Robust Face Recognition Using Advanced Correlation Filters with Bijective-Mapping Preprocessing

摘要

In this paper we explore performing robust face verification using Advanced Correlation Filters on Bijective-Mapping preprocessed face images. We show that using the proposed Bijective-Mapping preprocessing method we can increase verification performance (at 0.1% FAR) significantly in our experiments using the Face Recognition Grand Challenge (FRGC) database collected by the University of Notre Dame consisting of 152 subjects. This recognition experiment is challenging as the results reported on these experiments utilize only a single gallery image from each subject during the training phase and the probe images are captured in different time-lapsed sessions which vary mostly in pose and facial expression.