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 • Score normalization methods • Fusion methods • Experiment Results • Conclusion

3. Reference Paper • A. K. Jain, K. Nandakumar, and A. Ross, “Score normalization in multimodal biometric systems," Pattern Recognition , 2005.

4. Why score normalization ? • 1. The matching scores at the output of the individual matchers may not be homogeneous. • 2. The outputs of the individual matchers need not be on the same numerical scale (range). • 3. The matching scores at the output of the matchers may follow different statistical distributions.

5. Why score normalization ? • Score normalization refers to changing the location and scale parameters of the matching score distributions at the output of the individual matchers, so that the matching scores of different matchers are transformed into a common domain.

6. Score normalization • When the parameters used for normalization are determined using a fixed training set, it is referred to as fixed score normalization. • In adaptive score normalization, the normalization parameters are estimated based on the current feature vector.

7. A good normalization scheme • Robustness refers to insensitivity to the presence of outliers. • Efficiencyrefers to the proximity of the obtained estimate to the optimal estimate when the distribution of the data is known.

8. Normalization Techniques • 1. Min-max • 2. Decimal scaling • 3. z-score • 4. Median and MAD • 5. Double sigmoid function • 6. tanh-estimators

9. 1. Min-max normalization • Min-max normalization is best suited for the case where the bounds (maximum and minimum values) of the scores produced by a matcher are known. • We usually shift the minimum and maximum scores to 0 and 1. • xk : the kth matching score before normalization • xk’ : the kth matching score after normalization

10. 1. Min-max normalization • This method is not robust (i.e., the method is highly sensitive to outliers in the data used for estimation). • Min-max normalization retains the original distribution of scores except for a scaling factor and transforms all the scores into a common range [0, 1].

11. 2. Decimal scaling • For example, if one matcher has scores in the range [0, 1] and the other has scores in the range [0, 1000], the following normalization could be applied. • The problems with this approach are lack of robustness.

12. 3. z-score • The most commonly used score normalization technique is the z-score that is calculated using the arithmetic mean and standard deviation of the given data. • Both mean and standard deviation are sensitive to outliers and, hence, this method is not robust. • Z-score normalization does not guarantee a common numerical range for the normalized scores of the different matchers. • If the input scores are not Gaussian distributed, z-score normalization does not retain the input distribution at the output.

13. 3. z-score

14. 4. Median and MAD • Robust : The median and median absolute deviation (MAD) are insensitive to outliers and the points in the extreme tails of the distribution. • This normalization technique does not retain the input distribution and does not transform the scores into a common numerical range.

15. 4. Median and MAD

16. 5. Double sigmoid function • The normalized score is given by where m is the reference operating point and s1 and s2 denote the left and right edges of the region

17. 5. Double sigmoid function • where the scores in the [0, 300] range are mapped to the [0, 1] range using m = 200, s1 = 20 and s2 = 30. • Generally, m is chosen to be some value falling in the region of overlap between the genuine and impostor score distribution, and s1 and s2 are made equal to the extent of overlap between the two distributions toward the left and right of m, respectively.

18. 5. Double sigmoid function

19. Hampel estimators are based on the following influence ( )-function: 6. tanh-estimators • The tanh-estimators introduced by Hampel et al. are robust and highly efficient. • The normalization is given by where μGH and σGH are the mean and standard deviation estimates, respectively, of the genuine score distribution as given by Hampel estimators

20. 6. tanh-estimators

21. Summary of Normalization Techniques

22. Experimental Results • Database of 100 users with three modalities. • Each user having five biometric templates for each modality.

