“IRIS, FINGERPRINT AND FACE BASED MULTIMODAL SYSTEM FOR
IMPROVING THE ACCURACY AND SECURITY OFA SYSTEM”
GUIDED BY:-
Mr. Mukesh Azad
SRMSCET, Bareilly
SUBMITTED BY:-
Deep Kumar Sharma
M.Tech(S.E), IVth sem
SRMSCET, Bareilly
09/09/2015 1
CONTENTS:
• Introduction:
I) Biometrics (Unimodal).
II) Multimodal system.
• Problem statement.
• Literature review.
• Methodologies.
• Expected Result.
• Software/Tools.
• References.
09/09/2015 2
Introduction
I) Biometrics
• Is the term given to the use of
biological traits
OR
behavioral characteristics
to identify an individual.
09/09/2015 3
Characteristics
1) The common Physical characteristics are:
• Fingerprint
• Face
• Retina
• Iris
• Vein pattern, and
• Hand and finger geometry
09/09/2015 4
Characteristics
2) Behavioral characteristics are:
• Keystroke dynamics
• Voice
• Gait, and
• Signature dynamics
09/09/2015 5
II) Multimodal system
• However, even the best biometric traits till date are facing numerous problems
some of them are inherent to the technology itself.
• One way to overcome these problems is the use of multimodal system.
• A multimodal system uses multiple sensors for data acquisition.
• This allows capturing multiple samples of a single biometric trait and/or
samples of multiple biometric traits.
• This approach is enables to provide significant improvement over unimodal
biometric system in terms of higher accuracy.
09/09/2015 6
09/09/2015 7
II) Multimodal system
Multimodal login system
.
09/09/2015 8
Face
Hand geometry
Fingerprint
Problem statement
• The security is an important aspect in our daily life whichever the system we
consider security plays vital role.
• The multimodal biometric person identification technique based on the pattern
of the human iris, fingerprint and face is well suited to be applied to access
control and provides strong e-security.
• Security systems having realized the value of multimodal biometric system for
two basic purposes: to verify or identify users.
• The multimodal biometric system is more secure biometrics system than the
unimodal system.
• In unimodal system single trait is used for the authentication so it can be easy to
crack the security of the unimodal system.
• To solve this problem we can use the multimodal system.
09/09/2015 9
Literature review
• P.U.Lahane, Prof. S.R.Ganorkar, “Fusion of Iris & Fingerprint
Biometric for Security Purpose”, International Journal of Scientific &
Engineering Research, August-2012.
Has focused on to develop a biometric identification system that
represents a valid alternative to conventional approaches. Multimodal
biometric identification system based on iris & fingerprint trait is
proposed. Typically in a multimodal biometric system each biometric trait
processes its information independently. The processed information is
combined using an appropriate fusion scheme. Successively, the
comparison of data base template and the input data is done with the help
of Euclidean-distance matching algorithm. If the templates are matched
we can allow the person to access the system. We are going to check FAR
& FRR with different threshold level.
09/09/2015 10
Cont.
• Dipti.S.Randive, Manasi.M.patil, "Iris and Fingerprint Fusion for
Biometric Identification ", International Journal of Computer
Applications, September 2013.
Has discussed that a biometric system which relies only on a single biometric
identifier in making a personal identification is often not able to meet the
desired performance requirement.
•Andrea F. Abate, Michele Nappi, Daniel Riccio, Gabriele Sabatino, "2D
and 3D face recognition: A survey", Elsevier, January 2007.
Says that the Government agencies are investing a considerable amount of
resources into improving security systems as result of recent terrorist events
that dangerously exposed flaws and weaknesses in today’s safety mechanisms.
Badge or password-based authentication procedures are too easy to hack.
Biometrics represents a valid alternative but they suffer of drawbacks as well.
09/09/2015 11
Cont.
