JIS X 8101-1:2010 情報技術―バイオメトリック性能試験及び報告―第１部：原則及び枠組み | ページ 13

                                                                                             57
                                                            X 8101-1 : 2010 (ISO/IEC 19795-1 : 2006)
                                          附属書F
                                          (参考)
                    ROC,DET,CMCを生成するアルゴリズム
F.1   ROC及びDETのためのアルゴリズム
  DET又はROC上のデータ点を効率的に導くための手順を,次に示す。
a) 本人照合得点値を増加順にソートする。s1b) それぞれの本人照合得点値の頻度を数える。g1, g2, g3, ···, gk
c) 各区間(−∞, s1), (s1, s2), (s2, s3), ···, (sk, ∞)の偽者スコアの数を数える。それぞれをh0, h1, h2, ···, hkとす
    る。
d) 順にそれぞれの本人照合得点値(sj)を得る。
  1)   j以上の偽者スコアの数を数える。次によるkj i=hi 。
  2) 偽者入力試行の総数で除すことで,この照合得点のいき(閾)値における誤合致率を与える。
                                                      j−1
  3)   jより小さい本人照合得点の数を数える。次による igi
                                                      =1
                                                          。
  4) 本人入力試行の総数で除すことで,この照合得点のいき(閾)値における誤非合致率を与える。
F.2   CMCを生成するためのアルゴリズム
  効率的なデータ生成を行うための手順を,次に示す(一人につきテンプレートが1個と仮定する)。
a) 各入力試行における識別順位の決定を,次に示す。
  1) 入力試行に対する本人照合得点値を調べる。
  2) 次の入力試行(偽者テンプレートと本人テンプレートとの組合せに対して)における照合得点の数
      を数える。
    i)  本人照合得点値より大きいスコアの数 : x
    ii) 本人照合得点値と等しいスコアの数 : y
  3) (y=1)ならば,入力試行は識別順位(x+1)をもち,さもなければ,順位は(x+1), ···, (x+y)の範囲の値
      で定義される。
b) それぞれの(注目した)順位rに対して
  1)   以下の順位の入力試行の数を数える。順位が一意に決まらず,ある範囲内で計算される入力試行
      は,その区間のうち順位r以下にある値の割合をカウントする。
  2) 入力試行の総数で除すことで,テストサンプルにとっての真のテンプレート/モデルが生体情報登
      録データベース内の類似したテンプレートとして,r番目以内に見つかる確率が得られる。この確
      率は,CMCグラフ上でrに対してプロットされる。

――――― [JIS X 8101-1 pdf 61] ―――――

58
X 8101-1 : 2010 (ISO/IEC 19795-1 : 2006)
                                          参考文献
[1]   Fejfar, A. and Myers, J.W. The testing of three automatic identity verification techniques. Proceedings of the
      International Conference on Crime Countermeasures, Oxford, July 1977
[2]   Davies, D.W. and Price, W.L. Security for computer networks, Wiley, 1984. (Sections 7.10 & 7.11 review
      several performance evaluations)
[3]   Holmes, J.P., Wright, L.J., and Maxwell, R.L. A performance evaluation of biometric identification devices.
      Sandia report SAND91-0276, June 1991
[4]   Bouchier, F., Ahrens, J.S., and Wells, G. Laboratory evaluation of the iriscan prototype biometric identifier.
      Sandia report SAND96-1033, April 1996
[5]   Rauss, P., Phillips, P.J., Hamilton, M.K. and DePersia, A.T. FERET (face recognition technology)   ecognition
      algorithms. Proceedings of Automatic Target Recognizer System and Technology Conference, July 1996
[6]   Roethenbaugh, G. ICSA biometric certification. Biometric industry product buyer's guide, ICSA, 1998, 27-31
[7]   BIOIS: Comparative study of biometric identification systems: Public final report. Study by Fraunhofer- IGD
      for BSI (German Information Security Agency)   nd BKA (German Federal Police Agency), May 2000
[8]   Blackburn, D., Bone, M. and Phillips, J. Facial recognition vendor test 2000. February 2001
[9]   Mansfield, A.J., Kelly, G.P., Chandler, D.J. and Kane, J. Biometric product testing final report. Report for
      CESG and Biometrics Working Group, March 2001
[10]  Maio, D., Maltoni, D., Cappelli, R., Wayman, J.L. and Jam, A.K. FVC2000: Fingerprint verification
      competition. IEEE Trans. PAMI, 2002, 24(3), 402-412
[11]  Phillips, P.J., Grother, P., Michaels, R.J., Blackburn, D.M., Tabassi, E. and Bone, M. Face recognition vendor
      test 2002 Evaluation Report. NIST IR 6965, 2003
[12]  Mansfield, A.J. and Wayman, J.L. (2002)   est Practices in Testing and Reporting Performance of Biometric
      Devices, Version 2.01, NPL Report CMSC 14/02
[13]  Doddington, G.R., Przybocki, M.A., Martin, A.F. and Reynolds, D.A. The NIST speaker recognition
      evaluation: Overview methodology, systems, results, perspective. Speech Communication, 2000, 31(2-3),
      225-254
[14]  Phillips, P.J., Martin, A., Wilson, C.L. and Przybocki, M. An introduction to evaluating biometric systems.
      Computer, (Feb 2000), 56-63
[15]  Hennessy, J.L. and Patterson, D.A. Computer Architecture: A Quantitative Approach, 2nd ed., Morgan
      Kaufman, San Francisco, 1996
[16]  Doddington, G., Liggett, W., Martin, A., Przybocki, M. and Reynolds, D. Sheep, goats, lambs and wolves: A
      statistical analysis of speaker performance in the NIST 1998 speaker recognition evaluation. ICSLP,
      November 1998
[17]  Wayman, J.L. Multi-finger penetration rate and ROC variability for automatic fingerprint identification
      systems. National Biometric Test Center, May 1999
[18]  ISO/IEC 19794-4, Information technology−Biometric data interchange formats−Part 4: Finger image data
[19]  ISO/IEC 19794-5, Information technology−Biometric data interchange formats−Part 5: Face image data
[20]  ISO/IEC 19794-6, Information technology−Biometric data interchange formats−Part 6: Iris image data