23. Experimental Results

24. Experimental Results

25. Experimental Results

26. Experimental Results

27. Experimental Results

28. Experimental Results

29. Experimental Results

30. Feature Level Fusion • “Biometric A” feature vectors : X • “Biometric B” feature vectors : Y • Normalization -> X’ , Y’ • Dimension reduction • Combine two vector -> Z’ = { X’ , Y’ }

31. Reference Paper • A. Ross and R. Govindarajan. “Feature Level Fusion Using Hand and Face Biometrics.” In Proc. SPIE Conf. on Biometric Technology for Human Identication II, volume 5779, pages 196-204,Orlando, 2005. • SON, B. and LEE, Y. “The Fusion of Two User-friendly Biometric Modalities: Iris and Face”, IEICE Transactions on Information and Systems , 2006.

32. Fusion in feature and matching level • Normalization method : median and MAD • Dimension reduction method : PCA , LDA • Matching score fusion method : sum rule • Consider feature vectors {Xi ,Yi} and {Xj , Yj} obtained at two different time instances i and j. • Fusion in feature level -> { Zi ,Zj } • Let sX and sY be the normalized match (Euclidean distance) scores generated by comparing Xi with Xj and Yi with Yj , respectively. • smatch = (sX + sY)/2 be the fused match score obtained using the simple sum rule.

33. Experimentation • A set of 500 face images and hand images were acquired from 100 users (5 biometric samples per user per biometric) • Each face image was decomposed into its component R, G, B channels. Further, the grayscale rendition of the color image - I - was also computed. • The Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) were performed on these component images (i.e., R, G, B, I) in order to extract representational features.

34. Experimental Results

35. Experimental Results

36. The Fusion of Two User-friendly Biometric Modalities: Iris and Face

37. Fusion method • Dimension reduction method : • Wavelet Transform • LDA

38. Experimentation • Face Databases: • IISFace : We sampled frontal face images of 100 subjects from the IIS face database. Each subject has 10 images with varying expressions. • Iris Databases: • Iris1 : This data set consists of 1000 iris images acquired from 100 individuals. (good quality images) • Iris2 : The Iris2 database consists of 1000 iris images containing some bad quality ones acquired from 100 individuals.

39. Experimental Results

40. Experimentation • Face Databases: • ORLFace : The ORL data set consists of 400 frontal faces: 10 tightly cropped images of 40 subjects with variations in poses, illuminations, facial expressions and accessories. • Iris Databases: • Iris3 : The Iris3 database is composed of 400 good quality images sampled from the Iris1 database to combine with the ORLFace database. • Iris4 : The Iris4 is composed of 400 iris images containing some bad quality ones sampled from the Iris2 database to combine with the ORLFace.

41. Experimental Results

42. Reference Paper • M. Indovina, U. Uludag, R. Snelick, A. Mink and A. Jain, "Multimodal Biometric Authentication Methods: A COTS Approach", Proc. MMUA 2003, Workshop on Multimodal User Authentication, pp. 99-106, Santa Barbara, CA, December 11-12, 2003.

43. abstract • We examine the performance of multimodal biometric authentication systems using Commercial Off-the-Shelf (COTS) fingerprint and face biometrics. • It introduce novel methods of fusion and normalization that improve accuracy still further through population analysis.

44. Normalization methods • a matcher score as s from the set S of all scores for that matcher and the corresponding normalized score as n. • Min-Max • maps the scores to the [0, 1] range.

45. Normalization methods • Z-score • transforms the scores to a distribution with mean of 0 and standard deviation of 1. • Tanh • robust statistical techniques. • maps the scores to the (0, 1) range.

46. Normalization methods • Adaptive • Using an adaptive normalization procedure that aims to increase the separation of the genuine and impostor distributions.

47. Normalization methods • Two-Quadrics • composed of 2 quadratic segments that change concavity at c.

48. Normalization methods • Logistic • logistic function • The general shape of the curve is similar to Two-Quadrics • f(0) is equal to the constant Δ, which is selected to be a small value (0.01 in this study).

49. Normalization methods • Quadric-Line-Quadric • The overlapped zone, w, is left unchanged while the other regions are mapped with two quadratic function segments.

50. Fusion methods • Simple Sum • Scores for an individual are summed. • Min Score • Choose the minimum of an individual’s scores. • Max Score • Choose the maximum of an individual’s scores.