CASIA OpenIR  > 毕业生  > 硕士学位论文
Alternative TitleWriter Identification Based on Text-Independent Handwriting
Thesis Advisor王蕴红 ; 谭铁牛
Degree Grantor中国科学院研究生院
Place of Conferral中国科学院自动化研究所
Degree Discipline计算机应用技术
Keyword笔迹鉴别 文本独立 动态 Ica 融合 Writer Identification Text-independent Dynamic Ica Fusion
Abstract近年来,基于生物特征的身份识别技术取得了快速发展,手写笔迹鉴别技术是其中的重要研究方向,已经引起越来越多人的重视。文本独立笔迹鉴别技术因为其安全性高、普适性强、样本采集的无限制性等优点,成为笔迹鉴别技术研究中的热点,也是难点。本文总结了已有的文本无关和文本相关的笔迹鉴别方法和技术,提出了基于联合动态特征模型的笔迹鉴别方法、基于独立分量分析(ICA)的动态笔迹鉴别方法以及基于融合动态与静态特征的笔迹鉴别方法。本文主要贡献如下: [1] 分析了各种独立动态特征之间的联系,提出了基于联合动态特征统计模型的动态笔迹鉴别方法,大大深化了对原始动态特征进行有效信息的提取。 [2] 提出了利用独立分量分析(ICA)方法进行针对动态笔迹数据的笔迹鉴别的方法,使得笔迹动态信息的空间分布特征能够被用于笔迹鉴别中来。 [3] 提出了融合静态与动态特征的笔迹鉴别方法,并且在试验中改进了设定用户特性权值的方法。 总的来说,本文从不同角度对文本独立的笔迹鉴别问题进行分析,提出了出发点不同,但是效果良好的几种鉴别方法。
Other AbstractPersonal identification by handwriting is a very important research topic in biometrics. A wide variety of applications require reliable verification schemes to confirm an identity of an individual. Text-independent writer identification has gained much attention for its advantage of high security. In this paper, based on the analysis of recent research on writer identification by text-independent handwriting as well as text-dependent handwriting, we proposed some algorithms for writer identification by text-Independent handwriting. The main contributions of this paper are as follows: [1] By analyzing the common dynamic features of handwriting, an identification method based on compound dynamic features is proposed. This method extracts the relations between every two dynamic features, and can provide more information for writers identifying than the method proposed before. [2] A writer identification method based ICA(Independent Component Analysis) is proposed. ICA is employed to process dynamic handwriting data, which can make full use of the spatial distribution of the dynamic features. [3] Text-independent writer identification based on fusion of dynamic and static features is proposed. By this method, we has improved the identification accuracy and reduced the required data number.
Other Identifier200328014604129
Document Type学位论文
Recommended Citation
GB/T 7714
靳文峰. 文本独立笔迹鉴别方法研究[D]. 中国科学院自动化研究所. 中国科学院研究生院,2006.
Files in This Item:
File Name/Size DocType Version Access License
CASIA_20032801460412(2692KB) 暂不开放CC BY-NC-SAApplication Full Text
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[靳文峰]'s Articles
Baidu academic
Similar articles in Baidu academic
[靳文峰]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[靳文峰]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.

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