• Ujwalla Gawande1, Anushree Sapre2, Apurva Jain3, Sanchita
Bhriegu4, Shruti Sharma5,“ Fingerprint-Iris Fusion Based Multimodal
Biometric System Using Single Hamming Distance Matcher ",
International Journal of Engineering Inventions, February 2013.
explained that in the real world applications, unimodal biometric systems
often face limitations because of sensitivity to noise, intra class invariability,
data quality, and other factors. Improving the performance of individual
matchers in the aforementioned situation may not be effective.
09/09/2015 12
Cont.
• Shradha Tiwari, Prof. J.N. Chourasia, Dr. Vijay S. Chourasia,"A
Review of Advancements in Biometric Systems ", International Journal
of Innovative Research in Advanced Engineering January 2015.
Has discussed that Biometric systems for today’s high security
applications must meet stringent performance requirements. In this paper,
we provide an overview of the fundamentals of biometric identification,
together with a description of the main biometric technologies currently in
use, all of them within a common reference framework.
09/09/2015 13
Methodologies
• The objective is to develop a multimodal system to increase the accuracy and
security of a system.
• The multimodal system usage the two or more traits as input data for
authentication and authorization of any person.
• There are some fusion techniques and some feature extraction techniques are
used.
• In the Multimodal system two modules are used for processing:
I) Enrollment Module.
II) Matching Module.
09/09/2015 14
I) Enrollment Module
.
09/09/2015 15
IRIS FINGERPRINT
ROI EXTRACTION
NORMALIZATION
GABOR FILTER
EXTRACTED FEATURES
TEMPLATE DATABASE
I) Enrollment Module(Cont.)
In the enrollment module the
biometrics traits used for input.
Region of Interest extracted from
the images.
Then Normalization performed
on the ROI images.
Use the Gabor filter for feature
extraction.
Extracted features stored in the
Template database.
09/09/2015 16
II) Matching Module
.
09/09/2015 17
IRIS FINGERPRINT
ROI EXTRACTION
NORMALIZATION
GABOR FILTER
EXTRACTED FEATURES
TEMPLATE DATABASE
MATCHING
RESULT
II) Matching Module(Cont.)
In the Matching module the
biometrics traits used for input.
Region of Interest extracted from the
images.
Then Normalization performed on
the ROI images.
Use the Gabor filter for feature
extraction.
Extracted features are used for
matching with the extracted features
stored in the Template database .
After matching found the result.
09/09/2015 18
Expected Result
• We use the biometric multimodal system to increase the security of a
system.
• In this we use the different fusion methods, Feature Extraction
techniques.
• On the basis of different threshold levels calculate the values of optimal
False Acceptance Rate (FAR) & False Rejection Rate (FRR), to improve
the system accuracy, reliability & security.
09/09/2015 19
Software/Tools
Image processing toolbox in MATLAB & DATABASE will be used for the
implementation.
MATLAB 7.9: -
• The version of MATLAB R2009b is developed at September 4, 2009.
• It is a multi-paradigm numerical computing environment and fourth-generation
programming language. A proprietary programming language developed
by MathWorks, MATLAB allows matrix manipulations, plotting of
functions and data, implementation of algorithms, creation of user interfaces.
09/09/2015 20
References
[1] P.U.Lahane, Prof. S.R.Ganorkar, “Fusion of Iris & Fingerprint Biometric for
Security Purpose”, International Journal of Scientific & Engineering Research, August-
2012.
[2] Dipti.S.Randive, Manasi.M.patil, "Iris and Fingerprint Fusion for Biometric
Identification ", International Journal of Computer Applications, September 2013.
[3] Ujwalla Gawande1, Anushree Sapre2, Apurva Jain3, Sanchita Bhriegu4, Shruti
Sharma5,“ Fingerprint-Iris Fusion Based Multimodal Biometric System Using Single
Hamming Distance Matcher ", International Journal of Engineering Inventions,
February 2013.
