initial results have been achieved. In this work, an image segmentation algorithm is first introduced to locate the area of interest. And then, a wavelet transform with Mallat wavelet is applied to this area and the recognition is realized with the help of affine invariants. Experimental results have shown the effectiveness of the work. Moreover, pieces of advice are given to the research work to be done in the future. 语种: 中文 内容类型: 学位论文 URI标识: http://ir.ioe.ac.cn/handle/181551/41 Appears in Collections: 光电技术研究所博硕士论文_学位论文

 Files in This Item:
File Name/ File Size Content Type Version Access License
LW003197.pdf（1489KB）----限制开放View 联系获取全文

 Recommended Citation: 彭晓明. 小波变换用于复杂背景下目标识别的研究[D]. 中国科学院光电技术研究所. 中国科学院光电技术研究所. 2000.
 Service Recommend this item Sava as my favorate item Show this item's statistics Export Endnote File Google Scholar Similar articles in Google Scholar [彭晓明]'s Articles CSDL cross search Similar articles in CSDL Cross Search [彭晓明]‘s Articles Related Copyright Policies Null Social Bookmarking
 文件名： LW003197.pdf 格式： Adobe PDF

 您对该条目有什么异议，请填写以下表单，管理员会尽快联系您。 `内 容：` Email： * 单位： 验证码： 刷新
 您在IR的使用过程中有什么好的想法或者建议可以反馈给我们。 `标 题：` * `内 容：` Email： * 验证码： 刷新

Items in IR are protected by copyright, with all rights reserved, unless otherwise indicated.

 Copyright © 2007-2018  中国科学院光电技术研究所 - Feedback Powered by CSpace