Face verification using second orders polynomial correlation filters

Face verification is a critical task for individual authentication, e-commerce applications and security purpose. Correlation filtering has recently been reintroduced to the facial verification domain. In This paper we utilize polynomial correlation filter (PCF) based on unconstrained minimum average correlation energy (UMACE). The performance of UMACE-PCF is evaluated using YALE B database. A comparison of verification performance between the second orders of UMACE-PCF and UMACE filter is also presented.