© The Institution of Engineering and Technology
For an automatic comparison of a pair of biometric specimens, a similarity metric called ‘score’ is computed by the employed biometric recognition system. In forensic evaluation, it is desirable to convert this score into a likelihood ratio. This process is referred to as calibration. A likelihood ratio is the probability of the score given the prosecution hypothesis (which states that the pair of biometric specimens are originated from the suspect) is true divided by the probability of the score given the defence hypothesis (which states that the pair of biometric specimens are not originated from the suspect) is true. In practice, a set of scores (called training scores) obtained from the within-source and between-sources comparison is needed to compute a likelihood ratio value for a score. In likelihood ratio computation, the within-source and between-sources conditions can be anchored to a specific suspect in a forensic case or it can be generic within-source and between-sources comparisons independent of the suspect involved in the case. This results in two likelihood ratio values which differ in the nature of training scores they use and therefore consider slightly different interpretations of the two hypotheses. The goal of this study is to quantify the differences in these two likelihood ratio values in the context of evidence evaluation from a face, a fingerprint and a speaker recognition system. For each biometric modality, a simple forensic case is simulated by randomly selecting a small subset of biometric specimens from a large database. In order to be able to carry out a comparison across the three biometric modalities, the same protocol is followed for training scores set generation. It is observed that there is a significant variation in the two likelihood ratio values.
References
-
-
1)
-
15. Ali, T., Spreeuwers, L.J., Veldhuis, R.N.J.: ‘A review of calibration methods for biometric systems in forensic applications’. 33rd WIC Symp. on Information Theory in the Benelux, Boekelo, Netherlands, 2012, pp. 126–133.
-
2)
-
3. Lucy, D.: ‘Introduction to statistics for forensic scientists’ (John Wiley & Sons, Inc., 2005).
-
3)
-
21. Ramos-Castro, D., González-Rodrguez, J., Montero-Asenjo, A., et al: ‘Suspect-adapted map estimation of within-source distributions in generative likelihood ratio estimation’. Proc. IEEE Odyssey Speaker and Language Recognition Workshop, 2012, .
-
4)
-
16. Morrison, G.S.: ‘Tutorial on logistic-regression calibration and fusion: converting a score to a likelihood ratio’, Aust. J. Forensic Sci., 2012, 45, pp. 173–197 (doi: 10.1080/00450618.2012.733025).
-
5)
-
5. Robertson, B., Vignaux, G.A.: ‘Interpreting evidence’ (Wiley, Chichester, UK, 1995).
-
6)
-
24. Alberink, I., Jongh, A., Rodriguez, C.M.: ‘Fingermark evidence evaluation based on AFIS matching scores: sensitivity of likelihood ratios to different types of conditioning’, J Forensic Sci, 2014, 59, (1), pp. 70–81, (doi: 10.1111/1556-4029.12105).
-
7)
-
9. Ramos, D.: ‘Forensic evaluation of the evidence using automatic speaker recognition systems’. , Universidad Autonoma de Madrid, 2007.
-
8)
-
29. Mandasari, M.I., McLaren, M., Van Leeuwen, D.: ‘The effect of noise on modern automatic speaker recognition systems’. Proc. ICASSP, Kyoto, 2012.
-
9)
-
25. Evett, I.W., Buckleton, J.S.: ‘Statistical analysis of STR data’, in Carracedo, A., Brinkmann, B., Bär, W. (eds): ‘Advances in forensic haemogenetics’ (Springer-Verlag, New York, 1996).
-
10)
-
19. Brümmer, N., du Preez, J.: ‘Application-independent evaluation of speaker detection’, Comput. Speech Lang., 2006, 20, (2), pp. 230–275 (doi: 10.1016/j.csl.2005.08.001).
-
11)
-
22. Meuwly, D.: ‘Forensic individualization from biometric data’, Sci. Justice, 2006, 46, pp. 205–213 (doi: 10.1016/S1355-0306(06)71600-8).
-
12)
-
16. Champod, C., Meuwly, D.: ‘The inference of identity in forensic speaker recognition’, Speech Commun., 2000, 31, (2), pp. 193–203 (doi: 10.1016/S0167-6393(99)00078-3).
