Evaluation of Biometric Systems - scati.greyc.fr · Evaluation of biometric systems ... Touch...
Transcript of Evaluation of Biometric Systems - scati.greyc.fr · Evaluation of biometric systems ... Touch...
2
GREYC research lab
Evaluation: a love story
Evaluation of biometric systems
Quality of biometric templates
Conclusions & perspectives
Outline
3
Le pôle TES et le sans-contact
Laboratory staff: 7 CNRS researchers 25 Full professors 11 Associate professors 56 Assistant professors 79 PhD students 17 permanent staff 30 Engineers and post-doc
Research Group in Computer science, Automatics, Image processing and Electronics of Caen
Research topics: Electronics Image processing Algorithmic Document analysis Multi-agents Robotics navigation Automatics Computer security Natural language processing Biometrics Cryptography
GREYC Lab
5
Le pôle TES et le sans-contact
Biometrics: Operational authentication that respects the privacy of users
Biometric authentication (palm veins, keystroke dynamics…) Evaluation of biometric systems (acceptability, security…) Protection of biometrics (cancelable biometrics, smartcards…)
Research topics
GREYC Keystroke Keystroke dynamics
authentication
6
Research topics
Biometric systems
Keystroke dynamics
Touch screen interaction Hand shape, palm vein
Face
Finger Knuckle Print
Fingerprint
Signature dynamics
Iris
7
GREYC research lab
Evaluation: a love story
Evaluation of biometric systems
Quality of biometric templates
Conclusions & perspectives
Outline
8
Evaluation: a love story
PhD thesis: 1996-1999
« Adaptive segmentation: application to hyperspectral images »
Application: Algae detection
Questions:
How to choose the best segmentation method for a type of region ?
How to validate my results ?
9
Evaluation: a love story
Supervised evaluation: relevance
Use of an a priori information:
Synthetic
Easy to obtain (by construction),
Not always representative.
Expert
Dedicated to an application,
Costly.
Image
processing
algorithm
Reference
10
Evaluation: a love story
Image
processing
algorithm
Statistical parameters Example: PSNR, EQM…
Advantage
Easy computation
Automatic evaluation
Drawback
Difference with an expert jugment
Unsupervised evaluation: consistency
11
Which one is the
best ?
Segmentation 1
Segmentation 2
Segmentation 3
Original image
Evaluation: a love story
12
Evaluation: a love story
Paradox
Compression: PSNR known as a poor metric but still used
Segmentation : many metrics exist but not very often used
Interpretation : needs to use a benchmark (not easy), very few metrics for the evaluation of a single result
….
Still a long way to go
13
GREYC research lab
Evaluation: a love story
Evaluation of biometric systems
Quality of biometric templates
Conclusions & perspectives
Outline
14
Context
Biometrics: high level application with well defined tasks
Multiple organizations:
• BIOAPI consortium: development a biometric API standard (1998)
• National committee 37 (AFNOR): normalisation (2004)
Three important aspects:
• Performance
• Security
• Usability
Evaluation
15
Evaluation
M. El-Abed, R. Giot, B. Hemery, J.-J. Schwartzmann, C. Rosenberger, "Towards the Security Evaluation of Biometric
Authentication Systems", International Conference on Security
Science and Technology (ICSST) 2011
16
Evaluation
General process
In order to quantify the efficiency of a biometric system, we generally use two databases:
1-Learning database: used for the enrolment of individuals (can use different captures for the model definition);
2-Testing database: used for verification or identification with captures of known individuals (impostors and genuine users).
Learning
database
Test ing
database
17
Performance evaluation
EER
FRR
FAR
FAR : False Acceptance Rate
FRR : False Rejection Rate
EER : Equal Error Rate
ROC curve: FRR vs FAR
AUC : Area under the curve
Evaluation
18
Evaluation
Data for the tests:
Real users: time consuming, operators are needed
Benchmark databases:
• http://biosecure.it-sudparis.eu/AB/
• http://www4.comp.polyu.edu.hk/~biometrics/
• http://www.cbsr.ia.ac.cn:8080/iapr_home.jsp
• http://www.nist.gov/itl/biometrics/
Large datasets allowing a relative comparison
Different formats, naming conventions
Lots of computations (scenarios, size of the database…)
Sometimes not free
19
J. Mahier, B. Hemery, M. El Abed, M. El-Allam, M. Bouhaddaoui, C. Rosenberger. « Computation EvaBio: A Tool for Performance Evaluation in Biometrics », International Journal of Automated Identification Technology (IJAIT), 2011.
Evaluation
20
M. El-Abed, P. Lacharme, and C. Rosenberger, "Security EvaBio: An Analysis Tool for the Security Evaluation of Biometric
Authentication Systems", the 5th IAPR/IEEE International
Conference on Biometrics (ICB), New Delhi, India, p. 1-6, 2012.
Evaluation
Security audit
21
Evaluation
Usability analysis
M. El Abed, R. Giot, B. Hemery, C. Rosenberger, « Evaluation of Biometric Systems : A Study of Users' Acceptance and Satisfaction »
Inderscience International Journal of Biometrics (IJBM), pages 1-27,
2011.