[4] Andrea F. Abate, Michele Nappi, Daniel Riccio, Gabriele Sabatino, "2D and 3D
face recognition: A survey", Elsevier, January 2007.
[5] Shradha Tiwari, Prof. J.N. Chourasia, Dr. Vijay S. Chourasia, “ A Review of
Advancements in Biometric Systems ", International Journal of Innovative Research in
Advanced Engineering January 2015.
[6] S.P.Khandait, Dr. R.C.Thool, P.D.Khandait, "Automatic Facial Feature Extraction
and Expression Recognition based on Neural Network ", International Journal of
Advanced Computer Science and Applications, January 2011.
09/09/2015 21
References
[7] Maheswari M A.P, Ancy S and EbenPraisyDevanesam.K, “Biometric
identification system for features fusion of iris and fingerprint ", Recent Research in
Science and Technology 2012.
[8] Vaibhavkumar J. Mistry, Mahesh M. Goyani, " A literature survey on Facial
Expression Recognition using Global Features ", International Journal of Engineering
and Advanced Technology, April 2013.
[9] Vaibhavkumar J. Mistry1, Mahesh M. Goyani2, " Facial Expression Recognition
using Gabor Filter by minimizing Feature Vector ",International Journal of Computer
Science and Management Research May 2013.
[10] P.U.Lahane, Prof. S.R.Ganorkar, “Efficient Iris and Fingerprint Fusion for Person
Identification ", International Journal of Computer Applications, July 2012.
[11] Samarth Bharadwaj, Mayank Vatsa and Richa Singh, " Biometric quality: a
review of fingerprint, iris, and face ", EURASIP Journal on Image and Video
Processing 2014.
[12] Pradnya M. Shende, Dr.Milind V. Sarode, Prof. Mangesh M. Ghonge, “A Survey
Based on Fingerprint, Face and Iris Biometric Recognition System, Image Quality
Assessment and Fake Biometric ", International Journal of Computer Science
Engineering and Technology April 2014.
09/09/2015 22
THANK YOU
09/09/2015 23

Thesis presentation ist

  • 1.
    “IRIS, FINGERPRINT ANDFACE BASED MULTIMODAL SYSTEM FOR IMPROVING THE ACCURACY AND SECURITY OFA SYSTEM” GUIDED BY:- Mr. Mukesh Azad SRMSCET, Bareilly SUBMITTED BY:- Deep Kumar Sharma M.Tech(S.E), IVth sem SRMSCET, Bareilly 09/09/2015 1
  • 2.
    CONTENTS: • Introduction: I) Biometrics(Unimodal). II) Multimodal system. • Problem statement. • Literature review. • Methodologies. • Expected Result. • Software/Tools. • References. 09/09/2015 2
  • 3.
    Introduction I) Biometrics • Isthe term given to the use of biological traits OR behavioral characteristics to identify an individual. 09/09/2015 3
  • 4.
    Characteristics 1) The commonPhysical characteristics are: • Fingerprint • Face • Retina • Iris • Vein pattern, and • Hand and finger geometry 09/09/2015 4
  • 5.
    Characteristics 2) Behavioral characteristicsare: • Keystroke dynamics • Voice • Gait, and • Signature dynamics 09/09/2015 5
  • 6.
    II) Multimodal system •However, even the best biometric traits till date are facing numerous problems some of them are inherent to the technology itself. • One way to overcome these problems is the use of multimodal system. • A multimodal system uses multiple sensors for data acquisition. • This allows capturing multiple samples of a single biometric trait and/or samples of multiple biometric traits. • This approach is enables to provide significant improvement over unimodal biometric system in terms of higher accuracy. 09/09/2015 6
  • 7.
  • 8.
    Multimodal login system . 09/09/20158 Face Hand geometry Fingerprint
  • 9.