-
13)
-
4. Aitken, C.G.G., Taroni, F.: ‘Statistics and the evaluation of forensic evidence for forensic scientist’ (Wiley, Chichester, UK, 2004, 2nd edn).
-
14)
-
20. Davis, L.J., Saunders, C.P., Hepler, A.B., et al: ‘Using subsampling to estimate the strength of handwriting evidence via score-based likelihood ratios’, Forensic Sci. Int., 2012, 219, pp. 129–140 (doi: 10.1016/j.forsciint.2011.12.009).
-
15)
-
1. Jain, A.K., Flynn, P., Ross, A.: ‘Handbook of biometrics’ (Springer-Verlag, 2007).
-
16)
-
6. Morrison, G.S.: ‘Forensic voice comparison’, in Freckelton, I., Selby, H. (Eds.): ‘Expert evidence’ (Thomson Reuters, Sydney, Australia, 2010), .
-
17)
-
19. Nordgaard, A., Hoglund, T.: ‘Assessment of approximate likelihood ratios from continuous distributions: a case study of digital camera identification’, J. Forensic Sci., 2011, 56, pp. 390–402 (doi: 10.1111/j.1556-4029.2010.01665.x).
-
18)
-
30. Doddington, G., Liggett, W., Martin, A., et al: ‘Sheep, Goats, Lambs and Wolves: a statistical analysis of speaker performance in the NIST 1998 speaker recognition evaluation’. Proc. Int. Conf. Spoken Language Processing, 1998.
-
19)
-
26. Phillips, P.J., Flynn, P.J., Scruggs, T., et al: ‘Overview of the face recognition grand challenge’. Int. Conf. Computer Vision Pattern Recognition, 2005.
-
20)
-
12. Ali, T., Spreeuwers, L.J., Veldhuis, R.N.J., et al: ‘Effect of calibration data on forensic likelihood ratio from a face recognition system’. IEEE Sixth Int. Conf. Biometrics: Theory, Applications and Systems (BTAS), Washington DC, USA, 2013.
-
21)
-
22)
-
8. Rose, P.: ‘Technical forensic speaker recognition’, Comput. Speech Lang., 2006, 20, pp. 159–191 (doi: 10.1016/j.csl.2005.07.003).
-
23)
-
2. Peacock, C., Goode, A., Brett, A.: ‘Automatic forensic face recognition from digital images’, Sci. Justice: J. Forensic Sci. Soc., 2004, 44, (1), pp. 29 (doi: 10.1016/S1355-0306(04)71682-2).
-
24)
-
23. Botti, F., Alexander, A., Drygajlo, A.: ‘An interpretation framework for the evaluation of evidence in forensic automatic speaker recognition with limited suspect data’. Proc. Odyssey the Speaker and Language Recognition Workshop, Toledo, Spain, 2004, pp. 63–68.
-
25)
-
2. Meuwly, D., Veldhuis, R.N.J.: ‘Forensic biometrics: from two communities to one discipline’. Proc. Int. Conf. Biometrics Special Interest Group (BIOSIG), Darmstadt, Germany, 2012, pp. 1–12.
-
26)
-
57. Neumann, C., Evett, I.W., Skerrett, J.: ‘Quantifying the weight of evidence from a forensic fingerprint comparison: a new paradigm’, J. R. Stat. Soc. A, 2012, 175, (2), pp. 371–415 (doi: 10.1111/j.1467-985X.2011.01027.x).
-
27)
-
28)
-
17. Fawcett, T., Niculescu-Mizil, A.: ‘PAV and the ROC convex hull’, Mach. Learn., 2007, 68, pp. 97–106 (doi: 10.1007/s10994-007-5011-0).
-
29)
-
13. Ali, T., Spreeuwers, L.J., Veldhuis, R.N.J.: ‘Towards automatic forensic face recognition’. Int. Conf. Informatics Engineering and Information Science (ICIEIS), Communications in Computer and Information Science, Springer Verlag, Kuala Lumpur, Malaysia, 2011, vol. 252, pp. 47–55.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-bmt.2014.0009
Related content
content/journals/10.1049/iet-bmt.2014.0009
pub_keyword,iet_inspecKeyword,pub_concept
6
6