Chinchilla, R., & Baker, B. G. (2013, June), Methodology for Evaluating Statistical Equivalence in Face Recognition Using Live Subjects with Dissimilar Skin Tones  Paper presented at 2013 ASEE Annual Conference & Exposition, Atlanta, Georgia. 10.18260/1-2--22286

\bibitem{asee_peer_22286}
  Chinchilla, R., \& Baker, B. G. (2013, June), \emph{Methodology for Evaluating Statistical Equivalence in Face Recognition Using Live Subjects with Dissimilar Skin Tones}
  Paper presented at 2013 ASEE Annual Conference \& Exposition, Atlanta, Georgia.
  10.18260/1-2--22286

Rigoberto Chinchilla and Bryan G. Baker.  "Methodology for Evaluating Statistical Equivalence in Face Recognition Using Live Subjects with Dissimilar Skin Tones".  2013 ASEE Annual Conference & Exposition, Atlanta, Georgia, 2013, June.  ASEE Conferences, 2013.  https://peer.asee.org/22286 Internet.  12 Mar, 2025

\bibitem{asee_peer_22286}
  Rigoberto Chinchilla and Bryan G. Baker.
  "Methodology for Evaluating Statistical Equivalence in Face Recognition Using Live Subjects with Dissimilar Skin Tones".
  \emph{2013 ASEE Annual Conference \& Exposition, Atlanta, Georgia, 2013, June}.
  ASEE Conferences, 2013.
  https://peer.asee.org/22286 Internet.  12 Mar, 2025

@INPROCEEDINGS{asee_peer_22286
author = "Rigoberto Chinchilla and Bryan G. Baker"
title = "Methodology for Evaluating Statistical Equivalence in Face Recognition Using Live Subjects with Dissimilar Skin Tones"
booktitle = "2013 ASEE Annual Conference \& Exposition"
year = "2013"
month = "June"
address = "Atlanta, Georgia"
publisher = "ASEE Conferences"
note = {https://peer.asee.org/22286}
number = {10.18260/1-2--22286}
}

TY  - CPAPER
AB  -            Methodology for Evaluating Statistical Equivalence in Face           Recognition Using Live Subjects with Dissimilar Skin TonesThe general purpose of this study is to propose a methodology that can be employed in theapplication of facial recognition systems (FRS) to determine if a statistically significantdifference exists in a facial recognition system’s ability to match two dissimilar skin tonepopulations to their enrolled images. In particular, to test the face recognition system’s ability torecognize dark or light skin tone subjects. In addition to the direct comparison of results fromtwo different populations, this study uses a Box Behnken Design to examine four factorscommonly effecting facial recognition systems. The four factors tested were angle of the cameraviewing the subject; both horizontally to the left and right, as well as vertically, both above andbelow the subject’s line of sight. Additionally, the distance the subjects are from the camera, andthen intensity of the illumination on the subject. The experimentation was approached from theassumption that subjects are cooperative, following guidelines for proper enrollment andsubmission for matching. The experimentation of the four factors was conducted using two setsof three subjects. One set was dark skin tone males, and the second set was light skin tonemales. The results of the study showed a significance statistical difference at p = 0.05 levelbetween the two skin tones, with greater difficulty identifying the light skin tone test subjectsthan those with dark skin tone.
AU  - Rigoberto Chinchilla
AU  - Bryan G. Baker
CY  - Atlanta, Georgia
DA  - 2013/06/23
PB  - ASEE Conferences
TI  - Methodology for Evaluating Statistical Equivalence in Face Recognition Using Live Subjects with Dissimilar Skin Tones
UR  - https://peer.asee.org/22286
DO  - 10.18260/1-2--22286
ER  -