没有合适的资源?快使用搜索试试~ 我知道了~
指纹分类和识别算法的研究与实现1
需积分: 0 1 下载量 58 浏览量
2022-08-03
23:24:40
上传
评论
收藏 3.73MB PDF 举报
温馨提示
试读
88页
摘要随着互联网时代的到来,生物特征识别技术受到了社会各界的广泛关注,其中指纹识别技术一直都是国内外研究的热点和难点。越来越多的自动指纹识别产品被开发应用千人们的
资源详情
资源评论
资源推荐
隶南大·粤
硕士学位论文
指纹分类和识别算法的研究与实现
扣切大孚
硕士学位论文
指纹分类和识别算法的研究与实现
专业名称:模式识别与智能系统
研究生姓名:
尹婉琳
导师姓名:
叶棹教授
I删愀
RE
S
EARCH AND
IMPLEMENn气TION
OF
FINGERPRjNT
CLAS
SIFICATION
AND
IDENTIFICATION
A
Thesis
Submitted
to
S
outheast
UniVersity
For
the
Academic
De铲ee
of
Master
of
Engineering
BY
Yin
Wanlin
Supervised
by
Professor
Yje
Hua
School
ofAutomation
Southeast
UniVersi够
April
2015
翻脯
ll
曝曝呱胤圃
Y2921276
RESEARCH AND IMPLEMENTATION
OF FINGERPRINT CLASSIFICATION
AND IDENTIFICATION
A Thesis Submitted to
Southeast University
For the Academic Degree
of
Master
of
Engineering
BY
Yin Wanlin
Supervised by
Professor
Ye
Hua
School
of
Automation
Southeast University
April 2015
东南大学学位论文独创性声明
本人声明所呈交的学位论文是我个人在导师指导下进行的研究工作及取得
的研究成果。尽我所知,除了文中特别加以标注和致谢的地方外,论文中不包含
其他人已经发表或撰写过的研究成果,也不包含为获得东南大学或其它教育机构
的学位或证书而使用过的材料。与我一同工作的同志对本研究所做的任何贡献均
已在论文中作了明确的说明并表示了谢意。
研究生签名:三醚
日 期:
趁(:坐墨
东南大学学位论文使用授权声明
东南大学、中国科学技术信息研究所、国家图书馆有权保留本人所送交学位
论文的复印件和电子文档,可以采用影印、缩印或其他复制手段保存论文。本人
电子文档的内容和纸质论文的内容相一致。除在保密期内的保密论文和在技术保
护期限内的论文外,允许论文被查阅和借阅,可以公布(包括以电子信息形式刊
登)论文的全部内容或中、英文摘要等部分内容。论文的公布(包括以电子信息
形式刊登)授权东南大学研究生院办理。
研究生签名:三己丛
导师签名:业£益
日
期:边鉴:兰:呈
东南大学学位论文独创性声明
本人声明所呈交的学位论文是我个人在导师指导下进行的研究工作及取得
的研究成果。尽我所知,除了文中特别加以标注和致谢的地方外,论文中不包含
其他人已经发表或撰写过的研究成果,也不包含为获得东南大学或其它教育机构
的学位或证书而使用过的材料。与我一同工作的同志对本研究所做的任何贡献均
已在论文中作了明确的说明并表示了谢意。
研究生签名:三径抸长抹一
日期:万,
r
.
