Post on 23-Feb-2016
description
FATEMEH ARBABDEPARTMENT OF COMPUTER SCIENCE
UNIVERSITY OF CALGARYFARBAB@UCALGARY.CA
WINTER 2009
Ear Biometric
2
Out line
IntroductionAnatomy of EarInnarelli systemBurge and BurgerPCAHurley, Nixon and CarterAkkermans, Kenvenaar and SchobbenConclusion
3
Introduction
Why Ear? Stable structure Predictable change with age It’s fixed position Collection hygiene issues Unlikely to cause anxiety
4
Anatomy of Ear
5
Innarelli System
Used for forensic in 1949, USA
Specified distances Race Sex
6
Burge and Burger
Neighbor Graph Matching, 1998
Ear print Voronoi Diagram Neighbor Graph
7
Burge and Burger
Improving FAR
Still is not practical! Ear description is unstable Detected edges were occluded parts rather than surface
discontinuities Occlusion with hair
Thermogram
8
Principle Component Analysis
Basis elements in a Vector space
9
Principle Component Analysis
Implementation
Recognition rate of 98.4% on a data set of 252 ear images
10
Hurley, Nixon and Carter
Force Field Transform, 2005
11
Hurley, Nixon and Carter
Force Field Transforms:
Invertible transforms
12
Hurley, Nixon and Carter
Sample
Promising results on small database
13
Akkermans, Kenvenaar and Schobben
Acoustic Ear Recognition, 2005
Correlation of emitted and reflected wave Applicable on headphones or modified mobile phones 31 and 17 samples, respectively
14
Conclusion
Summary
Approach Neighbor Graph Matching
PCA Force Field Transform
Acoustic Ear Recognition
Data Source
2D 2D 2D Active Identification
Data Size n/a 189 n/a n/a
Recognition Rate
n/a 98.4% n/a n/a
15
What else…
Sample of 3D ear biometric
Iterative Closest Point
16
Major References
[1] D. J. Hurley, B. Arbab-Zavar, M. S. Nixon, The Ear as a Biometric, Handbook of Biometrics, Springer, 2008, pp.131-150.
[2] M. Burge, W. Burger, Ear Biometrics, BIOMETRICS: Personal Identification in a networked Society, Klumer Academic, 1998, pp. 273-286.
[3] K. H. Pun, Y. S. Moon, Recent advances in Ear Biometrics, in the proceedings of Sixth IEEE International Conference on Automatic Face and Gesture Recognition, May 2004, pp. 164-169.
[4] D. J. Hurley, M. S. Nixon, J. N. Carter, Force field feature extraction for ear biometrics, Computer Vision and Image Understanding, Elsevier Science, 2005, pp. 491-512.
[5] A. H. M. Akkermans, T. A. M. Kenvenaar, D. W. E. Schobben, Acoustic Ear Recognition for person Identification, in the proceedings of the Fourth IEEE Workshop on Automatic Identification Advanced Technologies, 2005, pp. 219-223.
[6] A. Okabe, B. Boots, K. Sugihara, Spatial Tessellations: concepts and applications of voronoi diagrams, John Wiley & Sons, 1992, chapter 3.
17
Thank You!