22
Evaluation
Update strategies analysis
R. Giot, B. Dorizzi, C. Rosenberger, "Analysis of Template Update Strategies for Keystroke Dynamics", SSCI 2011 CIBIM - 2011 IEEE
Workshop on Computational Intelligence in Biometrics and Identity
Management 2011
Performance analysis of an update strategy method for keystroke dynamics considering attacks
23
Evaluation
Evaluation of cancelable biometric systems
R. Belguechi, E. Cherrier, M. El Abed and C. Rosenberger, "Evaluation of Cancelable Biometric Systems : Application to
Finger-Knuckle-Prints", IEEE International Conference on Hand-
based Biometrics, 2011
24
GREYC research lab
Evaluation: a love story
Evaluation of biometric systems
Quality of biometric templates
Conclusions & perspectives
Outline
25
Quality of biometric data
Objective Quantifying the quality of a biometric raw data to optimize the performance of biometric systems
Patrick Grother, Elham Tabassi, "Performance of Biometric Quality
Measures", IEEE Transactions on Pattern Analysis and Machine
Intelligence archive, Volume 29 Issue 4, April 2007
26
Quality of biometric data
A generic approach
Image quality
Pattern-based quality
Multi-class SVM Quality
M. EL-Abed, B. Hemery, C. Charrier, and C. Rosenberger, "Evaluation de la qualité de données biométriques", RNTI journal,
special issue on "Qualité des Données et des Connaissances", p.
1-22, 2011.
Image quality: blind evaluation (without any reference)
Pattern-based quality: is there any interesting information in the image for the recognition ?
27
Quality of biometric data
M. Saad, A. C. Bovik and C. Charrier, “A DCT statistics-based blind image quality index,” IEEE Signal Processing Letters, 2010.
Image quality
BLIINDS [2] is a NR-IQ index combining three kinds of information:
Contrast distortion (v1)
Structure distortion (v2)
Anisotropy orientation (v3 & v4)
BLIINDS is entirely based on a DCT framework
It uses local DCT patch of size 17*17 to calculate the three information
Local contrast (pooled -> v1)
Kurtosis of the non-DCT coefficients (pooled -> v2)
2 measures based on Renyi Entropy (pooled -> v3 & v4)
For each patch k
28
Quality of biometric data
Pattern-based quality
The Scale-Invariant Feature Transform (SIFT)
SIFT
(X, Y) Scale Descriptor (128-
elements)
1) Number of keypoints detected from the image
2) DC coefficient of the m-by-n descriptors matrix (m = number of the keypoints detected and n = 128)
3) and 4) mean and standard deviation of scales
D. G. Lowe, “Distinctive image features from scale-invariant keypoints”. International journal of computer vision, 2004.
29
Quality of biometric data
Benchmark databases
Database Individuals/samples
FACES94 152 / 20
ENSIB 100 / 40
FERET 725 / average of 11
AR 120 / 26
30
Quality of biometric data
Synthetic alterations
An example of alterations for a reference image from FACES94. From
left to right, reference image then alteration level 1, 2 and 3
a) Blurring alteration
b) Gaussian noise alteration
c) Resize alteration
32
Quality of biometric data
The predicted EER /real EER values for each quality set
Database Good Fair Poor Very poor
FACES94 0.4744
0.2936
0.6843
0.5131
1.8078
1.661
5.7983
5.044
ENSIB 10.6397
10.413
13.2912
13.4
16.5495
16.53
17.787
17.774
FERET 31.88
26
32.23
30.187
32.52
32.12
34.37
33.757
P. Grother and E. Tabassi. Performance of biometric quality measures. IEEE Transactions on Pattern Analysis and Machine
Intelligence (PAMI), p. 531-543, 2007.
Validation
A good metric should be able to predict the performance of the biometric system based on the quality category
33
Quality of biometric data
M. El Abed, R. Giot, B. Hemery, C. Charrier, C. Rosenberger, "A SVM-Based Model for the evaluation of biometric sample quality" SSCI 2011 CIBIM -
2011 IEEE Workshop on Computational Intelligence in Biometrics and
Identity Management 2011.
Method Good Fair Poor Very poor
Contribution 0.869 0.828 0.797 0.626
NFIQ 0.82 0.698 0.632 0.64
Kolmogorov-Smirnov (KS) test of the genuine and impostor scores distribution
Comparison with NFIQ
Use the FVC2002 Db2 database (100 individuals, 8 samples)
Kolmogorov-Smirnov test on the intraclass and interclass distributions
34
Quality of biometric data
Applications
Optimization of the enrolment process
Comparison of biometric sensors
Use quality information in soft biometrics approaches
Use quality as a weighting factor in multibiometrics
35
GREYC research lab
Evaluation: a love story
Evaluation of biometric systems
Quality of biometric templates
Conclusions & perspectives
Outline
36
Conclusion
Evaluation of biometric systems: a major trend
• Transfer to industry
• Make the users confident in the technology
• Facilitate the work for researchers
Perspectives:
• Certification process for biometric systems ?
• “Biometrics Alliance Initiative”