――――― [JIS X 8101-1 pdf 62] ―――――

                                                                                             59
                                                            X 8101-1 : 2010 (ISO/IEC 19795-1 : 2006)
[21]  Cox, R. Three new speech coders from the ITU cover a range of applications. IEEE Communications
      Magazine, 1997, 35(9-special issue on standardization and characterization of G729), 40-47
[22]  Wayman, J.L. Technical testing and evaluation of biometric identification devices. Biometrics: Personal
      identification in networked society, edited by A.K. Jain, et al., Kluwer, 2000, 345-368
[23]  Godfrey, J., Graff, D. and Martin, A. Public databases for speaker recognition and verification. ESCA
      Workshop on Automatic Speaker Recognition, Identification and Verification, 1994
[24]  Wayman, J.L. Confidence interval and test size estimation for biometric data. Proceedings of the IEEE
      AutoID Conference, 1999
[25]  Newman, H.H., Freeman, F.N. and Holzinger, J.K. Twins, Chicago University Press, 1937. Results on
      fingerprint similarity between identical twins cited in [31, table 10.20.1]
[26]  Daugman, J. and Downing, C. Epigenetic randomness, complexity, and singularity of human iris patterns.
      Proceeding of the Royal Society Biological Sciences, 2001, 268, 1737-1740
[27]  Jain, A.K., Prabhakar, S. and Pankanti, S. On the similarity of identical twin fingerprints. Pattern
      Recognition, 2002, 35(11), 2653-2663
[28]  Louis, T.A. Confidence intervals for a binomial parameter after observing no successes. The American
      Statistician, 1981, 35(3), 154
[29]  Hanley, J.A. and Lippman-Hand, A. If nothing goes wrong, is everything all right・ Interpreting zero
      numerators. Journal of the American Medical Association, 1983, 249(13), 1743-1745
[30]  Jovanovic, B.D. and Levy, P.S. A look at the rule of three. The American Statistician, 1997, 51(2), 137-139
[31]  Snedecor, G.W. and Cochran, W.G. Statistical methods, Iowa State University Press, 1967 (Sixth edition)
[32]  Efron, B. and Tibshirani, R.J. An introduction to the bootstrap, Chapman and Hall, 1997
[33]  Diegert, K.V. Estimating performance characteristics of biometric identifiers. Proceedings of Biometrics
      Consortium Conference, San Jose, CA, June 1996
[34]  Bolle, R.M., Ratha, N.K. and Pankanti, S. Confidence interval measurement in performance analysis of
      biometric systems using the bootstrap. Proceedings of Workshop on Empirical Evaluation Methods in
      Computer Vision, Hawaii, December 2001
[35]  Maltoni, D. et al, Handbook of Fingerprint Recognition, Springer, 2003
[36]  Lumini, A, Maio, D. and Maltoni, D., Continuous versus exclusive classification for fingerprint retrieval,
      Pattern Recognition Letters, Vol.18, No.10, pp.1027-1034, 1997
[37]  Uchida, K., Kamei, T., Mizoguchi, M. and Temma, T., Fingerprint Card Classification with Statistical Feature
      Integration, Proceedings of the 14th International Conference on Pattern Recognition, Brisbane, Australia,
      pp.1833-1839, August 1998
[38]  Cappelli, R. and Maio, D., The State of the Art in Fingerprint Classification, in Ratha N. and Bolle R. (Eds.)
      Automatic Fingerprint Recognition, Chapter 9, pp.183-205
[39]  Kamei, T. Fingerprint Pre-selection Using Eigenfeatures for a Large-Size Database, in Ratha N. and Bolle, R.
      (Eds.), Automatic Fingerprint Recognition, Chapter 13, pp. 263-282