The document presents a simulation of palm print identification based on Zernike moments. It discusses extracting the region of interest from palm print images, preprocessing them, and extracting Zernike moments as features. These features are used to train a system and match test images to identify individuals. The simulation achieved up to 86% accuracy in matching palm prints using Zernike moments of orders 0-7. It concluded that Zernike moments make the system robust to rotations and translations of palm prints.
1. A Presentation on
“SIMULATION OF PALM PRINT
IDENTIFICATION BASED ON
ZERNIKE MOMENT”
Internal guide:
Mr. MITUL M. PATEL
Asst. Prof, E&C Dept.
PIET, Limda
Prepared By:
SHARMA ASHOK S.
Enrollment No.
100370722003
Master of Engineering
Digital Communication
2012-13
3. INTRODUCTION
• BIOMETRICS:
– Biometrics identification is the technique of
automatically identifying or verifying an
individual by physical characteristics or
personal trait.
– Types:
• Behavioral
• Physiological
6. DESIRED FEATURES IN A
BIOMETRIC
• High Accuracy
• Permanence of biometric in time
• Utilization of cheap acquisition devices
• Resistance to changes in environmental conditions
• No or very little public objection (Acceptability)
• Small template size
• Simple user – system interaction
[13] Palmprint Recognition Based On 2-d Gabor Filters - Baris Konuk
7. ADVANTAGES OF PALMPRINT
• Palm print has relatively
stable and unique features
• Collection of data is easy
and non-intrusive
• Devices to collect data are
economical
• It provides high efficiency
using low resolution images
[11] An Efficient Occlusion Invariant Palmprint Based Verification System -Naresh kumar kachhi
8. LITERATURE REVIEW
• Li Fang, Maylor K.H. Leung, Tejas Shikhare, Victor
Chan, Kean Fatt Choon, “Palmprint Classification” 2006
IEEE International Conference on Systems, Man, and
Cybernetics, October 8-11, 2006
– Classification of palm print in different categories.
• Madsu Hanmandlu, Neha Mittal “A comprehensive study
of palmprint based authentication”, International Journal
of Computer Applications, Jan 2012
– Use of new features for palm print recognition.
9. LITERATURE REVIEW
• K. B. Nagasundara, D. S. Guru “Multi-algorithm based
Palmprint Indexing”, International conference &
workshop on Recent Trends in Technology, 2012
– Proposed approach based on the fusion of Haar wavelets and
Zernike moments.
• Amir Tahmasbhi, Fatemeh Saki, Shahriar B. Shokouhi
“Classification of benign and malignant masses based on
Zernike moments” Elsevier, Computers in Biology and
Medicine, 2011
– Development of a novel Computer-aided Diagnosis (CADx) using
Zernike Moments.
10. LITERATURE REVIEW
• Atif Bin Mansoor , Hassan Masood, Mustafa Mumtaz ,
Shoab A. Khan “A feature level multimodal approach for
palm print identification using directional sub band
energies” Journal of Network and Computer Applications,
AUGUST 2010
– Different technique for ROI extraction.
11. JUSTIFICATION OF TOPIC
Need to build system which is robust to translation
and rotation, has constraint free acquisition, and uses
low cost scanner.
17. RESOLUTION REQUIREMENTS FOR
DIFFERENT PALM PRINT FEATURES
Palm Print Features Required Resolution (in dpi)
Principal Lines ≥75
Wrinkles ≥100
Ridges texture ≥125
[13] Palmprint Recognition Based On 2-d Gabor Filters - Baris Konuk
21. FEATURE EXTRACTION
• Zernike moments are used as features.
• Provides good discrimination ability.
• The order of Zernike moments determines the
details of information regarding palm print.
• Higher the order of moments, greater the details of
the image.
• But higher orders are sensitive to noise.
[15] Image Analysis by Moments –Simon Xinmeng Liao
22. ZERNIKE MOMENTS
• Mapping of an image onto a set of complex
Zernike polynomials.
• Orthogonal to each other.
• Represent the properties of an image with no
redundancy or overlap of information between the
moments.
[15] Image Analysis by Moments –Simon Xinmeng Liao
23. ZERNIKE MOMENT:
• 𝑍 𝑝𝑞 =
𝑝+1
𝜋 0
2𝜋
0
1
𝑉𝑝𝑞 𝑟, 𝜃 𝑓 𝑟, 𝜃 𝑟𝑑𝑟𝑑𝜃; 𝑟 ≤ 1
p-|q|=even and |p|≤q
where
𝑉𝑝𝑞 𝑟, 𝜃 = 𝑅 𝑝𝑞 𝑟 𝑒−𝑖𝑞𝜃
; 𝑖 = −1
where
𝑅 𝑝𝑞 𝑟 =
𝑘=0
𝑝− 𝑞
2
(−1) 𝑘
𝑝 − 𝑘 !
