ARTICLE I.Mantasari_IETBMT_2014/IDIAP Score Calibration in Face Recognition Mandasari, Miranti I. Günther, Manuel Wallace, Roy Saedi, Rahim Marcel, Sébastien Van Leeuwen, David calibration performance evaluation calibration performance metric categorical calibration face recognition system Inter-session Variability Modelling likelihood ratio interpretation linear score transformation linearly calibrated face recognition scores mobile biometrics speaker recognition field surveillance camera face databases EXTERNAL https://publications.idiap.ch/attachments/papers/2014/I.Mantasari_IETBMT_2014.pdf PUBLIC https://publications.idiap.ch/index.php/publications/showcite/I.Mantasari_Idiap-RR-01-2014 Related documents IET Biometrics 1-11 2047-4938 2014 http://digital-library.theiet.org/content/journals/10.1049/iet-bmt.2013.0066 URL 10.1049/iet-bmt.2013.0066 doi This paper presents an evaluation of verification and calibration performance of a face recognition system based on inter-session variability modeling. As an extension to the calibration through linear transformation of scores, categorical calibration is introduced as a way to include additional information of images to calibration. The cost of likelihood ratio, which is a well-known measure in the speaker recognition field, is used as a calibration performance metric. Evaluated on the challenging MOBIO and SCface databases, the results indicate that through linear calibration the scores produced by the face recognition system can be less misleading in its likelihood ratio interpretation. In addition, it is shown through the categorical calibration experiments that calibration can be used not only to assure likelihood ratio interpretation of scores, but also improving the verification performance of face recognition system. REPORT I.Mantasari_Idiap-RR-01-2014/IDIAP Score Calibration in Face Recognition I. Mantasari, Miranti Günther, Manuel Wallace, Roy Saedi, Rahim Marcel, Sébastien Van Leeuwen, David calibration forensic face recognition likelihood ratio linear score transformation. EXTERNAL https://publications.idiap.ch/attachments/reports/2013/I.Mantasari_Idiap-RR-01-2014.pdf PUBLIC Idiap-RR-01-2014 2014 Idiap January 2014 This paper presents an evaluation of verification and calibration performance of a face recognition system based on inter-session variability modeling. As an extension to the calibration through linear transformation of scores, categorical calibration is introduced as a way to include additional information of images to calibration. The cost of likelihood ratio, which is a well-known measure in the speaker recognition field, is used as a calibration performance metric. Evaluated on the challenging MOBIO and SCface databases, the results indicate that through linear calibration the scores produced by the face recognition system can be less misleading in its likelihood ratio interpretation. In addition, it is shown through the categorical calibration experiments that calibration can be used not only to assure likelihood ratio interpretation of scores, but also improving the verification performance of face recognition system.