l.f,,8
东南大学学位论文使用授权声明
东南大学、中国科学技术信息研究所、国家图书馆有权保留本人所送交学位
论文的复印件和电子文档,可以采用影印、缩印或其他复制手段保存论文。本人
电子文档的内容和纸质论文的内容相一致。除在保密期内的保密论文和在技术保
护期限内的论文外,允许论文被查阅和借阅,可以公布(包括以电子信息形式刊
登)论文的全部内容或中、英文摘要等部分内容。论文的公布(包括以电子信息
形式刊登)授权东南大学研究生院办理。
研究生签名:三户竺旦少
L
导师签名:」过二产
日
期:三控
I5µ.8
摘要
摘要
随着互联网时代的到来,生物特征识别技术受到了社会各界的广泛关注,其
中指纹识别技术一直都是国内外研究的热点和难点。越来越多的自动指纹识别产
品被开发应用于人们的生活,提供身份鉴别及安全防护的功能。尽管目前在理论
研究上已经取得了显著的成绩,但基于大规模指纹数据库的自动指纹识别系统在
识别准确率和处理速度上都亟待进一步的提高。本文结合目前数字图像处理技术
和模式识别技术的发展,深入研究了指纹识别的关键算法,主要的工作和创新总
结如下:
1.指纹图像预处理方面。在分析和研究了前人成果的基础上,实现了指纹
预处理算法中的关键步骤,并着重改进了直方图均衡化、方向场计算和图像增强
方法。显著增强了脊线和谷线的对比度,保留了奇异区的方向变化规律,提高了
指纹图像的清晰度,为特征提取等操作的顺利进行奠定了基础。
2.指纹图像分类方面。针对由于采集仪传感器面积小而无法提取三角点这
一分类特征的不足,研究并提出了一种包括分类预处理和多级分类两个步骤的指
纹分类方法。在分类预处理阶段,根据中心点附近的全局特征在指纹摆正时具有
可分类性的特点,首先采用拟合中位线法和最小外接椭圆法确定指纹的倾斜方向,
再通过仿射变换对指纹图像进行旋转校正。在此基础上,设计了一套具有粗定位、
快提取、基于人类经验去除伪中心点的中心点提取算法。在多级分类阶段,建立
了一套基于中心点数目、方向、斗型螺径、箕型中心拱形方向分布特征的三级指
纹分类算法,实现了大规模指纹数据库的自动分类。
3.指纹图像匹配方面。基于传统点模式指纹匹配算法计算较为耗时的缺点,
提出了一种包括初匹配和全局匹配的两级指纹匹配算法。初匹配所比对的特征向
量是由外接全等三角形和邻近点构成的三角形这两种子结构所组成,如果匹配成
功则直接退出,否则仍能为全局匹配剔除掉部分不符合的样本图像和参考点对,
达到减少全局匹配计算量的目的。实验结果表明,在全局匹配前增加初匹配能够
大幅度降低匹配时间,并提高识别准确率。
4.为了验证自动指纹识别相关的算法的可行性和实用性,结合设计模式思
想和数据库相关技术,基于VS2010和MYSQL搭建了自动指纹识别系统软件平
台。该软件整合了多个关键算法,可用于对指纹识别算法进行测试和研究。
大量实验数据结果表明,本文提出的预处理改进算法能够获得清晰的指纹图
像,多级分类方法也具有较高的分类准确性,最终的二级匹配算法处理效果又快
又好。
关键词:指纹识别,大规模指纹库,指纹预处理,旋转校正,中心点提取,指纹
三级分类,指纹二级匹配
摘要
摘要
随着互联网时代的到来,生物特征识别技术受到了社会各界的广泛关注,其
中指纹识别技术一直都是国内外研究的热点和难点。越来越多的自动指纹识别产
品被开发应用千人们的生活,提供身份鉴别及安全防护的功能。尽管目前在理论
研究上已经取得了显著的成绩,但基千大规模指纹数据库的自动指纹识别系统在
识别准确率和处理速度上都亟待进一步的提高。本文结合目前数字图像处理技术
和模式识别技术的发展,深入研究了指纹识别的关键算法,主要的工作和创新总
结如下:
I.
指纹图像预处理方面。在分析和研究了前人成果的基础上,实现了指纹
预处理算法中的关键步骤,并着重改进了直方图均衡化、方向场计算和图像增强
方法。显著增强了脊线和谷线的对比度,保留了奇异区的方向变化规律,提高了
指纹图像的清晰度,为特征提取等操作的顺利进行奠定了基础。
2.
指纹图像分类方面。针对由千采集仪传感器面积小而无法提取三角点这
一分类特征的不足,研究并提出了一种包括分类预处理和多级分类两个步骤的指
纹分类方法。在分类预处理阶段,根据中心点附近的全局特征在指纹摆正时具有
可分类性的特点,首先采用拟合中位线法和最小外接椭圆法确定指纹的倾斜方向,
再通过仿射变换对指纹图像进行旋转校正。在此基础上,设计了一套具有粗定位、
快提取、基千人类经验去除伪中心点的中心点提取算法。在多级分类阶段,建立
了一套基千中心点数目、方向、斗型螺径、箕型中心拱形方向分布特征的三级指
纹分类算法,实现了大规模指纹数据库的自动分类。
3.
