Fusion by Biometrics

1. Fusion by Biometrics 主講人：李佳明、陳明暘 指導教授：林維暘

2. Outline • Introduction • Biometric system • Feature extraction • The advantage of verification in biometrics • The flow of verification • Fusion methods • Experiment Results • Conclusion • Reference

3. Introduction • Multimodal biometrics systems consolidate the evidence presented by multiple biometric sources and typically provide better recognition performance compared to systems based on a single biometric modality. • Multi-biometrics systems provide anti-spoofing measures by making it difficult for an intruder to spoof multiple biometric traits simultaneously.

4. Biometrics

5. Comparison of various biometric technologies

6. The advantage of Multimodal Biometric • Multiple biometric sources enhance matching performance. • Reducing failure to enroll rate. • Difficult to spoof multiple traits simultaneously.

7. A biometric system

8. A biometric system • A biometric-based authentication system operates in two modes • 1. Enrollment mode • 2. Authentication mode

9. A biometric system • 1. Enrollment： • A user’s biometric data is acquired using a biometric reader and stored in a database. • The stored template is labeled with a user identity (e.g., name, identification number, etc.) to facilitate authentication.

10. A biometric system • 2. Authentication： • A user’s biometric data is once again acquired and the system uses this to either identify who the user is, or verify the claimed identity of the user. • Identification：Comparing the acquired biometric information against templates corresponding to all users in the database. • Verification：Comparison with only those templates corresponding to the claimed identity.

11. A biometric system

12. Feature extraction • Fingerprint • Face • Hand Geometry • Iris

13. Feature extraction • Fingerprint friction ridge details are generally described in a hierarchical order at three different levels： • Level 1 - pattern • Level 2 - minutia points • Level 3 - pores and ridge contours • Automated Fingerprint Identification Systems (AFIS) currently rely only on Level 1 and Level 2 features.

14. Feature extraction • Level 1 features, or patterns, are themacro details of the fingerprint such as ridge flow and patterntype.

15. Feature extraction • Level 2 features, or points, refer to the Galton characteristics or minutiae, such as ridge bifurcations and endings.

16. Feature extraction • Level 3 features, or shape, include all dimensional attributes of the ridge such as ridge path deviation, width, shape, pores, edge contour, incipient ridges, breaks, creases, scars, and other permanent details.

17. Feature extraction • Fingerprint image resolution. The same fingerprint captured at three different image resolutions • (a) 380 ppi (Identix 200DFR) • (b) 500 ppi (CrossMatch ID1000) • (c) 1,000 ppi (CrossMatch ID1000).

18. Feature extraction • Different levels of fingerprint features detected. • Level 3 features are matched using the ICP algorithm.

19. Feature extraction

20. Feature extraction • Reference point (X), the region of interest, and 80 sectors (B = 5, k = 16) superimposed on a fingerprint

21. Feature extraction • Face recognition is an important biometric identification technology. Facial scan is an effective biometric attribute/indicator. • The performance of face recognition systems dependent on consistent conditions such as lighting, pose and facial expression.

22. Feature extraction • Preprocessing • 幾何位置的調整 - 取人臉影像中兩個control point，分別為左眼的中心點和右眼的中心點，利用這兩個控制點。 • 明亮度的調整 - histogram equalization，此步驟是為了縮小各張影像之間亮度的改變所造成的差異

23. Feature extraction • 擷取三個人臉區域，在每個區域裡面，全部的影像灰階值都會被儲存在一個向量，該向量就是該區域的特徵向量。 • 利用了 Principal Component Analysis (PCA)將特徵向量降維。

24. Feature extraction • Automatic feature extraction for 3D face matching.

25. Feature extraction • Segmentation of facial scan.

26. Feature extraction • For a frontal facial scan, nose tip usually has the largest z value.

27. Feature extraction • Pose angle quantization. • Example of directional maximum.

28. Feature extraction • extracted nose profiles.

29. Feature extraction • Feature extraction results which lead to correct 3D face matches.

30. Feature extraction • Some biometrics may not be acceptable for the sake of protecting an individual's privacy. • As hand geometry information is not very distinctive, it is distinctive enough for verification but not for identification. • It is simple method of sensing which does not impose undue requirements on the imaging optics.