𝑘!
𝑝 + 𝑞
2 − 𝑘 !
𝑝 − 𝑞
2 − 𝑘 !
𝑟 𝑝−2𝑘
[14] Moments and Moment Invariants in Pattern Recognition-Jan Flusser, Tomáš Suk and
Barbara Zitová
28. EUCLIDEAN DISTANCE
• If p = (p1 ,p2,...,pn) and q = (q1 ,q2,...,qn) are
two points, then the distance from p to q is
given by
𝑑 𝑝, 𝑞 = (𝑝1 − 𝑞1)2+(𝑝2 − 𝑞2)2+ ⋯ + (𝑝𝑛 − 𝑞𝑛)2
37. PERFORMANCE EVALUATION
• FALSE ACCEPTANCE RATE:
• 𝐹𝐴𝑅 =
number of accepted imposter claims
total number of imposter accesses
× 100%
• FALSE REJECTION RATE:
• FRR =
number of rejected client claims
total number of client accesses
× 100%
• Receiver Operator Curve (ROC)
• Efficiency =
𝑡𝑟𝑢𝑒 𝑑𝑒𝑡𝑒𝑐𝑡𝑖𝑜𝑛
𝑡𝑜𝑡𝑎𝑙 𝑚𝑎𝑡𝑐ℎ𝑒𝑠
[9] Palmprint verification with moments –Ying Han Pang, Andrew T.B.J
45. CONCLUSION
• From this work it is concluded that there is a need
of Better biometric system for person
authentication with lower resolution capturing
device.
• By designing biometric system using palm print
we solved the above issue.
• Use of Zernike moments for identification makes
it robust to rotational and translational changes.
46. REFERENCES
[1] Vivek Kanhangad, Ajay Kumar, David Zhang, “A Unified Framework for
Contactless Hand Verification”, IEEE TRANSACTIONS ON
INFORMATION FORENSICS AND SECURITY, VOL.6, NO.3,
SEPTEMBER 2011
[2] Atif Bin Mansoor , Hassan Masood, Mustafa Mumtaz , Shoab A. Khan “A
feature level multimodal approach for palm print identification using
directional sub band energies” Journal of Network and Computer
Applications, AUGUST 2010
[3] Li Fang, Maylor K.H. Leung, Tejas Shikhare, Victor Chan, Kean Fatt
Choon, “Palmprint Classification” 2006 IEEE International Conference on
Systems, Man, and Cybernetics, October 8-11, 2006
[4] K. B. Nagasundara, D. S. Guru “Multi-algorithm based Palmprint
Indexing”, International conference & workshop on Recent Trends in
Technology, 2012
47. [5] Jian-GangWanga,Wei-Yun Yaua, Andy Suwandya, Eric Sungb “Person
recognition by fusing palm print and palm vein images based on
“Laplacian palm” representation”, 17 October 2007
[6] Zhu Le-qing, Zhang San-yuan, “Multimodal biometric identification
system based on finger geometry, knuckle print and palm print”, 1 June
2010
[7] Zhenhua Guo, Wangmeng Zuo, Lei Zhang, David Zhang, “A unified
distance measurement for orientation coding in palm print verification ”, 4
September 2009
[8] Madsu Hanmandlu, Neha Mittal “A comprehensive study of palmprint
based authentication”, International Journal of Computer Applications, Jan
2012
[9] Ying Han Pang, Andrew T.B.J “Palmprint verification with moments”
Journal of WSCG, Vol.12, No.1-3, ISSN 1213-6972
[10] The Poly U palmprint database.
http://www.commp.polyu.edu.hk/~biometrics
48. [11] Naresh kumar kachhi, “An Efficient Occlusion Invariant Palmprint
Based Verification System”, June 2009
[12] Diogo Santos Martins, “Biometric recognition based on the texture
along palmprint principal lines”,July 2011
[13] Baris Konuk, “Palmprint Recognition Based On 2-d Gabor Filters” Jan
2007
[14] Moments and Moment Invariants in Pattern Recognition-Jan Flusser,
Tomáš Suk and Barbara Zitová
[15] Image Analysis by Moments –Simon Xinmeng Liao
1. Universality: All individuals should possess the biometric characteristics.
2. Uniqueness: The biometric characteristics of different individuals should not
be the same.
3. Permanence: The biometric characteristics of individuals should not change
severely with the time.
4. Collectability: The biometric characteristics should be measurable with some
practical device.
5. Acceptability: Individuals should not have objections to the measuring or
collection of the biometric.