指纹图像匹配方面。基于传统点模式指纹匹配算法计算较为耗时的缺点,
提出了一种包括初匹配和全局匹配的两级指纹匹配算法。初匹配所比对的特征向
量是由外接全等三角形和邻近点构成的三角形这两种子结构所组成,如果匹配成
功则直接退出,否则仍能为全局匹配剔除掉部分不符合的样本图像和参考点对,
达到减少全局匹配计算量的目的。实验结果表明,在全局匹配前增加初匹配能够
大幅度降低匹配时间,并提高识别准确率。
4.
为了验证自动指纹识别相关的算法的可行性和实用性,结合设计模式思
想和数据库相关技术,基千
VS2010
和
MYSQL
搭建了自动指纹识别系统软件平
台。该软件整合了多个关键算法,可用于对指纹识别算法进行测试和研究。
大量实验数据结果表明,本文提出的预处理改进算法能够获得清晰的指纹图
像,多级分类方法也具有较高的分类准确性,最终的二级匹配算法处理效果又快
又好。
关键词:指纹识别,大规模指纹库,指纹预处理,旋转校正,中心点提取,指纹
三级分类,指纹二级匹配
Abstract
Abstract
With
the
advent of
the
Intemet
Era.Biometric
identification
has
anracted
lots
of
attention
and
made
great
progress
since
the
80s.Finge印rint,one
of
the
focuses
in
the
personal
identiflcation
field,is
the
hotspot
and
dimculty
to
researchers
at
home
and
abroad
for
a
long
time.Currently'an
increasing
number
of
automatic
fige印rint
identification
systems(AFIS)haVe
been
deVeloped
and
expanded
in
people’s
daily
life,
providing
identity
aumentication
and
security
protection.AltIlough
the
theoretical
research
has
made
significant
achivements,AFIS
baSed
on a
12urge—scale
fingerprint
database
is
still
to
be胁her
improved
on
accuracy
and
ef五ciency.Combined
with
the
current
deVelopment
of
digitalimage
processing
aIld
pattem
recogIlition
tecllniques,
this
thesis
researched
several
key
algoritllms
based
on
large-scale
finge叩rint
database,
mainly
focused
on
the
optimization
of
the
finge印rint
image
preprocessing,finge平r主nt
claSsmcation
aJld
finge印rint
identification.The
main
contributions
of
the
dissertation
are
aS
following:
1.Due
to
di蔬rent
kinds
of
noises,the
finge印rint
image
prerocessing
is
Very
importallt
to
improVe
the
quality
of
the
collected
images.0n
the
baSis
of
me
analysis
of
current
fingerprint
identification
technology
dissertations,this
thesis
realizes
the
key
steps
of
the
fIngerpmt
image
preprocessing.In
t11e
regaLrd,a
series
of
a190rithm
modifications
about
histogram
equalization,orientation
field
calculation
aIld
image
eIlllancement
is
proposed.This
algorit№significantly
en】1ances
the
contrast
of
tlle
ridge
and
the
Valley
line,ensure
the
accuracy
and
reliability
of
the
details
of
t11e
f.eature
extraction.
2.Usually
the
claSsic
fingerprint
claSsification
algorithm
needs
to
extract
core
and
delta
points.But
in
practical
application,it’s
highly
possible
that
delta
points
don’t
appear
in
the
collected
image,so
extracting
more
classification
features
to
mal(e
up
for
the
defect
will
be
very
necessary。A
new印proach
which
combines
the
mediall
line
fitting
with
tlle
minimum
bounding
ellipse
method
is
presented
to
extract
finger
placement
direction.Amne
transfomation
is
used
for
rotational
processing
aRer
calculating
the
compensation
of
a119le.In
the
aSpect
of
finge巾rint
feature
extraction,
two—steps
positolling
method
to
extracting
core
points
haS
been
studied,which
is
on
the
baSis
of
the
orientation
6eld
consisitencv
coefficient
a11d
modi6ed
Poincare
index
al罩Forithnl.E;ecause
of
the
pseudo
points,this
tllesis
has
proposed
a
sound
set
of
methods
based
on
h啪aIl
experience
to
help
enhance
the
classification
accuracy.
Finally'
a
three.1evel
fin2erprint
classification
system
baSed
on
the
n啪bers,
orientation,whorl‘s
radius
a11d
the
arch’s
direction
of
me
core
point,is
presented.It
can
be used
to
implement
the
classification
on
the
laurge.scale
database.
