P J. Phillips, J. R. Beveridge, Geof H. Givens, Bruce A. Draper
A statistical study is presented quantifying the effects of covariates such as gender, age, expression, image resolution and focus on three face recognition algorithms. Specifically, a Generalized Linear Mixed Effect model is used to relate probability of verification to sub ject and image covariates. The data and algorithms are selected from the Face Recognition Grand Challenge and the results show that the effects of covariates are strong and algorithm specific. The paper presents in detail all of the significant effects including interactions among covariates. One significant conclusion is that covariates matter. The variation in verification rates as a function of covariates is greater than the difference in average performance between the two best algorithms. Another is that few or no universal effects emerge; almost no covariates effect all algorithms in the same way and to the same degree. To highlight one specific effect, there is evidence that verification systems should enroll sub jects with smiling rather than neutral expressions for best performance.
face recognition, performance analysis, statistical modeling, subject covariates
, Beveridge, J.
, Givens, G.
and Draper, B.
Factors that Influence Algorithm Performance, Computer Vision and Image Understanding, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=890060
(Accessed December 11, 2023)