    Problem statement • Thesecurity is an important aspect in our daily life whichever the system we consider security plays vital role. • The multimodal biometric person identification technique based on the pattern of the human iris, fingerprint and face is well suited to be applied to access control and provides strong e-security. • Security systems having realized the value of multimodal biometric system for two basic purposes: to verify or identify users. • The multimodal biometric system is more secure biometrics system than the unimodal system. • In unimodal system single trait is used for the authentication so it can be easy to crack the security of the unimodal system. • To solve this problem we can use the multimodal system. 09/09/2015 9
  • 10.
    Literature review • P.U.Lahane,Prof. S.R.Ganorkar, “Fusion of Iris & Fingerprint Biometric for Security Purpose”, International Journal of Scientific & Engineering Research, August-2012. Has focused on to develop a biometric identification system that represents a valid alternative to conventional approaches. Multimodal biometric identification system based on iris & fingerprint trait is proposed. Typically in a multimodal biometric system each biometric trait processes its information independently. The processed information is combined using an appropriate fusion scheme. Successively, the comparison of data base template and the input data is done with the help of Euclidean-distance matching algorithm. If the templates are matched we can allow the person to access the system. We are going to check FAR & FRR with different threshold level. 09/09/2015 10
  • 11.
    Cont. • Dipti.S.Randive, Manasi.M.patil,"Iris and Fingerprint Fusion for Biometric Identification ", International Journal of Computer Applications, September 2013. Has discussed that a biometric system which relies only on a single biometric identifier in making a personal identification is often not able to meet the desired performance requirement. •Andrea F. Abate, Michele Nappi, Daniel Riccio, Gabriele Sabatino, "2D and 3D face recognition: A survey", Elsevier, January 2007. Says that the Government agencies are investing a considerable amount of resources into improving security systems as result of recent terrorist events that dangerously exposed flaws and weaknesses in today’s safety mechanisms. Badge or password-based authentication procedures are too easy to hack. Biometrics represents a valid alternative but they suffer of drawbacks as well. 09/09/2015 11
  • 12.
    Cont. • Ujwalla Gawande1,Anushree Sapre2, Apurva Jain3, Sanchita Bhriegu4, Shruti Sharma5,“ Fingerprint-Iris Fusion Based Multimodal Biometric System Using Single Hamming Distance Matcher ", International Journal of Engineering Inventions, February 2013. explained that in the real world applications, unimodal biometric systems often face limitations because of sensitivity to noise, intra class invariability, data quality, and other factors. Improving the performance of individual matchers in the aforementioned situation may not be effective. 09/09/2015 12
  • 13.
    Cont. • Shradha Tiwari,Prof. J.N. Chourasia, Dr. Vijay S. Chourasia,"A Review of Advancements in Biometric Systems ", International Journal of Innovative Research in Advanced Engineering January 2015. Has discussed that Biometric systems for today’s high security applications must meet stringent performance requirements. In this paper, we provide an overview of the fundamentals of biometric identification, together with a description of the main biometric technologies currently in use, all of them within a common reference framework. 09/09/2015 13
  • 14.
    Methodologies • The objectiveis to develop a multimodal system to increase the accuracy and security of a system. • The multimodal system usage the two or more traits as input data for authentication and authorization of any person. • There are some fusion techniques and some feature extraction techniques are used. • In the Multimodal system two modules are used for processing: I) Enrollment Module. II) Matching Module. 09/09/2015 14
  • 15.
    I) Enrollment Module . 09/09/201515 IRIS FINGERPRINT ROI EXTRACTION NORMALIZATION GABOR FILTER EXTRACTED FEATURES TEMPLATE DATABASE
  • 16.
    I) Enrollment Module(Cont.) Inthe enrollment module the biometrics traits used for input. Region of Interest extracted from the images. Then Normalization performed on the ROI images. Use the Gabor filter for feature extraction. Extracted features stored in the Template database. 09/09/2015 16
  • 17.
