Two biometric characteristics are considered in this study: iris and fingerprint. The score level fusion is used to combine the characteristics from different biometric modalities. Fusion at the score level is a new technique, which has a high potential for efficient consolidation of multiple unimodal biometric matcher outputs. Support vector machine and extreme learning techniques are used in this system for recognition of biometric traits. The proposed method provides better performance. ELM provides better performance as compare to the SVM. It reduces the classification time of current system. This work is valuable and makes an efficient accuracy in such applications. This system can be utilized for person identification in several applications.

1. A New Framework for
IRIS and Fingerprint
Recognition
Using SVM Classification and Extreme Learning Machine Based on
Score Level Fusion

2. Abstract
•
Two biometric characteristics are considered in this study: iris and fingerprint.
•
The score level fusion is used to combine the characteristics from different biometric
modalities.
–
Fusion at the score level is a new technique, which has a high potential for efficient consolidation
of multiple unimodal biometric matcher outputs.
•
Support vector machine and extreme learning techniques are used in this system for
recognition of biometric traits.
•
The proposed method provides better performance. ELM provides better performance
as compare to the SVM. It reduces the classification time of current system.
•
This work is valuable and makes an efficient accuracy in such applications. This system
can be utilized for person identification in several applications.

3. Objective
• Establishing the identity of a person is a critical
task in any identity management system.
• Surrogate representations of identity such as
passwords and ill cards are not sufficient for
reliable identity determination because they
can be easily misplaced, shared, or stolen.
• Biometric recognition is the science of
establishing the identity of a person using
his/her anatomical and behavioral traits.
• Our objective is to establish the identity of a
person, in any identity management system.

4. Software Requirements
• Operating System
:
Windows XP
• Language
:
MATLAB
• Version
:
MATLAB 7.9

5. Hardware Requirements
• Pentium IV – 2.7 GHz
• 1 GB DDR RAM
• 250 GB Hard Disk

6. Existing System
• Minutiae and texture based fingerprint fusion study using
a Quality-Weighted Sum (QWS) rule for score level fusion
• Palm print recognition using rank level fusion.
• Biometrics system using iris and face fusion is performed
at matching score level using weighted scores.
• Biometric system for face and hand using feature level
fusion with PCA (Principal Component Analysis) and LDA
(Linear Discriminant Analysis) method.
• Multimodal approach for palmprint and hand
geometry, with fusion methods at the feature level by
combining the feature vectors by concatenation, and
the matching score level by using max rule.

7. Proposed System
• Features are extracted from Fingerprint modality
and iris and are fused individually with the Iris
modality to further evaluate the fusion results.
• The individual features of two traits, iris and
fingerprint are combined at the matching score
level to develop a multimodal biometric
authentication system.
• K-means clustering
database.
is
used
to
searching
the
• Support vector machine and Extreme learning
machine is used for recognition.

8. Applications
• Access control
–
–
–
–
Access control to computer systems (workstations
Door security
Portable media: USB sticks & mobile hard-drives
Safes with biometric locks
• Time and attendance management
– Avoids fooling
– Reduces overhead for security personnel when badges
are lost or pin-codes forgotten.
• Surveillance
• Visit program

9. Conclusion
•
This work focuses on using the multimodal biometrics: A New framework for
fingerprint and iris recognition using support vector machine based score
level fusion.
•
The individual scores of two traits, iris and fingerprint are combined at the
matching score level to develop a multimodal biometric authentication
system.
•
K-means clustering is used to searching the database.
•
Comparison of Support vector machine and Extreme learning machine will
decrease the recognition time.
•
The experiments are conducted to evaluate the performance of support
vector machine and extreme learning machine.
•
Comparing the classification time perform Extreme learning machine better
than the support vector machine.
•
The experimental results show that comparing SVM and ELM with K-mean
cluster methods provide clustering score based on similarity done and
reduce the classification time.

10. Future Work
• To employ the same feature extraction
technique for iris also with few additional preprocessing
steps
such
as
histogram
equalization,
fast
fourier
transform, binarization, direction and thinning.

11. /AvvenireTechnologies
/avveniretech