CASIA OpenIR  > 毕业生  > 硕士学位论文
Thesis Advisor刘迎建
Degree Grantor中国科学院自动化研究所
Place of Conferral中国科学院自动化研究所
Degree Discipline模式识别与智能系统
Keyword指纹鉴别 直接灰度提取 细节点 识别 特征抽取 图象处理匹配 Fingerprint Verification Direct Gray-scale Extraction Mintiae Recognition Feature Extraction Image Processing Matching
Abstract本文研究了一种自动指纹鉴别系统。自动指纹鉴别系统利用了人的活体指纹 的稳定性和特定性,可以应用到大多数需要进行个人身份鉴定的场合,如身份验 证,门禁系统,银行系统等等领域。自动指纹鉴定具有很高的安全性,对自动指 纹鉴别系统的研究具有非常重要的意义。 本文主要从五个方面对系统进行了研究: (1)从实际应用的角度,进行了系统的整体设计 (2) 比较了指纹图象处理的方法和探讨了实际存在的问题,采用了直接灰 度提取的方法对指纹图进行纹线跟踪和细节点提取。 (3) 研究了细节点集合的内在情况,并合理利用和抛弃了一些细节点的特 征。 (4) 比较了各种指纹细节点匹配算法,创新性的提出了一种基于三角邻域 模型的细节点匹配算法,该算法具有很高的鲁棒性,和准确率和快速 性。 (5) 150个指头每个取5幅一共750幅的指纹进行一对一匹配,正确拒绝 率7.8%,错误接收率2.5%,结果令人鼓舞。
Other AbstractAn automatic fingerprint verification system(AFVS) is presented in this paper. For its immutability and uniqueness, AFVS can be applied to most fields which needs personal identity, such as identity verification, door lock, bank verification etc. Research on AFVS is getting more and more urgent and important. Our study focus on five major parts: (1) Based on the applying environment and real usage, we discuss design of the system. (2) The methods processing the fingerprint image are discussed and compared in this paper. We take a Direct Gray-Scale Extraction Method by which we extract the minutiae and trace the skeleton of the fingerprint. (3) Based on the study of the minutiae set, we reasonably discard some features of traditional features of minutiae. (4) A kind of minutiae matching method based on "Triangle-Neighbor-Structure Model" was proposed originally. This method is robust, accurate and rapid. (5) An average of five samples from 150 fingers was collected to test our system. We obtained a very promising result, the True Rejection Rate is 7.8% and the False Acceptance Rate is 2.5%.
Other Identifier556
Document Type学位论文
Recommended Citation
GB/T 7714
黄开竹. 自动指纹鉴别系统的研究[D]. 中国科学院自动化研究所. 中国科学院自动化研究所,2000.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[黄开竹]'s Articles
Baidu academic
Similar articles in Baidu academic
[黄开竹]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[黄开竹]'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.