    II) Matching Module . 09/09/201517 IRIS FINGERPRINT ROI EXTRACTION NORMALIZATION GABOR FILTER EXTRACTED FEATURES TEMPLATE DATABASE MATCHING RESULT
  • 18.
    II) Matching Module(Cont.) Inthe Matching module the biometrics traits used for input. Region of Interest extracted from the images. Then Normalization performed on the ROI images. Use the Gabor filter for feature extraction. Extracted features are used for matching with the extracted features stored in the Template database . After matching found the result. 09/09/2015 18
  • 19.
    Expected Result • Weuse the biometric multimodal system to increase the security of a system. • In this we use the different fusion methods, Feature Extraction techniques. • On the basis of different threshold levels calculate the values of optimal False Acceptance Rate (FAR) & False Rejection Rate (FRR), to improve the system accuracy, reliability & security. 09/09/2015 19
  • 20.
    Software/Tools Image processing toolboxin MATLAB & DATABASE will be used for the implementation. MATLAB 7.9: - • The version of MATLAB R2009b is developed at September 4, 2009. • It is a multi-paradigm numerical computing environment and fourth-generation programming language. A proprietary programming language developed by MathWorks, MATLAB allows matrix manipulations, plotting of functions and data, implementation of algorithms, creation of user interfaces. 09/09/2015 20
  • 21.
    References [1] P.U.Lahane, Prof.S.R.Ganorkar, “Fusion of Iris & Fingerprint Biometric for Security Purpose”, International Journal of Scientific & Engineering Research, August- 2012. [2] Dipti.S.Randive, Manasi.M.patil, "Iris and Fingerprint Fusion for Biometric Identification ", International Journal of Computer Applications, September 2013. [3] Ujwalla Gawande1, Anushree Sapre2, Apurva Jain3, Sanchita Bhriegu4, Shruti Sharma5,“ Fingerprint-Iris Fusion Based Multimodal Biometric System Using Single Hamming Distance Matcher ", International Journal of Engineering Inventions, February 2013. [4] Andrea F. Abate, Michele Nappi, Daniel Riccio, Gabriele Sabatino, "2D and 3D face recognition: A survey", Elsevier, January 2007. [5] Shradha Tiwari, Prof. J.N. Chourasia, Dr. Vijay S. Chourasia, “ A Review of Advancements in Biometric Systems ", International Journal of Innovative Research in Advanced Engineering January 2015. [6] S.P.Khandait, Dr. R.C.Thool, P.D.Khandait, "Automatic Facial Feature Extraction and Expression Recognition based on Neural Network ", International Journal of Advanced Computer Science and Applications, January 2011. 09/09/2015 21
  • 22.
    References [7] Maheswari MA.P, Ancy S and EbenPraisyDevanesam.K, “Biometric identification system for features fusion of iris and fingerprint ", Recent Research in Science and Technology 2012. [8] Vaibhavkumar J. Mistry, Mahesh M. Goyani, " A literature survey on Facial Expression Recognition using Global Features ", International Journal of Engineering and Advanced Technology, April 2013. [9] Vaibhavkumar J. Mistry1, Mahesh M. Goyani2, " Facial Expression Recognition using Gabor Filter by minimizing Feature Vector ",International Journal of Computer Science and Management Research May 2013. [10] P.U.Lahane, Prof. S.R.Ganorkar, “Efficient Iris and Fingerprint Fusion for Person Identification ", International Journal of Computer Applications, July 2012. [11] Samarth Bharadwaj, Mayank Vatsa and Richa Singh, " Biometric quality: a review of fingerprint, iris, and face ", EURASIP Journal on Image and Video Processing 2014. [12] Pradnya M. Shende, Dr.Milind V. Sarode, Prof. Mangesh M. Ghonge, “A Survey Based on Fingerprint, Face and Iris Biometric Recognition System, Image Quality Assessment and Fake Biometric ", International Journal of Computer Science Engineering and Technology April 2014. 09/09/2015 22
  • 23.