31. Feature extraction • Hand geometry sensing device. • 5 images of the same hand are taken.

32. Feature extraction • Hand shape alignment • We represent the shape of a hand by a set of ordered points in the Euclidean plane.

33. Feature extraction • The fourteen axes along which feature values are computed.

34. Feature extraction • The iris is a protected internal organ whose random texture is complex, unique, and stable throughout life . • It can serve as a kind of living passport or password that one need not remember but can always present. • "Biometric Personal Identification System Based on Iris Analysis." U.S. Patent No. 5,291,560 issued March 1, 1994 (J. Daugman).

35. Feature extraction • Finding an Iris in an Image • minimum of 70 pixels in iris radius. Iris radius of 80 to 130 pixels has been more typical. • Monochrome CCD cameras (480 x 640) have been used. • using a coarse-to-fine strategy terminating in single-pixel precision estimates of the center coordinates and radius of both the iris and the pupil.

36. Feature extraction • The outline overlay shows results of the iris and pupil localization.

37. Feature extraction • Iris Feature Encoding by 2D Wavelet Demodulation. • Each isolated iris pattern is then demodulated to extract its phase information using quadrature 2D Gabor wavelets. • This process is repeated all across the iris with many wavelet sizes, frequencies, and orientations, to extract 2,048 bits.

38. Feature extraction • Advantages of the Iris for Identification • Highly protected, internal organ of the eye. • Externally visible; • high degree of randomness . • Pre-natal morphogenesis (7th month of gestation) • Limited genetic penetrance of iris patterns • Patterns apparently stable throughout life • Encoding and decision-making are tractable

39. Feature extraction • Disadvantages of the Iris for Identification • Small target to acquire from a distance • Located behind a curved, wet, reflecting surface • Obscured by eyelashes, lenses, reflections • Partially occluded by eyelids, often drooping • Deforms non-elastically as pupil changes size • Illumination should not be visible or bright

40. A biometric system has four important components 1. Sensor module: • Acquire the biometric data of an individual. 2. Feature extraction module : • Acquire data is processed to extract feature values.

41. A biometric system has four important components 3.Matching module : • Feature values are compared against those in the template by generating a matching score. 4.Decision-making module : • The user’s identity is established or a claimed identity is either accepted or rejected based on the matching score generated in the matching module.

42. Fusion in biometrics (1) Fusion at the feature extraction level : • 1. The data obtained from each sensor is used to compute a feature vector. • 2. Concatenate the two vectors into a single new vector. • 3. Feature reduction techniques may be employed.

43. Multimodal biometric system A prototype multimodal biometric system.

44. Fusion in biometrics (2) Fusion at the matching scorelevel : • Each system provides a matching score indicating the proximity of the feature vector with the template vector. • These scores can be combined to assert the veracity of the claimed identity.

45. Fusion in biometrics (3) Fusion at the decision level: • Each sensor can capture multiple biometric data and the resulting feature vectors individually classified into the two classes –– accept or reject. • A majority vote scheme can be used to make the final decision.

46. Fusion in biometrics • Fusion in the context of biometrics can take the following forms : • (1) Single biometric multiple representation. • (2) Single biometric multiple matchers. • (3) Multiple biometric fusion.

47. Fusion in biometrics • (1) Single biometric multiple representation. • This type of fusion involves using multiple representations on a single biometric indicator. • Typically, each representation has its own classifier.

48. Fusion in biometrics • (2) Single biometric multiple matchers. • It is also possible to incorporate multiple matching strategies in the matching module of a biometric system and combine the scores generated by these strategies.

49. Fusion in biometrics • (3) Multiple biometric fusion. • By integrating matching scores obtained from multiple biometric sources. • These include majority voting, sum and product rules, k-NN classifiers, SVMs, decision trees, Bayesian methods, etc.

50. Fusion in biometrics • (4) Others • 1. Store multiple templates in database. • Example : A fingerprint biometric system may store multiple templates of a users fingerprint (same finger) in its database. When a fingerprint impression is presented to the system for verification, it is compared against each of the templates, and the matching score generated by these multiple matchings are integrated.