3.In
order
to
optimize
me
commonly
fingerprint
identification
algorit№s
based
on
the
minutiae
matclling,a
two—leVel
finge印rint
matChing
algoritllIIl
is
deVeloped.
First.a
discrim
inative
sub.stmcture
is
defined
f-or
each
minutia,、Vhich
includes
a
extemal
congment
triangle
aIld
a
triangle
made
up
of
the
neighbor
minutiaes.Then
a
similarity
score
is
employed
to
decide
whether
it
is
necessa叫to
get
to
the
global
matching.If
the
similarity
score
doesn’t
reach
a
certain
tbresh01d,the
potential
images
and
candidate
refIerence
pairs
which
have
gotten
higher
scores
will
be used
in
the
Abstract
Abstract
With the advent
of
the Internet Era, Biometric identification has attracted lots
of
attention and made great progress since the 80s. Fingerprint, one
of
the focuses in the
personal identification field,
is
the hotspot and difficulty to researchers at home and
abroad for a long time. Currently, an increasing number
of
automatic figerprint
identification systems (AFIS) have been developed and expanded in people's daily life,
providing identity authentication and security protection. Although the theoretical
research has made significant achivements, AFIS based on a large-scale fingerprint
database is still to be further improved on accuracy and efficiency. Combined with the
current development
of
digital image processing and pattern recognition techniques,
this thesis researched several key algorithms based on large-scale fingerprint database,
mainly focused on the optimization
of
the fingerprint image preprocessing, fingerprint
classification and fingerprint identification. The main contributions
of
the dissertation
are as following:
I. Due to different kinds
of
noises, the fingerprint image prerocessing is very
important to improve the quality
of
the collected images. On the basis
of
the analysis
of
current fingerprint identification technology dissertations, this thesis realizes the
key steps
of
the fingerpmt image preprocessing. In the regard, a series
of
algorithm
modifications about histogram equalization, orientation field calculation and image
enhancement is proposed. This algorithm significantly enhances the contrast
of
the
ridge and the valley line, ensure the accuracy and reliability
of
the details
of
the
feature extraction.
2.
Usually the classic fingerprint classification algorithm needs
to
extract core
and delta points. But in practical application, it's highly possible that delta points don't
appear in the collected image,
so
extracting more classification features to make up
for the defect will be very necessary. A new approach which combines the median line
fitting with the minimum bounding ellipse method
is
presented to extract finger
placement direction. Affine transformation is used for rotational processing after
calculating the compensation
of
angle. In the aspect
of
fingerprint feature extraction,
two-steps positoning method
to
extracting core points has been studied, which is on
the basis
of
the orientation field consisitency coefficient and modified Poincare index
algorithm. Because
of
the pseudo points, this thesis has proposed a sound set
of
methods based on human experience to help enhance the classification accuracy.
Finally, a three-level fingerprint classification system based on the numbers,
orientation, whorl's radius and the arch's direction
of
the core point, is presented. It
can be used to implement the classification on the large-scale database.
3.
In
order to optimize the commonly fingerprint identification algorithms based
on the minutiae matching, a two-level fmgerprint matching algorithm is developed.
First, a discrim inative sub-structure is defined for each minutia, which includes a
external congruent triangle and a triangle made up
of
the neighbor minutiaes. Then a
similarity score
is
employed to decide whether it is necessary to get to the global
matching.
If
the similarity score doesn't reach a certain threshold, the potential images
and candidate reference pairs which have gotten higher scores will be used in the
II
剩余87页未读,继续阅读
有只风车子
- 粉丝: 30
- 资源: 329
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
最新资源
- 基于matlab实现的 压缩传感使用并行坐标下降算法(冗余字典由各种小波变换和离散余弦变换被用于图像修复.rar
- 基于matlab实现的 Coefficients of Polynomial Chaos Expansion (PCE).rar
- 基于matlab实现的 贝叶斯和通用阈值软阈值图像去噪方法MATLAB程序,希望对大家有帮助,仅供大家参考,希望有用.rar
- (自适应手机端)餐饮小吃火锅店网站pbootcms模板 餐饮火锅加盟网站源码下载.zip
- 32-074X婴儿床S-V2.0-含摄像头功能.apk
- 3333333333333333333
- 企业网络关系数据集(2006-2022年).xlsx
- Microsoft.Web.UI.WebControls动态链接库
- 44444444444444444444444
- 基于D^2-City大规模行车记录视频数据集
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功
评论0